An appraisal-based chain-of-emotion architecture for affective language model game agents
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new Chain-of-Emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms control LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Gross, J. J., & John, O. P. (2003) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.85.2.348 · Cited by 11,929 · cited 1×
“Appraisal therefore represents a flexible process that adapts to individual differences [22] and the current context [38].”
BackgroundPicard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Appraisal Processes in Emotion: Theory, Methods, Research
(2001) · doi:10.1093/oso/9780195130072.001.0001 · Cited by 2,384
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · cited 10×
“Similarly, as Park et al. [44] describe, simulating believable behaviour in a digital world includes various important steps (including storing and retrieving memory, reflecting in addition to observing, etc.) that ultimately work together to improve the probability to generate expected and natural…”
BackgroundMethodInfluentialGenerative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
Basic emotions, relations among emotions, and emotion-cognition relations.
Izard, C. E. (1992) · Psychological Review · doi:10.1037/0033-295x.99.3.561 · Cited by 972 · cited 1×
“Moreover, while much work has been done to empirically investigate emotions, many core theoretical disagreements remain [52], including debates between dimensional [49], discrete [27], constructivist [5], and cognitive [53] perspectives.”
BackgroundA Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838
Linguistic Markers of Psychological Change Surrounding September 11, 2001
Cohn, M. A., Mehl, M. R., & Pennebaker, J. W. (2004) · Psychological Science · doi:10.1111/j.0956-7976.2004.00741.x · Cited by 808 · cited 1×
“calculates scores for authenticity (see [40] for details) and emotional tone, which signalizes how positive the overall of the text is (see [14] for details).”
BackgroundThe many meanings/aspects of emotion: definitions, functions, activation, and regulation
Izard, C. E. (2010) · Emotion Review · doi:10.1177/1754073910374661 · Cited by 574 · cited 1×
“Affective processes are very complex and involve multiple components (such as cognitive, behavioural, physiological, and feeling [53]) that are not fully understood and often debated on a fundamental level [28], which makes computational representations very difficult [25].”
BackgroundUsing cognitive psychology to understand GPT-3
Binz, M., & Schulz, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2218523120 · Cited by 559 · cited 9×
“Each STEU item presents a situation (e.g. "Clara receives a gift.") and a question with five possible answers, one of which is right (e.g.”
BackgroundMethodResultInfluentialA review and critique of emotional intelligence measures
Conte, J. M. (2005) · Journal of Organizational Behavior · doi:10.1002/job.319 · Cited by 431 · cited 1×
“However, the definition of EI as a construct is fuzzy and many measures are criticized for measuring potentially different abilities all under the umbrella term EI [15].”
BackgroundCreating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast
Topsakal, O., & Akinci, T. C. (2023) · International Conference on Applied Engineering and Natural Sciences · doi:10.59287/icaens.1127 · Cited by 331 · cited 1×
“P REPRINT”
Evaluating Large Language Models in Generating Synthetic HCI Research Data: a Case Study
Hämäläinen, P., Tavast, M., & Kunnari, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580688 · Cited by 248
Transformers learn in-context by gradient descent
von Oswald, J., Niklasson, E., Randazzo, E., Sacramento, J., Mordvintsev, A., Zhmoginov, A., & Vladymyrov, M. (2022) · arXiv · doi:10.48550/arxiv.2212.07677 · Cited by 87
Playing games with AIs: the limits of GPT-3 and similar large language models
Sobieszek, A., & Price, T. (2022) · Minds and Machines · doi:10.1007/s11023-022-09602-0 · Cited by 86
Keep CALM and Explore: Language Models for Action Generation in Text-based Games
Yao, S., Rao, R., Hausknecht, M., & Narasimhan, K. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.704 · Cited by 75
A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
Ma, L., Zhang, R., Han, Y., Yu, S., Wang, Z., Ning, Z., Zhang, J., Xu, P., Li, P., Qiao, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.11703 · Cited by 34
Openly accessible LLMs can help us to understand human cognition
Frank, M. C. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01732-4 · Cited by 18
Research works printed but not linked: 51
- E Hudlicka, 2011, Guidelines for designing computational models of emotions, International Journal of Synthetic Emotions (IJSE), 2, 26, 10.4018/jse.2011010103 · DOI · Paper page
- R Reisenzein, 2013, Computational modeling of emotion: Toward improving the inter-and intradisciplinary exchange, IEEE Transactions on Affective Computing, 4, 246, 10.1109/T-AFFC.2013.14 · DOI · Paper page
- R Beale, 2009, Affective interaction: How emotional agents affect users, International journal of human-computer studies, 67, 755, 10.1016/j.ijhcs.2009.05.001 · DOI · Paper page
- Luxton DD, Hudlicka E. Intelligent Virtual Agents in Behavioral and Mental Healthcare Mental healthcare: Ethics Ethics and Application Considerations. In: Artificial Intelligence in Brain and Mental Health: Philosophical, Ethical & Policy Issues. Springer; 2022. p. 41–55. · DOI
- KR Scherer, 2022, Theory convergence in emotion science is timely and realistic, Cognition and Emotion, 36, 154, 10.1080/02699931.2021.1973378 · DOI
- KR Scherer, 2000, Psychological models of emotion, The neuropsychology of emotion, 137, 137
- M Croissant, 2023, Theories, methodologies, and effects of affect-adaptive games: A systematic review, Entertainment Computing, 100591, 10.1016/j.entcom.2023.100591 · DOI
- AI Siam, 2022, Deploying machine learning techniques for human emotion detection, Computational intelligence and neuroscience, 2022
- Kosinski M. Theory of mind may have spontaneously emerged in large language models. arXiv preprint arXiv:230202083. 2023;.
- LF Barrett, 2017, How emotions are made: The secret life of the brain
- A Moors, 2013, Appraisal theories of emotion: State of the art and future development, Emotion Review, 5, 119, 10.1177/1754073912468165 · DOI · Paper page
- KA Lindquist, 2015, Does language do more than communicate emotion?, Current directions in psychological science, 24, 99, 10.1177/0963721414553440 · DOI · Paper page
- JA Brooks, 2017, The role of language in the experience and perception of emotion: A neuroimaging meta-analysis, Social Cognitive and Affective Neuroscience, 12, 169
- L Anolli, 2010, Emotions in serious games: From experience to assessment, International Journal of Emerging Technologies in Learning (iJET), 5, 10.3991/ijet.v5s3.1496 · DOI · Paper page
- Hudlicka E. Affective computing for game design. In: Proceedings of the 4th Intl. North American Conference on Intelligent Games and Simulation. McGill University Montreal, Canada; 2008. p. 5–12.
- GN Yannakakis, 2014, Emotion in games, Handbook on affective computing, 2014, 459
- Croissant M, Schofield G, McCall C. Emotion Design for Video Games: A Framework for Affective Interactivity. ACM Games: Research and Practice. 2023;. · DOI
- A Ortony, 1990, The cognitive structure of emotions
- A Popescu, 2013, Gamygdala: An emotion engine for games, IEEE Transactions on Affective Computing, 5, 32, 10.1109/T-AFFC.2013.24 · DOI · Paper page
- Bosse T, Zwanenburg E. There’s always hope: Enhancing agent believability through expectation-based emotions. In: 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops. IEEE; 2009. p. 1–8. · DOI
- GN Yannakakis, 2011, Experience-driven procedural content generation, IEEE Transactions on Affective Computing, 2, 147, 10.1109/T-AFFC.2011.6 · DOI · Paper page
- Shaker N, Yannakakis G, Togelius J. Towards automatic personalized content generation for platform games. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. vol. 5; 2010. · DOI · Paper page
- N Shaker, 2013, Fusing visual and behavioral cues for modeling user experience in games, IEEE Transactions on cybernetics, 43, 1519, 10.1109/TCYB.2013.2271738 · DOI · Paper page
- JA Russell, 1980, A circumplex model of affect, Journal of personality and social psychology, 39, 1161, 10.1037/h0077714 · DOI · Paper page
- RS Lazarus, 1968, Nebraska symposium on motivation
- RS Lazarus, 1991, Emotion and adaptation, 10.1093/oso/9780195069945.001.0001 · DOI · Paper page
- B Mesquita, 2014, Emotions in context: A sociodynamic model of emotions, Emotion Review, 6, 298, 10.1177/1754073914534480 · DOI · Paper page
- Freiknecht J, Effelsberg W. Procedural generation of interactive stories using language models. In: Proceedings of the 15th International Conference on the Foundations of Digital Games; 2020. p. 1–8. · DOI · Paper page
- Callison-Burch C, Tomar GS, Martin LJ, Ippolito D, Bailis S, Reitter D. Dungeons and dragons as a dialog challenge for artificial intelligence. arXiv preprint arXiv:221007109. 2022;. · DOI
- Ciolino M, Kalin J, Noever D. The go transformer: natural language modeling for game play. In: 2020 Third International Conference on Artificial Intelligence for Industries (AI4I). IEEE; 2020. p. 23–26. · DOI
- Sun T, He J, Qiu X, Huang X. BERTScore is unfair: On social bias in language model-based metrics for text generation. arXiv preprint arXiv:221007626. 2022;. · DOI
- Singh M, SB V, Malviya N, et al. Mind meets machine: Unravelling GPT-4’s cognitive psychology. arXiv preprint arXiv:230311436. 2023;.
- P Salovey, 1990, Emotional intelligence, Imagination, cognition and personality, 9, 185, 10.2190/DUGG-P24E-52WK-6CDG · DOI · Paper page
- S Newsome, 2000, Assessing the predictive validity of emotional intelligence, Personality and Individual differences, 29, 1005, 10.1016/S0191-8869(99)00250-0 · DOI · Paper page
- PK Papadogiannis, 2009, An ability model of emotional intelligence: A rationale, description, and application of the Mayer Salovey Caruso Emotional Intelligence Test (MSCEIT), Assessing emotional intelligence: Theory, research, and applications, 43, 10.1007/978-0-387-88370-0_3 · DOI
- C MacCann, 2008, New paradigms for assessing emotional intelligence: theory and data, Emotion, 8, 540, 10.1037/a0012746 · DOI · Paper page
- P Sajjadi, 2019, A personality-based emotional model for embodied conversational agents: Effects on perceived social presence and game experience of users, Entertainment Computing, 32, 100313, 10.1016/j.entcom.2019.100313 · DOI
- JW Pennebaker, 2001, Linguistic inquiry and word count: LIWC 2001, Mahway: Lawrence Erlbaum Associates, 71, 2001
- JH Kahn, 2007, Measuring emotional expression with the Linguistic Inquiry and Word Count, The American journal of psychology, 120, 263, 10.2307/20445398 · DOI · Paper page
- ML Newman, 2003, Lying words: Predicting deception from linguistic styles, Personality and social psychology bulletin, 29, 665, 10.1177/0146167203029005010 · DOI · Paper page
- K Krippendorff, 2018, Content analysis: An introduction to its methodology
- HA Elfenbein, 2015, The social perception of emotional abilities: expanding what we know about observer ratings of emotional intelligence, Emotion, 15, 17, 10.1037/a0038436 · DOI
- KS Law, 2004, The construct and criterion validity of emotional intelligence and its potential utility for management studies, Journal of applied Psychology, 89, 483, 10.1037/0021-9010.89.3.483 · DOI · Paper page
- AJ Cuddy, 2007, The BIAS map: behaviors from intergroup affect and stereotypes, Journal of personality and social psychology, 92, 631, 10.1037/0022-3514.92.4.631 · DOI · Paper page
- Croissant, M. An Appraisal-Based Chain-of-Emotion Architecture for Affective Language Model Game Agents. OSF Digitial Repository. https://doi.org/10.17605/OSF.IO/QPT6Z. · doi:10.17605/osf.io/qpt6z
- Frank MC. Large language models as models of human cognition. PsyArXiv. 2023;. · DOI
- Li C, Wang J, Zhu K, Zhang Y, Hou W, Lian J, et al. Emotionprompt: Leveraging psychology for large language models enhancement via emotional stimulus. arXiv preprint arXiv:230711760. 2023;. · DOI
- SA Kotz, 2011, Emotion, language, and the brain, Language and Linguistics Compass, 5, 108, 10.1111/j.1749-818X.2010.00267.x · DOI · Paper page
- K Isbister, 2022, Better game characters by design: A psychological approach
- Wu T, Terry M, Cai CJ. Ai chains: Transparent and controllable human-ai interaction by chaining large language model prompts. In: Proceedings of the 2022 CHI conference on human factors in computing systems; 2022. p. 1–22. · DOI · Paper page
- Liu H, Ning R, Teng Z, Liu J, Zhou Q, Zhang Y. Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv preprint arXiv:230403439. 2023;.
Metadata
- Authors
- Croissant, M., Frister, M., Schofield, G., & McCall, C.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2024-05-10
- Volume
- 19
- Issue
- 5
- Pages
- e0301033
- ISSN
- 1932-6203
- Cited by
- 15
- References
- 21
- Language
- en
- Funders
- EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (EP/S022325/1)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.