Self-improving adaptive instructional systems can select and generate moral stories, scenarios, or cases to discuss with individuals and teams. Man-machine literature discussions about moral stories could provide value both to individuals (Goldenberg, 1992) and to artificial-intelligence systems (Sinatra, Graesser, Hu, Brawner, & Rus, 2019; Tong & Hu, 2024).
Self-improving adaptive instructional systems model users, both learners and experts. These models can be more generic, or stereotype-based, or more specific and highly adaptive.
User models can be of use for intelligently selecting, generating, distributing, and administering moral stories across populations to maximize value both for users and artificial-intelligence systems.
Beyond presenting users with adaptive and personalized sequences of questions about moral stories, artificial-intelligence systems can, increasingly, participate in more interesting, engaging, and enriching man-machine literature discussions.
While the discourse of reading groups has previously been explored (Peplow, Swann, Trimarco, & Whitely, 2015), man-machine literature discussions and co-reading are comparably new terrain.
To increase the value of resultant educational data, techniques from opinion polling, survey design, and questionnaire construction could be of use during literature discussions. Pertinent topics would include avoiding leading questions or loaded questions, and having a mindfulness of the framing of questions, context effects, and item-sequencing effects.
When artificial-intelligence systems generate moral stories, they could also generate agentic workflows, or "scripts", describing the processes with which to discuss the stories and how to intersperse questions or testlets. Discussion questions for readers can be presented to them in the middles of reading moral stories, e.g., at section or chapter boundaries, and upon stories' completions.
Agentic workflows, or "scripts", can include branching points. There could be multiple paths available both through them and accompanying testlets.
Artificial-intelligence systems can generate stories in order to accomplish specified pedagogical objectives. Specified pedagogical objectives should be preserved and accompany generated story items, alongside other artifacts produced during story generation, as metadata to simplify story understanding, analysis, and evaluation.
Descriptions of intended audiences can also be provided to story generators. These input data would allow generated moral stories to be developmentally appropriate with respect to their subject matter, grammar, and vocabulary (Valentini, Weber, Salcido, Wright, Colunga, & Kann, 2023).
Moral stories present readers with situations in story contexts about which moral reasoning and discussion occur. Meanwhile, values can be both general and context-specific with respect to alignment (Liscio, van der Meer, Siebert, Jonker, & Murukannaiah, 2022).
Components could be created for modeling aspects of story comprehension during, in the middles of, unfolding stories. Predictions, then, could be made with respect to readers' responses to those moral situations occurring in those contexts presented by stories.
Different stories about identical moral themes can cause different distributions of responses and discussions.
Over the course of time, provided with adequate data, artificial-intelligence systems could discern and learn causal relationships between the types, meanings, structures, devices, forms, and effects of moral stories.
Artificial-intelligence systems can self-improve with respect to both the generation and execution of agentic workflows, or "scripts".
Components for the generation, understanding, analysis, and evaluation of moral stories can self-improve. In these regards, perhaps forms of A/B and multivariate testing could occur as systems exploited and explored variations in moral stories and literature discussions to achieve pedagogical objectives.
In artificial intelligence, value-alignment challenges include how to align artificial-intelligence systems to sets of values and how to determine which to do so for (Gabriel, 2020).
Artificial-intelligence systems can learn from and be aligned to values from moral stories (Riedl & Harrison, 2016; Emelin, Le Bras, Hwang, Forbes, & Choi, 2020; Nahian, Tasrin, Frazier, Riedl, & Harrison, 2025).
Man-machine literature discussions about selected or generated moral stories can also provide value to artificial-intelligence systems. Research is underway into mining human tutorial discussions (Maharjan, Rus, & Gautam, 2018; Lin, Singh, Sha, Tan, Lang, Gašević, & Chen, 2022) and these techniques will be increasingly useful for analyzing and learning from transcripts of man-machine discussions.
Artificial-intelligence systems will be able to select and generate moral stories to engage in man-machine literature discussions, continuously learning from experts while tutoring learners.
Instead of attempting to train a morally absolutist artificial-intelligence system, systems could be trained to be increasingly capable of adopting a variety of ideological stances, positions, perspectives, schools of thought, and wisdom traditions. Resultant pluralist systems could, then, be prompted to perform moral reasoning and to engage in dialogue from described personas (Shanahan, McDonell, & Reynolds, 2023; Kovač, Portelas, Sawayama, Dominey, & Oudeyer, 2024).
In addition to single artificial-intelligence systems capable of performing many personas, components can be envisioned which can route descriptions of personas to those other models most capable of performing them.
Multi-agent systems can be of use for: intelligent tutoring (Šarić-Grgić, Grubišić, Stankov, & Štula, 2019); representing personas capable of performing reasoning and dialogue from differing ideological stances, positions, perspectives, schools of thought, and wisdom traditions; contextual value alignment (Dognin, Rios, Luss, Padhi, Riemer, Liu, Sattigeri, Nagireddy, Varshney, & Bouneffouf, 2024); story generation (Huot, Amplayo, Palomaki, Jakobovits, Clark, & Lapata, 2024); literature discussions; and otherwise modeling and simulating both learners and experts.
Teams of specialized technical personnel could operate self-improving adaptive instructional systems, review automatically-generated story items, monitor unfolding performance metrics pertaining to story items, and monitor real-time analytics dashboards pertaining to the administering of testlets and to the literature discussions between artificial-intelligence systems and populations of learners and experts.
Learners' parents, teachers, teaching assistants, guidance counselors, and school administrators could be provided with means of engaging with educational artificial-intelligence systems, e.g., using multimodal dialogue enhanced by data visualizations and analytics dashboards.
Self-improving adaptive instructional systems can select and generate moral stories, scenarios, or cases to discuss with individuals and teams. Man-machine literature discussions about moral stories could provide value both to individuals and to artificial-intelligence systems.
Artificial-intelligence systems will be able to select and generate moral stories to engage in man-machine literature discussions, continuously learning from experts while tutoring learners.
One secondary benefit of the architectural approaches considered and discussed above is that, with the same components, users would be able to narrate real-world or hypothetical scenarios to artificial-intelligence systems, these serving as the stories for discussion, and to select or describe personas to interact with.
Dognin, Pierre, Jesus Rios, Ronny Luss, Inkit Padhi, Matthew D. Riemer, Miao Liu, Prasanna Sattigeri, Manish Nagireddy, Kush R. Varshney, and Djallel Bouneffouf. "Contextual moral value alignment through context-based aggregation." arXiv preprint arXiv:2403.12805 (2024).
Emelin, Denis, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes, and Yejin Choi. "Moral stories: Situated reasoning about norms, intents, actions, and their consequences." arXiv preprint arXiv:2012.15738 (2020).
Gabriel, Iason. "Artificial intelligence, values, and alignment." Minds and Machines 30, no. 3 (2020): 411-437.
Goldenberg, Claude. "Instructional conversations: Promoting comprehension through discussion." The Reading Teacher 46, no. 4 (1992): 316-326.
Huot, Fantine, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, and Mirella Lapata. "Agents' room: Narrative generation through multi-step collaboration." arXiv preprint arXiv:2410.02603 (2024).
Kovač, Grgur, Rémy Portelas, Masataka Sawayama, Peter Ford Dominey, and Pierre-Yves Oudeyer. "Stick to your role! Stability of personal values expressed in large language models." arXiv preprint arXiv:2402.14846 (2024).
Lin, Jionghao, Shaveen Singh, Lele Sha, Wei Tan, David Lang, Dragan Gašević, and Guanliang Chen. "Is it a good move? Mining effective tutoring strategies from human–human tutorial dialogues." Future Generation Computer Systems 127 (2022): 194-207.
Liscio, Enrico, Michiel T. van der Meer, Luciano C. Siebert, Catholijn M. Jonker, and Pradeep K. Murukannaiah. "What values should an agent align with? An empirical comparison of general and context-specific values." Autonomous Agents and Multi-Agent Systems (2022).
Maharjan, Nabin, Vasile Rus, and Dipesh Gautam. "Discovering effective tutorial strategies in human tutorial sessions." In The Thirty-First International Flairs Conference (2018).
Nahian, Md Sultan Al, Tasmia Tasrin, Spencer Frazier, Mark Riedl, and Brent Harrison. "The Goofus & Gallant story corpus for practical value alignment." arXiv preprint arXiv:2501.09707 (2025).
Peplow, David, Joan Swann, Paola Trimarco, and Sara Whiteley. The Discourse of Reading Groups: Integrating Cognitive and Sociocultural Perspectives. Routledge, (2015).
Riedl, Mark O., and Brent Harrison. "Using stories to teach human values to artificial agents." In Workshops at the Thirtieth AAAI Conference on Artificial Intelligence (2016).
Šarić-Grgić, Ines, Ani Grubišić, Slavomir Stankov, and Maja Štula. "An agent-based intelligent tutoring systems review." International Journal of Learning Technology 14, no. 2 (2019): 125-140.
Shanahan, Murray, Kyle McDonell, and Laria Reynolds. "Role-play with large language models." Nature 623, no. 7987 (2023): 493-498.
Sinatra, Anne M., Arthur C. Graesser, Xiangen Hu, Keith Brawner, and Vasile Rus, eds. Design Recommendations for Intelligent Tutoring Systems: Volume 7 - Self-improving Systems. US Army Research Laboratory, (2019).
Tong, Richard Jiarui, and Xiangen Hu. "Future of education with neuro-symbolic AI agents in self-improving adaptive instructional systems." Frontiers of Digital Education 1, no. 2 (2024): 198-212.
Valentini, Maria, Jennifer Weber, Jesus Salcido, Téa Wright, Eliana Colunga, and Katharina Kann. "On the automatic generation and simplification of children's stories." arXiv preprint arXiv:2310.18502 (2023).
Computational storyboarding builds upon traditional storyboarding techniques, combining elements from screenplays, storyboards, functions, diagrams, and animation.
Computational storyboards are intended to be of use as input for generative artificial-intelligence systems to create longer-form output video.
A motivating use case is simplifying the creation of educational videos, e.g., lecture videos. With computational storyboards, content creators could describe single-character stories where the main characters were tutors instructing audiences with respect to provided subject matter, utilizing boards or screens displaying synchronized multimedia content from textbooks, encyclopedia articles, or slideshow presentations.
A screenplay is a form of narration in which the movements, actions, expressions, and dialogue of characters are described in a certain format. Visual and cinematographic cues might also be given as well as scene descriptions and changes.
A storyboard is an organization technique consisting of illustrations or images, thumbnails, traditionally displayed in sequences. Storyboards have traditionally been used for pre-visualizing motion pictures, animations, motion graphics, and other interactive media sequences.
Storyboards' thumbnails have traditionally provided information about content layering, audio and sound effects, camera shots, character shots, transitions between scenes, and more.
In theory, nodes in diagrammatic computational storyboards could refer to other diagrams by URLs, weaving webs of interconnected diagrams. End-users could click on these referring nodes to expand them, loading referenced content from URL-addressable resources into diagrams.
Computational storyboard diagrams could be collaboratively editable, enabling wiki platforms.
Functions would enable modularity and the reuse of storyboard content. Beyond referring to other diagrams by URLs, function-calling nodes in computational storyboard diagrams could refer to function-like diagrams by URLs while invoking and passing arguments to them.
With computational storyboarding functions, scenes’ characters, settings, props, actions, dialogue, and properties of these could all be parameterized.
Arguments provided to invoked functions could be in the form of multimedia content, structured objects, or text. Arguments and variables in functions could be used to create the prompts to be provided to generative artificial-intelligence systems including those prompts with which to generate thumbnails' images.
Markers, resembling keykodes or timecodes, could be placed between thumbnails in computational storyboard diagrams. Alternatively, some or all of the thumbnails could be selected to serve as referenceable markers, keykodes, or timecodes in resultant video. With markers, content creators could refer to instants or intervals of video generated from invoked functions.
Components in computational storyboard diagrams could be annotated with metadata.
Functions, for instance, could be annotated with metadata describing one or more sample argument sequences. In this way, content creators could have options for generating thumbnails' images while designing.
With respect to computational storyboarding functions and their diagrams, there are two varieties of control-flow constructs to consider.
A first variety of control-flow construct would route execution at runtime to paths of subsequent thumbnails. Such branching could occur either based upon the evaluation of expressions involving input arguments and variables or upon asking questions of interoperating artificial-intelligence systems.
A second variety of control-flow construct would result in branching or interactive video output, with routes or paths to be selected by viewers during playback. Generated interactive video content could interface with playback environments, e.g., in Web browsers, to provide viewers with features. Uses of interactive video include providing viewers with options, e.g., navigational menus.
While computational storyboards were executed or run to generate video, execution contexts, these building on the concepts of “call stacks”, could be utilized. Execution contexts would include nested frames, these building on the concepts of “stack frames”, which would each include those active nodes in functions' diagrams and those values of their input arguments and variables.
In addition to computational storyboards' functions providing their diagrammatic contents with their input arguments and variables, functions could contain nodes for obtaining “random values” from specified numerical intervals or, perhaps, for randomly selecting from nodes in containers.
Random variation could, optionally, be utilized by content creators to vary resultant video.
In theory, beyond using “random values” to simply vary generated video contents, diagram nodes for providing “automatic values” could be used to provide values, either scalars from intervals or selections from nodes in containers, which were intended to be optimized across multiple executions or runs while observations and data were collected.
As envisioned, developing and providing these components for computational storyboarding diagrams would simplify A/B testing and related techniques for content creators.
As considered, at least some computational storyboards’ thumbnails would have their images created by generative artificial-intelligence systems. Multimodal prompts, in these regards, could be varied including by using functions’ input arguments and variables.
A goal for computational storyboards is that generative artificial-intelligence systems could process them into longer-form video content.
Towards this goal, computational storyboards could provide materials beyond extensible thumbnails for generative artificial-intelligence systems. Notes about directing, cinematography, and characters or acting could be provided to systems. Multimedia materials with respect to characters, settings, props, and style could be provided to systems. That content intended to be synchronized and placed onto one or more display surfaces in generated video could be provided to systems.
Generated videos could utilize one or more tracks to enable features in playback environments. Transcripts or captions, for instance, alongside accompanying metadata track items, could be sent to viewers' artificial-intelligence assistants for these systems to be able to answer questions about videos’ contents.
With respect to generating video from computational storyboards, there could exist a “debugging” mode. When generated from such a mode, output video would contain extra metadata tracks providing objects for content creators to utilize to be able to jump into computational storyboards resumed to appropriate execution contexts for points of interest in the generated videos.
In theory, existing video content could be processed into computational storyboards.
Envisioned computational storyboards build on traditional storyboarding techniques while intending to enable generative artificial-intelligence systems to create longer-form output video, e.g., educational video.
Today, research is underway into aiding and automating scientific and scholarly research processes. Zhang, Pearson, and Wang (2024) discuss automated scientific research in the form of literature reviews. Kang and Xiong (2024) have developed a benchmark for measuring artificial-intelligence systems’ capabilities with respect to conducting academic surveys.
In the not-too-distant future, artificial-intelligence systems will be capable of performing some historical research tasks. This kind of research is expounded upon by Schrag (2021) and has its own particular caveats and fallacies, including those listed by Fischer (1970).
Historical research should begin with questions. With respect to historical research, there are “who”, “what”, “where”, and “when” factual questions and also “why”, “how”, and “with-what-consequences” interpretive questions. Historians tend to explore factual questions while addressing overarching interpretive questions.
Historical research questions should be carefully framed and, in these regards, Fischer (1970) enumerates the following pertinent fallacies: the Baconian fallacy; many questions; false dichotomous questions; metaphysical questions; fictional questions; semantical questions; declarative questions; counterquestions; tautological questions; contradictory questions; and “potentially verifiable” questions.
In addition to these fallacies, there are also to be wary of: deceptively-simple questions; impossible-to-answer questions; opinion questions; ethical questions; anachronistic questions; and non-historical questions.
When faced with problematic questions, history-educational question-answering systems could, instead of conducting automated historical research and answering them, provide relevant search engine results.
Technologies exist today for both manually and automatically fact-checking content using core sets of sources (e.g., history books, history textbooks, or encyclopedias), including when the content references a wider set of sources.
One example of such a technology is Citation Needed, a Web-browser extension developed by the Wikimedia Foundation’s Future Audiences team. It allows end-users to fact-check selections of content using Wikipedia articles as a core set of sources.
When content, or important assertions and claims therein, cannot be automatically corroborated by a core set of sources, systems could enqueue that content for more elaborate algorithms to process or for human personnel to review.
Multi-agent systems could contribute to and perform the same group processes through which encyclopedic articles are co-created (Kopf, 2022). Agents could co-write and revise answers to historical questions, historical essays, and long-form historical documents.
Interestingly, man-machine interactions, such as debate and consensus-building, could result in automatic modifications or revisions to systems’ output documents.
Narratives are critical to communicating historical knowledge (Munslow, 2018). Artificial-intelligence systems will, increasingly, be able to aid and automate the co-creation of research-based, multimodal historical stories and works of historical fiction.
Kindenberg (2024) recently compared artificial-intelligence generated and student-written historical narratives and found that artificial-intelligence generated stories tended to convey less emotion.
Past and present approaches to automatic story generation were surveyed by Alhussain and Azmi (2021). Research is unfolding with respect to multi-agent multimodal story generation (Arif, Arif, Khan, Haroon, Raza, & Athar, 2024; Hout, Amplayo, Palomaki, Jakobovits, Clark, & Lapata, 2024).
Recently, Laney and Dewan (2024) explored instructor-mediated man-machine interactions in educational structured forums, specifically class discussion boards. Artificial-intelligence agents supported teaching assistants in answering students’ questions.
In the near future, artificial-intelligence agents participating in structured forums will be able to follow end-users’ instructions to perform tasks and subtasks including answering historical questions and conducting historical research and writing.
Beyond idly awaiting questions and instructions from end-users, artificial-intelligence agents could proactively examine unfolding discussions to produce and provide suggestions with respect to how they might be of assistance.
Processes mediated and explicated by structured forums can be assessed and evaluated, processes involving historical thinking and reasoning (Van Drie & Van Boxtel, 2008; Bertram, Weiss, Zachrich, & Ziai, 2021), the co-creation of documents (Kopf, 2022), debate (Ulrich, 1986), and consensus-building (Lehrer & Wagner, 2012).
In the not-too-distant future, artificial-intelligence technologies will be able to aid and to automate the assessment and evaluation of historical research, reasoning, discussion, and writing processes mediated and explicated by structured forums.
Alhussain, Arwa I., and Aqil M. Azmi. "Automatic story generation: A survey of approaches." ACM Computing Surveys (CSUR) 54, no. 5 (2021): 1-38.
Arif, Samee, Taimoor Arif, Aamina Jamal Khan, Muhammad Saad Haroon, Agha Ali Raza, and Awais Athar. "The art of storytelling: Multi-agent generative AI for dynamic multimodal narratives." arXiv preprint arXiv:2409.11261 (2024).
Bertram, Christiane, Zarah Weiss, Lisa Zachrich, and Ramon Ziai. "Artificial intelligence in history education. Linguistic content and complexity analyses of student writings in the CAHisT project (Computational assessment of historical thinking)." Computers and Education: Artificial Intelligence (2021): 100038.
Fischer, David Hackett. Historians' fallacies: Toward a logic of historical thought. 1970.
Huot, Fantine, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, and Mirella Lapata. "Agents' room: Narrative generation through multi-step collaboration." arXiv preprint arXiv:2410.02603 (2024).
Kang, Hao, and Chenyan Xiong. "ResearchArena: Benchmarking LLMs' ability to collect and organize Information as research agents." arXiv preprint arXiv:2406.10291 (2024).
Kindenberg, Björn. "ChatGPT-generated and student-written historical narratives: A comparative analysis." Education Sciences 14, no. 5 (2024): 530.
Kopf, Susanne. A discursive perspective on Wikipedia: More than an encyclopaedia?. Springer Nature, 2022.
Laney, Mason, and Prasun Dewan. "Human-AI collaboration in a student discussion forum." In Companion Proceedings of the 29th International Conference on Intelligent User Interfaces, pp. 74-77. 2024.
Lehrer, Keith, and Carl Wagner. Rational consensus in science and society: A philosophical and mathematical study. Vol. 24. Springer Science & Business Media, 2012.
Munslow, Alun. Narrative and history. Bloomsbury Publishing, 2018.
Schrag, Zachary. The Princeton guide to historical research. Princeton University Press, 2021.
Ulrich, Walter. Judging academic debate. National Textbook Company, 1986.
Van Drie, Jannet, and Carla Van Boxtel. "Historical reasoning: Towards a framework for analyzing students’ reasoning about the past." Educational Psychology Review 20 (2008): 87-110.
Zhang, Starkson, Alfredo Pearson, and Zhenting Wang. "Autonomous generalist scientist: Towards and beyond human-level automatic research using foundation model-based AI agents and robots (a position)." (2024).
Attention span is the amount of time that learners can spend concentrating on tasks. Sustained attention develops through childhood and into adulthood, with a period of accelerated development occurring during early and middle childhood (Slattery, O’Callaghan, Ryan, Fortune, & McAvinue, 2022).
Attention training is a part of education. Learners are trained to remain focused on discussion topics for extended periods of time and to develop listening and analytical skills in the process. For over a century, there has been keen interest in improving children’s attention in educational contexts.
Adaptive instructional systems, a comparably recent development, adapt instruction based upon learners’ states of engagement, arousal, motivation, prior knowledge, anxiety, and engaged concentration (Sottilare & Goodwin, 2017).
A tutoring strategy for learners in states of engaged concentration might be to “do nothing” because they would already be in ideal states for learning. However, a longer-term tutoring strategy might be to strengthen learners’ capabilities to maintain their states of sustained attention and concentration.
How can adaptive instructional systems scheduling learners’ homework items contribute to increasing their attention spans and concentration?
Computer-administered and strategically, adaptively scheduled educational exercises and activities could be organized into gamified sprints, each sprint containing one or more stages. Learners would be encouraged to only take a break from or to conclude their schoolwork at the completion of a sprint stage and not in the middle of one.
To encourage the sustained, uninterrupted completion of schoolwork, the gamification could be such that a learner would have to repeat an entire sprint stage from the beginning – though not necessarily with the exact same items – if they didn’t finish it before taking a break or concluding. That is, checkpoints or save points could be provided only after sprint stages.
Adaptive instructional systems would control when sprints were presented to learners, the number of stages and items that would be in each, and their other properties including whether or not they would have countdown timers for successful completions. Informed by models of learners, adaptive instructional systems would be able to create and to utilize sprints to encourage capable learners to complete just one more item or just a few more items.
The goal posts for individual learners’ daily and weekly educational exercises and activities would be placed by adaptive instructional systems to be, on average, just a bit ahead of their comfort zones but within their performance capabilities.
What differentiates homework items from one another in terms of their attentional, concentrative, and other cognitive demands? For each item, for each learner, for a pace of progression, which cognitive reservoirs are depleted and to which extents? At which rates do individual learners’ various cognitive reservoirs replenish? Which cognitive reservoirs exist alongside redundant others, and which do not?
Cognitive load can be defined as a multidimensional construct representing the load that performing a particular task imposes on a learner’s cognitive system. The construct has a causal dimension reflecting the interaction between task and learner characteristics and an assessment dimension reflecting the measurable concepts of mental load, mental effort, and performance. Task characteristics that have been identified in previous research include task format, task complexity, uses of multimedia, time pressure, and the pacing of instruction (Paas, Tuovinen, Tabbers, & Van Gerven, 2003).
Xie and Salvendy (2000) distinguished between instantaneous load, peak load, accumulated load, average load, and overall load. Instantaneous load represents the dynamics of cognitive load, which fluctuate each moment that a learner works on a task. Peak load is the maximum value of instantaneous load while working on a task. Accumulated load is the total amount of load that a learner experiences during a task. Average load represents the mean intensity of load during the performance of a task. Overall load is the experienced load based on the whole working procedure or the mapping of instantaneous load or accumulated and average load in the learner’s brain.
Cognitive fatigue can be understood to be an “executive failure to maintain and optimize performance over acute but sustained cognitive effort resulting in performance that is lower and more variable than the individual’s optimal ability” (Holtzer, Shuman, Mahoney, Lipton, & Verghese, 2010). Cognitive fatigue typically develops gradually over time as a person engages in prolonged and demanding mental activities.
Cognitive fatigue may be assessed either subjectively or objectively. Subjective cognitive fatigue involves learners’ perceptions of their exhaustion. Objective cognitive fatigue is measured by changes in cognitive performance relative to a baseline (Karim, Pavel, Nikanfar, Hebri, Roy, Nambiappan, Jaiswal, Wylie, & Makedon, 2024).
While learners can express subjective cognitive fatigue to adaptive instructional systems at any point, considered, here, are automatically detecting learners’ instantaneous, accumulated, and overall cognitive load and objective cognitive fatigue as they progress through and complete strategically, adaptively scheduled homework items from one or more courses.
For over a century, there has been keen interest in improving children’s attention in educational contexts. There have been, thus far, three broad approaches to strengthening attention: attention network training, attention state training, and attention strategy training.
The first approach, attention network training – also referred to as cognitive training or brain training – involves the repetitive practice of cognitive tasks specifically thought to exercise neural networks related to attention.
Adaptive instructional systems could, in theory, intersperse attention-related cognitive tasks into learners’ multi-course, multi-objective schedules of homework items. However, a review of 14 attention network training intervention studies from 1999 to 2021 found that these cognitive tasks, these approaches, did not reliably improve sustained attention capacity (Slattery, O’Callaghan, Ryan, Fortune, & McAvinue, 2022).
The second approach, attention state training, involves practice designed to train brain states thought to influence attention and other networks. Attention state training may also involve networks but, importantly, does not include cognitive tasks specifically designed to train attentional networks.
Adaptive instructional systems could strategically schedule homework items and incorporate gamification, e.g., sprints, to contribute to the strengthening of attention span and concentration. Such techniques can be used in combination with other attention state training activities such as physical activity and meditation. Adaptive instructional systems could also intersperse meditative and mindfulness activities during learners’ homework activities.
The third approach, strategy training, focuses on practicing strategies that momentarily boost attention.
With respect to adaptive instructional systems and gamification, previous works include explorations into uses of: avatars, badges, progress bars, levels, narratives / stories, special effects, non-player characters, tasks / quests, timers, leaderboards, bonuses / rewards / trophies / collectibles, points, roles, virtual currencies, and maps (Ramadhan, Warnars, & Razak, 2023; Seaborn & Fels, 2015).
Adaptive instructional systems can incorporate gamification to strategically, adaptively schedule learners’ homework items from one or more courses, e.g., into sprints, to motivate learners to sustain attention and concentration.
Over the course of time, these processes should increase learners’ capabilities to their maximum potentials. As a result, learners’ performances in other areas for which sustained attention and concentration are prerequisites should also tend to improve.
Holtzer, Roee, Melissa Shuman, Jeannette R. Mahoney, Richard Lipton, and Joe Verghese. "Cognitive fatigue defined in the context of attention networks." Aging, Neuropsychology, and Cognition 18, no. 1 (2010): 108-128.
Karim, Enamul, Hamza R. Pavel, Sama Nikanfar, Aref Hebri, Ayon Roy, Harish R. Nambiappan, Ashish Jaiswal, Glenn R. Wylie, and Fillia Makedon. "Examining the landscape of cognitive fatigue detection: A comprehensive survey." Technologies 12, no. 3 (2024): 38.
Paas, Fred, Juhani E. Tuovinen, Huib Tabbers, and Pascal W. M. Van Gerven. "Cognitive load measurement as a means to advance cognitive load theory." Educational Psychologist 38, no. 1 (2003): 63-71.
Ramadhan, Arief, Harco L. H. S. Warnars, and Fariza H. A. Razak. "Combining intelligent tutoring systems and gamification: A systematic literature review." Education and Information Technologies (2023): 1-37.
Seaborn, Katie, and Deborah I. Fels. "Gamification in theory and action: A survey." International Journal of Human-computer Studies 74 (2015): 14-31.
Slattery, Éadaoin J., Eoin O’Callaghan, Patrick Ryan, Donal G. Fortune, and Laura P. McAvinue. "Popular interventions to enhance sustained attention in children and adolescents: A critical systematic review." Neuroscience and Biobehavioral Reviews 137 (2022): 104633.
Sottilare, Robert A., and Gregory A. Goodwin. "Adaptive instructional methods to accelerate learning and enhance learning capacity." In International Defense and Homeland Security Simulation Workshop of the I3M Conference. 2017.
Xie, Bin, and Gavriel Salvendy. "Prediction of mental workload in single and multiple tasks environments." International Journal of Cognitive Ergonomics 4, no. 3 (2000): 213-242.
Agents representing ideological stances, positions, perspectives, or schools of thought can serve in multi-agent systems which generate encyclopedic answers to end-users' complex questions.
Large language models can generate content while role-playing, or impersonating, characters and personas (Shanahan, McDonell, & Reynolds, 2023). They can be fine-tuned using the works of individual philosophers to subsequently generate virtually indistinguishable responses (Schwitzgebel, Schwitzgebel, & Strasser, 2023). They can generate content from specified stances, positions, perspectives, and schools of thought. They can also generate content aligned with the attitudes and opinions of described groups, sub-populations, or demographics of interest (Santurkar, Durmus, Ladhak, Lee, Liang, & Hashimoto, 2023).
When should agents be searched for, retrieved, reused, designed, created, or varied? Which agents should be consulted when generating encyclopedic answers to end-users’ complex questions? Which agents’ responses would prove most valuable to consolidate, summarize, or synthesize into resultant encyclopedic answers? Should it be anticipated that selected teams of agents will recur across questions?
Automatically and manually designed agents, beyond potentially differing in terms of their models, training, fine-tuning, and prompts, could be provided with differing libraries of documents and could weigh, rank, or prioritize these documents differently.
Should agents and each of their libraries of documents be logically consistent and ideologically coherent? How should agents synthesize multiple challenging, potentially conflicting documents on complex issues and the arguments in them? Will these capabilities, additionally or instead, be emergent capabilities of orchestrated multi-agent systems?
Processes and strategies from multiple-text comprehension, reading group discussions, the Socratic method, the dialectic method, consensus building, group decision-making, and synthesis writing are anticipated to be of use to manager, facilitator, or moderator agents orchestrating teams of other agents, some representing individuals, groups, stances, positions, perspectives, or schools of thought.
Multiple-text comprehension results from processes and strategies with which readers make sense of complex topics or issues based on information presented in multiple texts. These processes and strategies are necessary when readers encounter multiple challenging, conflicting documents on complex issues (Anmarkrud, Bråten, & Strømsø, 2014; List & Alexander, 2017).
Reading group discussion strategies can enhance multiple readers’ comprehensions of texts. Transcripts from these multi-agent processes should prove valuable to consolidate, summarize, or synthesize (Goldenberg, 1992; Berne & Clark, 2008).
The principles and guidelines of the Socratic method include: the use of open-ended questions, clarifications of terms, providing examples and evidence, challenging arguments, summarization, drawing conclusions, and reflecting on the process. These key principles are realized through strategies such as: definition, generalization, induction, elenchus, hypothesis elimination, maieutics, dialectic, recollection, irony, and analogy (Chang, 2023).
The dialectic method involves dialogues between groups holding different points of view about subjects but wishing to arrive at truths through reasoned argumentation. With respect to multi-agent systems, formal, computational, and game-theoretic approaches have been and remain topics of ongoing research (Wells, 2007). The advancement of large-language-model-based agents has inspired a renewed interest in multi-agent argumentation and debate (Du, Li, Torralba, Tenenbaum, & Mordatch, 2023; Wang, Yue, & Sun, 2023; Wang, Du, Yu, Chen, Zhu, Chu, Yan, & Guan, 2023).
Processes which to build rational consensus and related decision-making procedures may be brought to bear during the orchestration of multi-agent systems (Lehrer & Wagner, 2012).
Synthesis writing is a set of processes and strategies through which the contents of multiple texts, including agent-generated contents, can be integrated into resultant output texts (Van Ockenburg, van Weijen, & Rijlaarsdam, 2019; Van Steendam, Vandermeulen, De Maeyer, Lesterhuis, Van den Bergh, & Rijlaarsdam, 2022). Argumentative synthesis writing combines intratextual and intertextual integration processes and strategies to generate texts from diverse sources, perspectives, and arguments (Mateos, Martín, Cuevas, Villalón, Martínez, & González-Lamas, 2018).
In particular when multi-agent systems encounter conflicting information in libraries of documents, a best possible answer might not be one providing a single alternative determined from group deliberation processes, but one providing a list of top alternatives where each could have available its supporting justification and opposing argumentation. Manager, facilitator, or moderator agents orchestrating teams of other agents could be expected to be capable of detecting and determining when these situations arise, when one alternative should prevail from unfolding group deliberation and when a list of top alternatives is, instead, the answer.
Teams of agents could search for, retrieve and reuse, or generate new documents and multimedia subcomponents combining natural language, structured knowledge, source code, multimedia, charts, diagrams, and infographics.
Hypermedia encyclopedia articles tend to result from hypertext layouts containing multimedia subcomponents. Some of these multimedia subcomponents could result from generative computation upon input prompts.
Approaches to consider include uses of planners to orchestrate agentic systems to search for, retrieve and reuse, or generate new layouts and content-related plans (Bao, 2023; Qiao, Li, Zhang, He, Kang, Zhang, Yang, et al., 2023; Wu, Bansal, Zhang, Wu, Zhang, Zhu, Li, Jiang, Zhang, & Wang, 2023).
Macroplans could be provided to manager, facilitator, or moderator agents and to groups of subordinate agents. Agents in these teams could either: (1) interact with one another via exchanging messages, or (2) interact with one another via forum software.
The production, preservation, aggregation, analysis, and maintenance of citations to referenced materials through these processes could be subjects of continuing research (Gao, Yen, Yu, & Chen, 2023).
Specialized agents could be invoked to produce kinds of "computational-notebook cells" containing prompts from which multimedia subcomponents could be searched for, retrieved and reused, or generated (Dibia, 2023).
Furthermore, documents and their multimedia subcomponents, in particular those subcomponents generated from prompts, could be subsequently editable. Each subcomponent could have its own changelog, or revision history, and discussion area.
Transcripts of multi-agent processes could be preserved and accompany resultant documents and their subcomponents. These transcripts could be forum-based, having multiple threads of structured discussions, or could be more intricate.
People and artificial-intelligence agents could interact in these multi-threaded, structured discussion forums or collaboration spaces. Man-machine interactions could potentially result in automatic updates to generated documents or to their multimedia subcomponents.
Automatically-generated content could include hyperlinks, context menu items, or other means of navigating from portions of content to any relevant argumentation or procedures in the accompanying multi-threaded, structured discussion forums or collaboration spaces.
Changelogs or revision histories could accompany documents and their subcomponents. People and artificial-intelligence agents could provide rationale, explanations, or justifications in them for modifications made to reusable, revisable documents and their subcomponents.
People could be provided with opportunities to provide structured feedback or open-ended, natural-language comments about portions of documents, sections, paragraphs, sentences, or content selections, and about other document subcomponents. These feedback, comments, and annotations could be displayed for only those opting into viewing them or quality-filtered subsets. When displayed, these could be expandable margin notes proximate to relevant document content.
People desiring to provide feedback or comments about document could additionally be provided with opportunities to interact with dialogue systems conducting contextual and adaptive surveys and opinion polls.
How should encyclopedic answers to end-users’ complex questions be evaluated? How should agents’ performances in coordinated dialogues, debates, and processes be evaluated? How should their contributions to collaborative document-generation processes be evaluated?
With evaluation frameworks and rubrics, components of automatically or manually designed and varied agents could be independently measured and compared. These kinds of scientific architectures could empower teams of humans to continuously improve multi-agent systems.
Large language models have been evaluated with respect to their exhibited moral beliefs (Scherrer, Shi, Feder, & Blei, 2023).
Algorithmic fidelity is defined to be the degree to which the complex patterns of relationships between ideas, attitudes, and socio-cultural contexts within a model accurately mirror those within a range of human sub-populations (Argyle, Busby, Fulda, Gubler, Rytting, & Wingate, 2023).
Value stability, the adherence to roles, characters, or personas during unfolding interactions, is argued to be another dimension of large language model comparison and evaluation alongside knowledge, model size, and speed (Kovač, Portelas, Sawayama, Dominey, & Oudeyer, 2024).
With respect to resultant encyclopedic answers, desired qualities include: verifiability and accuracy, objectivity, and neutrality, plurality, diversity, fairness, balance, and comprehensiveness with respect to relevant points of view (McGrady, 2020).
Socratic assistants have been explored for both moral enhancement and educational purposes (Lara & Deckers, 2020). The manager, facilitator, or moderator agents, discussed above, could coordinate teams comprised of artificial-intelligence agents, humans, or combinations of both.
Artificial intelligence systems for facilitation with respect to group meetings and discussions have been previously researched in the form of group support systems (Bostrom, Anson, & Clawson, 1993).
Educational applications of the technologies under discussion include intelligent tutoring systems for teams (Sottilare, Burke, Salas, Sinatra, Johnston, & Gilbert, 2018) and artificial-intelligence-enhanced pedagogical discussion forums (Butcher, Read, Jensen, Morel, Nagurney, & Smith, 2020).
Artificial intelligence systems capable of debating with humans are a subject of ongoing research (Slonim, Bilu, Alzate, Bar-Haim, Bogin, Bonin, & Choshen, 2021).
Modular systems containing multiple interlocutors, each with their own distinct points of view reflecting their training in a diversity of concrete wisdom traditions, have been previously considered (Volkman & Gabriels, 2023).
Anmarkrud, Øistein, Ivar Bråten, and Helge I. Strømsø. "Multiple-documents literacy: Strategic processing, source awareness, and argumentation when reading multiple conflicting documents." Learning and Individual Differences 30 (2014): 64-76.
Argyle, Lisa P., Ethan C. Busby, Nancy Fulda, Joshua R. Gubler, Christopher Rytting, and David Wingate. "Out of one, many: Using language models to simulate human samples." Political Analysis 31, no. 3 (2023): 337-351.
Bao, Yunqian. "Towards automated generation of open domain Wikipedia articles." Master's thesis, University of Illinois at Urbana-Champaign, 2023.
Berne, Jennifer I., and Kathleen F. Clark. "Focusing literature discussion groups on comprehension strategies." The Reading Teacher 62, no. 1 (2008): 74-79.
Bostrom, Robert P., Robert Anson, and Vikki K. Clawson. "Group facilitation and group support systems." Group support systems: New perspectives 8 (1993): 146-168.
Butcher, Tamarin, Michelle Fulks Read, Ann Evans Jensen, Gwendolyn M. Morel, Alexander Nagurney, and Patrick A. Smith. "Using an AI-supported online discussion forum to deepen learning." In Handbook of research on online discussion-based teaching methods, pp. 380-408. IGI Global, 2020.
Chang, Edward Y. "Prompting large language models with the Socratic method." In 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), pp. 0351-0360. IEEE, 2023.
Dibia, Victor. "Lida: A tool for automatic generation of grammar-agnostic visualizations and infographics using large language models." arXiv preprint arXiv:2303.02927 (2023).
Du, Yilun, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. "Improving factuality and reasoning in language models through multiagent debate." arXiv preprint arXiv:2305.14325 (2023).
Gao, Tianyu, Howard Yen, Jiatong Yu, and Danqi Chen. "Enabling large language models to generate text with citations." arXiv preprint arXiv:2305.14627 (2023).
Goldenberg, Claude. "Instructional conversations: Promoting comprehension through discussion." The Reading Teacher 46, no. 4 (1992): 316-326.
Kovač, Grgur, Rémy Portelas, Masataka Sawayama, Peter Ford Dominey, and Pierre-Yves Oudeyer. "Stick to your role! Stability of personal values expressed in large language models." arXiv preprint arXiv:2402.14846 (2024).
Lara, Francisco, and Jan Deckers. "Artificial intelligence as a Socratic assistant for moral enhancement." Neuroethics 13, no. 3 (2020): 275-287.
Lehrer, Keith, and Carl Wagner. Rational consensus in science and society: A philosophical and mathematical study. Vol. 24. Springer Science & Business Media, 2012.
List, Alexandra, and Patricia A. Alexander. "Analyzing and integrating models of multiple text comprehension." Educational Psychologist 52, no. 3 (2017): 143-147.
Mateos, Mar, Elena Martín, Isabel Cuevas, Ruth Villalón, Isabel Martínez, and Jara González-Lamas. "Improving written argumentative synthesis by teaching the integration of conflicting information from multiple sources." Cognition and Instruction 36, no. 2 (2018): 119-138.
McGrady, Ryan Douglas. Consensus-based encyclopedic virtue: Wikipedia and the production of authority in encyclopedias. North Carolina State University, 2020.
Qiao, Bo, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, et al. "TaskWeaver: A code-first agent framework." arXiv preprint arXiv:2311.17541 (2023).
Santurkar, Shibani, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. "Whose opinions do language models reflect?." arXiv preprint arXiv:2303.17548 (2023).
Scherrer, Nino, Claudia Shi, Amir Feder, and David Blei. "Evaluating the moral beliefs encoded in LLMs." Advances in Neural Information Processing Systems 36 (2023).
Schwitzgebel, Eric, David Schwitzgebel, and Anna Strasser. "Creating a large language model of a philosopher." arXiv preprint arXiv:2302.01339 (2023).
Shanahan, Murray, Kyle McDonell, and Laria Reynolds. "Role-play with large language models." Nature 623, no. 7987 (2023): 493-498.
Slonim, Noam, Yonatan Bilu, Carlos Alzate, Roy Bar-Haim, Ben Bogin, Francesca Bonin, Leshem Choshen, et al. "An autonomous debating system." Nature 591, no. 7850 (2021): 379-384.
Sottilare, Robert A., C. Shawn Burke, Eduardo Salas, Anne M. Sinatra, Joan H. Johnston, and Stephen B. Gilbert. "Designing adaptive instruction for teams: A meta-analysis." International Journal of Artificial Intelligence in Education 28 (2018): 225-264.
Van Ockenburg, Liselore, Daphne van Weijen, and Gert Rijlaarsdam. "Learning to write synthesis texts: A review of intervention studies." Journal of Writing Research 10, no. 3 (2019): 401-428.
Van Steendam, Elke, Nina Vandermeulen, Sven De Maeyer, Marije Lesterhuis, Huub Van den Bergh, and Gert Rijlaarsdam. "How students perform synthesis tasks: An empirical study into dynamic process configurations." Journal of Educational Psychology 114, no. 8 (2022): 1773.
Volkman, Richard, and Katleen Gabriels. "AI moral enhancement: Upgrading the socio-technical system of moral engagement." Science and Engineering Ethics 29, no. 2 (2023): 11.
Wang, Boshi, Xiang Yue, and Huan Sun. "Can ChatGPT defend its belief in truth? Evaluating LLM reasoning via debate." In Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 11865-11881. 2023.
Wang, Haotian, Xiyuan Du, Weijiang Yu, Qianglong Chen, Kun Zhu, Zheng Chu, Lian Yan, and Yi Guan. "Apollo's oracle: Retrieval-augmented reasoning in multi-agent debates." arXiv preprint arXiv:2312.04854 (2023).
Wells, Simon. "Formal dialectical games in multiagent argumentation." PhD thesis, University of Dundee, 2007.
Wu, Qingyun, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. "AutoGen: Enabling next-gen LLM applications via multi-agent conversation framework." arXiv preprint arXiv:2308.08155 (2023).
Wise people share advice and wisdom in the forms of allegories, anecdotes, aphorisms, apologues, fables, folklore, historical analogues, jokes, literature, lyrics, parables, poems, proverbs, quotations, stories, and witticisms. It is a multidisciplinary challenge to build artificial intelligence systems capable of these tasks.
Towards solving this challenge, a new approach is presented: story-based search and recommendation. In this approach, individuals provide stories to retrieve content that is to be useful for selected story characters. The stories they provide could be real-world stories and the characters they select, in these cases, could be themselves or other people. Interestingly, individuals’ social media posts and feeds could be of similar use for establishing contexts for search and recommendation.
While the comprehension of story and social situations are key to the contextual search for and recommendation of advice and wisdom, there is a need for overarching architectures, frameworks, and models for artificial intelligence systems to best do so at scale. Intelligent coaching systems are indicated to be of use in these regards.
Search and recommender system approaches are considered here, in addition to dialogue systems and chatbots, because intelligent coaching systems, at scale, are envisioned as extensively reusing items, e.g., messages of advice, rather than utilizing natural-language generation algorithms to contextually produce new such messages for individuals in an on-the-fly manner.
Applications of the technologies under discussion include social media, education, library and information science, knowledge management, and history.
In story-based search and recommendation, individuals provide stories to retrieve content that is to be useful for selected story characters. These provided stories can be fictional or real-world stories.
Use case scenarios for fictional stories include their uses in training, testing, and evaluation. These datasets could utilize metadata for indicating stories’ reading levels and other developmental narratological factors.
Use case scenarios for real-world stories include those where individuals seek to retrieve content for themselves and those where individuals, e.g., peers, teachers, or guidance counselors, seek to retrieve content for other individuals or audiences.
Stories provide a natural means of establishing cognitive contexts. Viewing them in this way, active or conversational story comprehension can be considered. Narratees can ask questions of narrators during conversational processes of narration. Vague or partial cognitive story comprehension contexts can inform narratees’ processes of forming questions for narrators about unfolding narratives.
In incremental story-based search and recommendation, individuals engage in dialogues, narrating to artificial intelligence systems, and receive dynamically updating lists of recommended content for selected story characters. These recommended items could include question items and individuals could select these to have systems ask them them in unfolding dialogues. As individuals narrate to and answer questions from artificial intelligence systems incrementally comprehending their stories, content recommendations for selected characters would be provided.
In order for artificial intelligence systems to be able to search for and recommend content for selected characters in provided stories, these systems should be able to comprehend stories.
One thing which separates machine reading comprehension from text processing is inferencing. Taxonomies describing reading-related inferences make distinctions between: automatic and strategic; online and offline; text-connecting, knowledge-based, and extratextual; local and global; coherence and elaborative; unconscious and conscious; bridging; text-connecting and gap-filling; coherence, elaborative, knowledge-based, and evaluative; and anaphoric, text-to-text, and background-to-text (Kispal, 2008).
Types of reading-related inferences include: referential, case structure role assignment, antecedent causal, superordinate goal, thematic, character emotion, causal consequence, instantiation noun category, instrument, subordinate goal action, state, reader’s emotion, and author’s intent (Graesser, Singer, & Trabasso, 1994).
Situation models, types of mental models, were devised to understand comprehension. These models are applicable to both story and social comprehension (Morrow, Bower, & Greenspan, 1989; Zwaan, Magliano, & Graesser, 1995; Zwaan & Radvansky, 1998; Wyer Jr, 2003).
Early research into machine story comprehension produced artificial intelligence systems which applied scripts, plans, plot units, and thematic structures. Examples of such systems include: SAM, PAM, FRUMP, and BORIS (László, 2008).
More recently, character networks can be extracted from stories (Labatut & Bost, 2019). In these dynamic networks, nodes correspond to characters and edges to the interactions between them. These nodes and edges can be mapped to embedding vectors (Lee & Jung, 2020; Hoang, Jeon, You, Yoon, Jung, & Lee, 2023).
Similarly, individuals in dynamic social-media networks can be mapped to embedding vectors (Pan & Ding, 2019; Hoang, Jeon, You, Yoon, Jung, & Lee, 2023).
Human lives can be viewed as sequences of events and represented in a way which shares a structural similarity with language. In the “life2vec” approach, resultant embedding spaces were found to be robust and highly structured (Savcisens, Eliassi-Rad, Hansen, Mortensen, Lilleholt, Rogers, Zettler, & Lehmann, 2023).
Characters in fictional and real-world stories could be mapped to corresponding “life2vec” vectors. These vectors would be updated as pertinent events occurred. With computational representations of situational contexts which include embedding vectors for characters, story-based contextual recommendations could be made for selected characters.
Systems capable of predicting stories’ trajectories and inferring characters’ mental states would make better story-based contextual recommendations (Gordon, Bejan, & Sagae, 2011; Chaturvedi, Peng, & Roth, 2017). The “life2vec” approach has shown promise with respect to both its predictive capabilities and its modeling of individuals’ personality nuances.
Inferring the goals and objectives of story characters and individuals will prove critical for contextually providing that content which is to be of the most use to them (Richards & Singer, 2001; Trabasso & Wiley, 2005). Computational approaches to these topics are explored in artificial intelligence with respect to robotic systems (Van-Horenbeke & Peer, 2021) and broader applications (Mao, Liu, Zhao, Ni, Lin, & He, 2023).
Beyond extracting character networks from stories, knowledge graphs could be extracted, mapped with embedding vectors, and subsequently utilized (Andrus, Nasiri, Cui, Cullen, & Fulda, 2022).
Narrative psychology includes multiple parallel approaches: cognitive, psychometric, hermeneutic, scientific, and computational (László, 2008). Considered here are overlaps between artificial intelligence and those scientific and computational approaches of narrative psychology.
The contents and styles of the stories that individuals tell about their lives are of considerable importance. As story-based search and recommendation systems are constructed and continue to advance, opportunities for computer-aided and automated narrative coaching are expected to arise.
Narrative coaching works with coachees at three primary levels: (1) drawing on narrative psychology to understand and connect to the narrator, (2) drawing on narrative structure to understand and elicit the material in the narrated stories, and (3) drawing on narrative practices to understand and harvest the dynamics of the narrative field. The goal is to help coachees to forge new connections between their stories, their identity, and their behaviors in order to generate and embody new options in these three domains (Drake, 2010).
Established theoretical models from mentoring and coaching will be of use for designing artificial intelligence systems which process stories or social media data to contextually search for and recommend items in a personalized manner for characters or individuals at scale.
Definitions of mentoring and coaching vary throughout the literature and have been the subjects of considerable debate (Passmore, Peterson, & Freire, 2016). For clarity, and for discussing artificial intelligence systems which can perform pertinent tasks, generic definitions of coaching and mentoring are offered here.
Mentoring is a relationship in which a mentor shares their knowledge, skills, and experience with a person, a mentee, to help them to progress.
Intelligent mentoring systems have been considered with respect to education, self-regulated learning, lifelong learning, career counseling, and beyond. With respect to mentoring beyond the scopes of educational courses or programs, challenges include the collection and integration of data from multiple sources to construct and maintain models of mentees (Kravčík, Schmid, & Igel, 2019).
Coaching is a form of human development in which a coach supports learners, clients, or coachees to achieve specific personal or professional goals by providing training and guidance. Coaching differs from mentoring by its focus on specific tasks or objectives, as opposed to a focus on more general goals or overall development. Applications of coaching include: business and executive, career, co-coaching, dating, education, financial, health and wellness, homework, life, relationship, religious, sports, vocal, and writing.
Individuals’ specific goals and objectives could be inferred by artificial intelligence systems and/or obtained through direct interactions using established theoretical models. Systems could interact with individuals using natural-language dialogues or by means of adaptive input forms. With detailed knowledge of individuals’ goals and objectives, intelligent coaching systems could better contextually recommend items for them.
The PRACTICE model details the following steps: problem identification, development of realistic goals, generation of alternative solutions, consideration of each solutions’ consequences, targeting of the most feasible solution, implementation of the chosen solution, and evaluation (Palmer, 2007). When goal-setting, SMART principles suggest that individuals’ goals should be specific, measurable, achievable, relevant, and time-bound (Doran, 1981).
To best obtain and maintain knowledge of individuals’ dynamic and unfolding goals and objectives, over time, frameworks for the design of intelligent coaching systems describe system attributes for developing strong and efficacious relationships: trust, empathy, transparency, predictability, reliability, ability, benevolence, and integrity (Terblanche, 2020).
Other models from positive psychological coaching can guide the design of intelligent coaching systems including: authentic happiness coaching, the flow-enhancing model, the co-active coaching model, positive organizational psychology, and the good work and good mentoring approach (Passmore, Peterson, & Freire, 2016).
Areas where intelligent coaching systems are expected to excel include evidence-based coaching and continual improvement. In these regards, multi-armed and contextual bandits address the primary difficulty of sequential decision-making under uncertainty, namely, the exploitation versus exploration dilemma. Exploitation involves choosing the best option based upon current knowledge of a system, while exploration involves trying out new options that may lead to better outcomes in the future at the expense of an exploitation opportunity. Applications of these techniques include: healthcare, e.g., clinical trials, recommender systems, information retrieval, and dialogue systems (Bouneffouf & Rish, 2019).
Research into advice can be organized into four paradigms: the message, discourse, psychological, and network paradigms. Each of these provides different insights about the characteristics, functions, and outcomes of advice (MacGeorge, Feng, & Guntzviller, 2016).
The message paradigm focuses on qualities of advice messages and on the effort to predict supportive outcomes for recipients, often between peers.
The discourse paradigm provides insights into the structure and interpretation of advice in interactions.
The psychological paradigm focuses on cognitive and emotional processes which predict the uses of advice in decision-making.
The network paradigm highlights the utility of advice, often in organizational settings, as well as emergent global outcomes which arise from exchanges of advice.
In the future, users of social media could be provided with means of browsing content pertinent to the situations described in their recent or selected posts, content aligned with their preferences and aesthetic tastes, while having the capability to provide feedback on the contextual recommendations and on the content recommended.
Artificial intelligence systems could provide multiple personas, each having different values, styles, or configurations with respect to content recommendation. In this way, individuals could browse and select from values, styles, and configurations using anthropomorphized personas. Opting into and out of content recommendation services could be as easy for individuals as friending and unfriending artificial intelligence personas.
At least initially, individuals might receive paginated lists of recommended items. Eventually, more advanced systems might be able to more intelligently sort items, refine items, and even decide upon single items.
Personalization and user modeling can be of use for enhancing contextual content recommendations. With personalization, systems can select and prioritize items aligned with individuals’ preferences and aesthetic tastes. Individual users, their preferences, and their aesthetic tastes can be represented using embedding vectors (Pan & Ding, 2019; Rizkallah, Atiya, & Shaheen, 2021).
Individuals should be able to provide feedback about contextual recommendations and the content recommended by means of using “like” buttons, upvoting mechanisms, input forms, or follow-up dialogues. Artificial intelligence systems could learn from and continuously improve using these and other sources of feedback.
While personalized content from artificial intelligence personas might be sent to individuals’ direct message inboxes, individuals should be able to easily repost or share these contents alongside any of their positive or negative comments, reactions, opinions, or evaluations.
Towards determining the value provided by contextually recommended content, artificial intelligence systems could observe individuals’ trajectories in embedding spaces after their encounters with recommended content. Encounters with recommended content could accompany individuals’ other social media data.
Research into moderating large language models is applicable to moderating story-based search and recommendation systems (Rebedea, Dinu, Sreedhar, Parisien, & Cohen, 2023). With respect to input moderation, for example, regions in situation spaces could be defined by system administrators as being inappropriate for their systems to provide content, advice or items of wit and wisdom, for.
In addition to their commercial applications, the technologies under discussion have applications to education, library and information science, knowledge management, and history.
With respect to education, contextually recommended items of advice and wisdom can provide educational value to individuals. Educational recommender systems have been previously explored for recommending academic advice, courses, educational programs, exams, learning resources, online learning opportunities, papers, pedagogical resources, professions, programming problems, study sequences or syllabuses, teaching practice resources, and schools or universities (Urdaneta-Ponte, Mendez-Zorrilla, & Oleagordia-Ruiz, 2021).
With respect to social-emotional learning and character education, representing learners’ paths as trajectories through embedding spaces could provide a new and powerful tool for understanding when best to use which pedagogical strategy.
With respect to library and information science, contextually recommended content, e.g., excerpts and quotations from literary works, could include hyperlinks to relevant books and materials.
With respect to knowledge management, organizations could index, search for, and retrieve content utilizing story-based contexts.
With respect to history, historians could contextually retrieve content, e.g., historical events and analogues, pertinent to contemporary societal-scale narratives.
Recommending quotations for dialogue systems and writing tasks are being researched (Ahn, Lee, Jeon, Ha, & Lee, 2016; MacLaughlin, Chen, Ayan, & Roth, 2021).
Improving recommender systems by incorporating social contextual information is being explored (Ma, Zhou, Lyu, & King, 2011) and so too are context-aware recommender systems for social networks (Suhaim & Berri, 2021).
Research is underway into advice-related interactions between individuals and artificial intelligence systems (Liao, Oh, Feng, & Zhang, 2023).
Andrus, Berkeley R., Yeganeh Nasiri, Shilong Cui, Benjamin Cullen, and Nancy Fulda. "Enhanced story comprehension for large language models through dynamic document-based knowledge graphs." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 10, pp. 10436-10444. 2022.
Ahn, Yeonchan, Hanbit Lee, Heesik Jeon, Seungdo Ha, and Sang-goo Lee. "Quote recommendation for dialogs and writings." In CBRecSys@RecSys, pp. 39-42. 2016.
Bouneffouf, Djallel, and Irina Rish. "A survey on practical applications of multi-armed and contextual bandits." arXiv preprint arXiv:1904.10040 (2019).
Chaturvedi, Snigdha, Haoruo Peng, and Dan Roth. "Story comprehension for predicting what happens next." In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1603-1614. 2017.
Doran, George T. "There's a SMART way to write management’s goals and objectives." Management review 70, no. 11 (1981): 35-36.
Drake, David B. "Narrative coaching." In The complete handbook of coaching edited by Elaine Cox, Tatiana Bachkirova, and David Clutterbuck. p 120-131. SAGE. 2010.
Gordon, Andrew, Cosmin Bejan, and Kenji Sagae. "Commonsense causal reasoning using millions of personal stories." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 25, no. 1, pp. 1180-1185. 2011.
Graesser, Arthur C., Murray Singer, and Tom Trabasso. "Constructing inferences during narrative text comprehension." Psychological review 101, no. 3 (1994): 371.
Hoang, Van Thuy, Hyeon-Ju Jeon, Eun-Soon You, Yoewon Yoon, Sungyeop Jung, and O-Joun Lee. "Graph representation learning and its applications: A survey." Sensors 23, no. 8 (2023): 4168.
Kispal, Anne. Effective teaching of inference skills for reading: Literature review. National Foundation for Educational Research. The Mere, Upton Park, Slough, Berkshire, SL1 2DQ, UK. 2008.
Kravčík, Milos, Katharina Schmid, and Christoph Igel. "Towards requirements for intelligent mentoring systems." In Proceedings of the 23rd International Workshop on Personalization and Recommendation on the Web and Beyond, pp. 19-21. 2019.
Labatut, Vincent, and Xavier Bost. "Extraction and analysis of fictional character networks: A survey." ACM Computing Surveys (CSUR) 52, no. 5 (2019): 1-40.
László, János. The science of stories: An introduction to narrative psychology. Routledge, 2008.
Lee, O-Joun, and Jason J. Jung. "Story embedding: Learning distributed representations of stories based on character networks." Artificial Intelligence 281 (2020): 103235.
Liao, Wang, Yoo Jung Oh, Bo Feng, and Jingwen Zhang. "Understanding the influence discrepancy between human and artificial agent in advice interactions: The role of stereotypical perception of agency." Communication Research (2023): 00936502221138427.
Ma, Hao, Tom Chao Zhou, Michael R. Lyu, and Irwin King. "Improving recommender systems by incorporating social contextual information." ACM Transactions on Information Systems (TOIS) 29, no. 2 (2011): 1-23.
MacGeorge, Erina L., Bo Feng, and Lisa M. Guntzviller. "Advice: Expanding the communication paradigm." Communication yearbook 40 (2016): 239-270.
MacLaughlin, Ansel, Tao Chen, Burcu Karagol Ayan, and Dan Roth. "Context-based quotation recommendation." In Proceedings of the International AAAI Conference on Web and Social Media, vol. 15, pp. 397-408. 2021.
Mao, Yuanyuan, Shuang Liu, Pengshuai Zhao, Qin Ni, Xin Lin, and Liang He. "A review on machine theory of mind." arXiv preprint arXiv:2303.11594 (2023).
Mieder, Wolfgang, ed. Wise words: Essays on the proverb. Routledge, 2015.
Morrow, Daniel G., Gordon H. Bower, and Steven L. Greenspan. "Updating situation models during narrative comprehension." Journal of memory and language 28, no. 3 (1989): 292-312.
Palmer, Stephen. "PRACTICE: A model suitable for coaching, counselling, psychotherapy and stress management." The Coaching Psychologist 3, no. 2 (2007): 71-77.
Pan, Shimei, and Tao Ding. "Social media-based user embedding: A literature review." arXiv preprint arXiv:1907.00725 (2019).
Passmore, Jonathan, David Peterson, and Teresa Freire, eds. The wiley blackwell handbook of the psychology of coaching and mentoring. Nashville, TN: John Wiley & Sons. 2016.
Rebedea, Traian, Razvan Dinu, Makesh Sreedhar, Christopher Parisien, and Jonathan Cohen. "Nemo guardrails: A toolkit for controllable and safe llm applications with programmable rails." arXiv preprint arXiv:2310.10501 (2023).
Richards, Eric, and Murray Singer. "Representation of complex goal structures in narrative comprehension." Discourse Processes 31, no. 2 (2001): 111-135.
Rizkallah, Sandra, Amir F. Atiya, and Samir Shaheen. "New vector-space embeddings for recommender systems." Applied Sciences 11, no. 14 (2021): 6477.
Savcisens, Germans, Tina Eliassi-Rad, Lars K. Hansen, Laust H. Mortensen, Lau Lilleholt, Anna Rogers, Ingo Zettler, and Sune Lehmann. "Using sequences of life-events to predict human lives." Nature Computational Science (2023): 1-14.
Suhaim, Areej Bin, and Jawad Berri. "Context-aware recommender systems for social networks: review, challenges and opportunities." IEEE Access 9 (2021): 57440-57463.
Terblanche, Nicky. "A design framework to create artificial intelligence coaches." International Journal of Evidence Based Coaching & Mentoring 18, no. 2 (2020).
Trabasso, Tom, and Jennifer Wiley. "Goal plans of action and inferences during comprehension of narratives." Discourse processes 39, no. 2-3 (2005): 129-164.
Urdaneta-Ponte, María Cora, Amaia Mendez-Zorrilla, and Ibon Oleagordia-Ruiz. "Recommendation systems for education: Systematic review." Electronics 10, no. 14 (2021): 1611.
Van-Horenbeke, Franz A., and Angelika Peer. "Activity, plan, and goal recognition: A review." Frontiers in Robotics and AI 8 (2021): 643010.
Wyer Jr, Robert S. Social comprehension and judgment: The role of situation models, narratives, and implicit theories. Psychology Press, 2003.
Yankah, Kwesi. "Do proverbs contradict?." In Wise words: Essays on the proverb, pp. 127-142. Routledge, 2015.
Zwaan, Rolf A., Joseph P. Magliano, and Arthur C. Graesser. "Dimensions of situation model construction in narrative comprehension." Journal of experimental psychology: Learning, memory, and cognition 21, no. 2 (1995): 386.
Zwaan, Rolf A., and Gabriel A. Radvansky. "Situation models in language comprehension and memory." Psychological bulletin 123, no. 2 (1998): 162.