pith. sign in

arxiv: 2601.12912 · v1 · submitted 2026-01-19 · 💻 cs.AI

Human Emotion Verification by Action Languages via Answer Set Programming

Andreas Br\"annstr\"om , Juan Carlos Nieves This is my paper

Pith reviewed 2026-05-16 13:49 UTC · model grok-4.3

classification 💻 cs.AI
keywords action languageanswer set programmingmental statesemotion verificationtransition systemsappraisal theorycausal rules
0
0 comments X

The pith

The C-MT action language models human mental state evolution using multi-dimensional emotion configurations and a forbids-to-cause rule to enforce psychological transition principles.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops the C-MT language on top of answer set programming to represent how mental states evolve after sequences of actions. It draws on appraisal theory to define emotions as multi-dimensional setups and introduces a new causal rule to forbid certain state transitions. This setup allows checking trajectories in transition systems for properties like invariance, supporting models that prevent unwanted mental side effects from actions. A sympathetic reader would care because it offers a formal method to design and verify agent behaviors aligned with human psychology.

Core claim

C-MT extends action languages with expressions for mental state dynamics and the forbids to cause rule, translating psychological principles into transition constraints evaluated over trajectories to enable controlled reasoning about the dynamic evolution of human mental states and support emotion verification models.

What carries the argument

The C-MT language, an extension of action languages with a forbids-to-cause causal rule and mental state expressions that encode transition principles from psychological theories into transition system constraints.

If this is right

  • Models for emotion verification can be designed using the language.
  • Trajectories adhering to different psychological principles can be compared.
  • Properties of invariance in mental state evolution can be rigorously evaluated.
  • Reasoning about dynamic evolution of mental states can be controlled to restrict unwanted side-effects.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Such models could be tested against real human response data to validate the encoded principles.
  • Extensions might allow simulation of therapeutic interventions by selecting actions that guide mental states.
  • Integration with planning systems could ensure AI agents avoid inducing prohibited emotional states.

Load-bearing premise

Established psychological theories can be faithfully represented as multi-dimensional configurations and transition constraints without omitting essential features of real mental dynamics.

What would settle it

A concrete sequence of actions that leads to a mental state change forbidden by the encoded principles, yet the C-MT model accepts it as valid, or rejects a change that the theory permits.

Figures

Figures reproduced from arXiv: 2601.12912 by Andreas Br\"annstr\"om, Juan Carlos Nieves.

Figure 1
Figure 1. Figure 1: In CMT , available sequences of actions and states (trajectories) in the “physical” state space are constrained by the actions’ influence on the “mental” state space. plan its interactions in order to anticipate and reduce unwanted influence as a result of its behavior. Moreover, effective methods for verifying that such side-effects are avoided are essential. This requires dynamic models of the human mind… view at source ↗
Figure 2
Figure 2. Figure 2: Conceptual Framework [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Emotion states following the Appraisal theory of Emotion by Roseman (1996) [PITH_FULL_IMAGE:figures/full_fig_p026_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Emotional Reachability: Counting generated trajectories (HER and UER based) [PITH_FULL_IMAGE:figures/full_fig_p043_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Reachability: HER Shame Anger Hope Joy Relief Dislike Liking Regret Disgus Fear Pride Sadne Distr Surpr Guilt Frust Reachability Emotion state Full Reachability [PITH_FULL_IMAGE:figures/full_fig_p044_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Emotional Priority: HER ne go co ac [PITH_FULL_IMAGE:figures/full_fig_p046_7.png] view at source ↗
read the original abstract

In this paper, we introduce the action language C-MT (Mind Transition Language). It is built on top of answer set programming (ASP) and transition systems to represent how human mental states evolve in response to sequences of observable actions. Drawing on well-established psychological theories, such as the Appraisal Theory of Emotion, we formalize mental states, such as emotions, as multi-dimensional configurations. With the objective to address the need for controlled agent behaviors and to restrict unwanted mental side-effects of actions, we extend the language with a novel causal rule, forbids to cause, along with expressions specialized for mental state dynamics, which enables the modeling of principles for valid transitions between mental states. These principles of mental change are translated into transition constraints, and properties of invariance, which are rigorously evaluated using transition systems in terms of so-called trajectories. This enables controlled reasoning about the dynamic evolution of human mental states. Furthermore, the framework supports the comparison of different dynamics of change by analyzing trajectories that adhere to different psychological principles. We apply the action language to design models for emotion verification. Under consideration in Theory and Practice of Logic Programming (TPLP).

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The paper introduces the C-MT (Mind Transition) action language, extending ASP and transition systems to model evolution of human mental states (formalized as multi-dimensional configurations drawn from Appraisal Theory) in response to observable actions. It adds a novel 'forbids to cause' causal rule plus specialized mental-state expressions to encode principles of valid transitions, which are then turned into transition constraints and evaluated via trajectories for invariance properties and emotion verification; the framework also supports comparison of different psychological dynamics.

Significance. If the encoding of Appraisal Theory into ASP atoms and the 'forbids to cause' constraints can be shown to preserve essential psychological transition properties without semantic loss, the work would supply a logic-programming tool for controlled, verifiable reasoning about mental-state dynamics in agents, enabling formal comparison of alternative psychological models.

major comments (2)
  1. [Abstract] Abstract and overall presentation: the formalization is described at a high level with no concrete mapping from appraisal dimensions to ASP atoms, no semantics for the 'forbids to cause' rule, and no example trajectories or proof sketches; this prevents verification that the generated trajectories respect documented psychological transitions rather than encoding artifacts.
  2. [Abstract] The central claim that the novel rule and expressions 'enable the modeling of principles for valid transitions' is load-bearing yet unsupported by any explicit derivation or invariance check in the provided description; without such material the soundness of the transition-system evaluation cannot be assessed.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed feedback. We address the major comments point by point below, clarifying the content of the full manuscript and indicating revisions to improve the abstract and presentation.

read point-by-point responses

  1. Referee: [Abstract] Abstract and overall presentation: the formalization is described at a high level with no concrete mapping from appraisal dimensions to ASP atoms, no semantics for the 'forbids to cause' rule, and no example trajectories or proof sketches; this prevents verification that the generated trajectories respect documented psychological transitions rather than encoding artifacts.

    Authors: The full manuscript provides these details: Section 3 gives the concrete mapping (appraisal dimensions such as valence and arousal encoded as ASP fluents with domain values drawn from Appraisal Theory), Definition 4.1 defines the semantics of the 'forbids to cause' rule as a transition constraint that eliminates invalid mental-state evolutions, and Section 5 presents example trajectories together with invariance checks. We agree the abstract is too high-level for standalone verification and will revise it to include a brief mapping example and one short trajectory illustration. revision: yes

  2. Referee: [Abstract] The central claim that the novel rule and expressions 'enable the modeling of principles for valid transitions' is load-bearing yet unsupported by any explicit derivation or invariance check in the provided description; without such material the soundness of the transition-system evaluation cannot be assessed.

    Authors: Section 4 derives the translation of 'forbids to cause' rules into transition constraints and shows how trajectories are generated and checked for invariance properties via ASP solving. The soundness argument is given by construction: only trajectories satisfying the encoded psychological principles are admitted. To address the concern, we will add a concise derivation sketch and invariance statement to the revised abstract. revision: yes

Circularity Check

0 steps flagged

No significant circularity in C-MT derivation

full rationale

The paper introduces C-MT as an extension of standard ASP and transition systems, encoding Appraisal Theory as multi-dimensional configurations and transition constraints. No load-bearing step reduces by construction to a self-definition, fitted parameter renamed as prediction, or self-citation chain. The central claims concern the formalization of mental-state trajectories and invariance properties, which remain independent of the paper's own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 2 invented entities

The central claim rests on standard answer-set-programming semantics and the assumption that Appraisal Theory supplies accurate multi-dimensional mental-state representations; no numerical parameters are fitted and no new physical entities are postulated.

axioms (2)
  • domain assumption Appraisal Theory of Emotion can be represented as multi-dimensional configurations of mental states
    Invoked to formalize emotions as the basis for transition rules.
  • domain assumption Transition systems and trajectories can capture the dynamic evolution of mental states under action sequences
    Core modeling choice that turns psychological principles into verifiable constraints.
invented entities (2)
  • C-MT action language no independent evidence
    purpose: To represent mental-state transitions with specialized causal rules
    Newly defined language extending ASP.
  • forbids to cause rule no independent evidence
    purpose: To restrict actions that would produce unwanted mental side-effects
    Novel causal construct introduced in the paper.

pith-pipeline@v0.9.0 · 5495 in / 1405 out tokens · 25313 ms · 2026-05-16T13:49:24.202876+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

78 extracted references · 78 canonical work pages · 2 internal anchors

  1. [1]

    A logical formalization of the OCC theory of emotions

    Carole Adam, Andreas Herzig, and Dominique Longin. “A logical formalization of the OCC theory of emotions”. In:Synthese168 (2009), pp. 201–248

    work page 2009

  2. [2]

    A BDI emotional reasoning engine for an artificial companion

    Carole Adam and Emiliano Lorini. “A BDI emotional reasoning engine for an artificial companion”. In:International Conference on Practical Applications of Agents and Multi-Agent Systems. Springer. 2014, pp. 66–78. 52Human Emotion Verification

    work page 2014

  3. [3]

    Empathic conversational agents for real-time monitoring and co-facilitation of patient-centered healthcare

    Achini Adikari et al. “Empathic conversational agents for real-time monitoring and co-facilitation of patient-centered healthcare”. In:Future Generation Computer Systems126 (2022), pp. 318–329

    work page 2022

  4. [4]

    Human-aware plan- ning: A survey related to joint human-agent activities

    Sebastian Ahrndt, Johannes F¨ ahndrich, and Sahin Albayrak. “Human-aware plan- ning: A survey related to joint human-agent activities”. In:Trends in Practi- cal Applications of Heterogeneous Multi-Agent Systems. The PAAMS Collection. Springer, 2014, pp. 95–102

    work page 2014

  5. [5]

    The theory of planned behavior

    Icek Ajzen et al. “The theory of planned behavior”. In:Organizational behavior and human decision processes50.2 (1991), pp. 179–211

    work page 1991

  6. [6]

    Locus of control and self- responsibility for behavior

    Loretta Brown Autry and Michael Langenbach. “Locus of control and self- responsibility for behavior”. In:The Journal of Educational Research79.2 (1985), pp. 76–84

    work page 1985

  7. [7]

    Building and ex- ploiting emotinet, a knowledge base for emotion detection based on the appraisal theory model

    Alexandra Balahur, Jesus M Hermida, and Andres Montoyo. “Building and ex- ploiting emotinet, a knowledge base for emotion detection based on the appraisal theory model”. In:IEEE transactions on affective computing3.1 (2011), pp. 88– 101

    work page 2011

  8. [8]

    Routledge, 2021

    Albert Bandura.Psychological modeling: Conflicting theories. Routledge, 2021

    work page 2021

  9. [9]

    Probabilistic reasoning with answer sets

    Chitta Baral, Michael Gelfond, and Nelson Rushton. “Probabilistic reasoning with answer sets”. In:Theory and Practice of Logic Programming9.1 (2009), pp. 57– 144

    work page 2009

  10. [10]

    A logical model of Theory of Mind for virtual agents in the context of job interview simulation

    Marwen Belkaid and Nicolas Sabouret. “A logical model of theory of mind for virtual agents in the context of job interview simulation”. In:arXiv preprint arXiv:1402.5043(2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  11. [11]

    Epistemic planning for single- and multi-agent systems

    Thomas Bolander and Mikkel Birkegaard Andersen. “Epistemic planning for single- and multi-agent systems”. In:Journal of Applied Non-Classical Logics21.1 (2011), pp. 9–34

    work page 2011

  12. [12]

    Improving the normaliza- tion of weight rules in answer set programs

    Jori Bomanson, Martin Gebser, and Tomi Janhunen. “Improving the normaliza- tion of weight rules in answer set programs”. In:European Workshop on Logics in Artificial Intelligence. Springer. 2014, pp. 166–180

    work page 2014

  13. [13]

    Emotional Reasoning in an Action Language for Emotion-Aware Planning

    Andreas Br¨ annstr¨ om and Juan Carlos Nieves. “Emotional Reasoning in an Action Language for Emotion-Aware Planning”. In:International Conference on Logic Programming and Nonmonotonic Reasoning. Springer. 2022, pp. 103–116

    work page 2022

  14. [14]

    Modelling Human Mental-States in an Action Language following the Theory of Planned Behavior

    Andreas Br¨ annstr¨ om and Juan Carlos Nieves. “Modelling Human Mental-States in an Action Language following the Theory of Planned Behavior”. In:14th Workshop on Answer Set Programming and Other Computing Paradigms (ASPOCP 2021), virtual, September 20–27, 2021.Vol. 2970. CEUR-WS. 2021

    work page 2021

  15. [15]

    A formal understand- ing of computational empathy in interactive agents

    Andreas Br¨ annstr¨ om, Joel Wester, and Juan Carlos Nieves. “A formal understand- ing of computational empathy in interactive agents”. In:Cognitive Systems Re- search85 (2024), p. 101203

    work page 2024

  16. [16]

    Answer set program- ming at a glance

    Gerhard Brewka, Thomas Eiter, and Miros law Truszczy´ nski. “Answer set program- ming at a glance”. In:Communications of the ACM54.12 (2011), pp. 92–103

    work page 2011

  17. [17]

    A closer look at life goals across adulthood: Applying a developmental perspective to content, dynamics, and outcomes of goal importance and goal attainability

    Janina Larissa B¨ uhler et al. “A closer look at life goals across adulthood: Applying a developmental perspective to content, dynamics, and outcomes of goal importance and goal attainability”. In:European Journal of Personality33.3 (2019), pp. 359– 384. Human Emotion Verification53

    work page 2019

  18. [18]

    Technological state of the art of electronic mental health interventions for major depressive dis- order: systematic literature review

    Franziska Burger, Mark A Neerincx, Willem-Paul Brinkman, et al. “Technological state of the art of electronic mental health interventions for major depressive dis- order: systematic literature review”. In:Journal of medical Internet research22.1 (2020), e12599

    work page 2020

  19. [19]

    Human-aware planning revisited: A tale of three models

    Tathagata Chakraborti, Sarath Sreedharan, and Subbarao Kambhampati. “Human-aware planning revisited: A tale of three models”. In:Proceedings of the AAAI 2018 Workshop on Explainable Artificial Intelligence Planning (XAIP). 2018, pp. 18–25

    work page 2018

  20. [20]

    Automatic estimation of interpersonal engagement during naturalistic conversation using dyadic physiological measurements

    Iman Chatterjee et al. “Automatic estimation of interpersonal engagement during naturalistic conversation using dyadic physiological measurements”. In:Frontiers in Neuroscience15 (2021), p. 757381

    work page 2021

  21. [21]

    Conflicting theories of social change

    James S Coleman. “Conflicting theories of social change”. In:American Behavioral Scientist14.5 (1971), pp. 633–650

    work page 1971

  22. [22]

    A logic of emotions: from appraisal to cop- ing

    Mehdi Dastani and Emiliano Lorini. “A logic of emotions: from appraisal to cop- ing”. In:11th International Conference on Autonomous Agents and Multiagent Sys- tems (AAMAS 2012). ACM: Association for Computing Machinery. 2012, pp. 1133– 1140

    work page 2012

  23. [23]

    A simple framework for cognitive planning

    Jorge Luis Fernandez Davila et al. “A simple framework for cognitive planning”. In:Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. 7. 2021, pp. 6331–6339

    work page 2021

  24. [24]

    From needs to goals and representations: Foundations for a unified theory of motivation, personality, and development

    Carol S Dweck. “From needs to goals and representations: Foundations for a unified theory of motivation, personality, and development.” In:Psychological review124.6 (2017), p. 689

    work page 2017

  25. [25]

    Modeling Biological Networks by Action Languages via An- swer Set Programming

    S. Dworschak et al. “Modeling Biological Networks by Action Languages via An- swer Set Programming”. In:Constraints13.1 (2008), pp. 21–65

    work page 2008

  26. [26]

    TOMA: Computational Theory of Mind with Abstractions for Hybrid Intelligence

    Emre Erdogan et al. “TOMA: Computational Theory of Mind with Abstractions for Hybrid Intelligence”. In:Journal of Artificial Intelligence Research82 (2025), pp. 285–311

    work page 2025

  27. [27]

    Rationale for human modelling in human in the loop systems design

    Didier Fass and Romain Lieber. “Rationale for human modelling in human in the loop systems design”. In:2009 3rd Annual IEEE Systems Conference. IEEE. 2009, pp. 27–30

    work page 2009

  28. [28]

    Teacher evaluation policy and conflicting theories of moti- vation

    William A Firestone. “Teacher evaluation policy and conflicting theories of moti- vation”. In:Educational researcher43.2 (2014), pp. 100–107

    work page 2014

  29. [29]

    Theory of mind

    Chris Frith and Uta Frith. “Theory of mind”. In:Current biology15.17 (2005), R644–R645

    work page 2005

  30. [30]

    Datalogisk Institut, Aarhus Universitet, 2003

    Mikkel Nygaard Hansen and Erik Meineche Schmidt.Algorithms and data struc- tures: transition systems. Datalogisk Institut, Aarhus Universitet, 2003

    work page 2003

  31. [31]

    Appraisal theories for emotion classification in text

    Jan Hofmann et al. “Appraisal theories for emotion classification in text”. In:arXiv preprint arXiv:2003.14155(2020)

    work page arXiv 2003

  32. [32]

    Predicting affective appraisals from facial expressions and physiology using machine learning

    Laura SF Israel and Felix D Sch¨ onbrodt. “Predicting affective appraisals from facial expressions and physiology using machine learning”. In:Behavior Research Methods 53 (2021), pp. 574–592

    work page 2021

  33. [33]

    Theory of mind as inverse reinforcement learning

    Julian Jara-Ettinger. “Theory of mind as inverse reinforcement learning”. In:Cur- rent Opinion in Behavioral Sciences29 (2019), pp. 105–110. 54Human Emotion Verification

    work page 2019

  34. [34]

    EBDI: an architecture for emotional agents

    Hong Jiang, Jose M Vidal, and Michael N Huhns. “EBDI: an architecture for emotional agents”. In:Proceedings of the 6th international joint conference on Au- tonomous agents and multiagent systems. 2007, pp. 1–3

    work page 2007

  35. [35]

    Personality, Emotions and Physiology in a BDI Agent Architecture: The PEP-BDI Model

    Haza¨ el Jones, Julien Saunier, and Domitile Lourdeaux. “Personality, Emotions and Physiology in a BDI Agent Architecture: The PEP-BDI Model”. In:2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelli- gent Agent Technology. Vol. 2. IEEE. 2009, pp. 263–266

    work page 2009

  36. [36]

    Goal recognition design

    Sarah Keren, Avigdor Gal, and Erez Karpas. “Goal recognition design”. In:Twenty- Fourth International Conference on Automated Planning and Scheduling. 2014

    work page 2014

  37. [37]

    The circumplex structure of affect: A Swedish ver- sion

    Igor Knez and Staffan Hygge. “The circumplex structure of affect: A Swedish ver- sion”. In:Scandinavian Journal of Psychology42.5 (2001), pp. 389–398

    work page 2001

  38. [38]

    Adaptive Human-Aware Task Planning

    M Leonetti et al. “Adaptive Human-Aware Task Planning”. In:Workshop on Plan- ning and Robotics (PlanRob) at the International Conference on Automated Plan- ning and Scheduling (ICAPS). 2019

    work page 2019

  39. [39]

    Splitting a logic program

    Vladimir Lifschitz and Hudson Turner. “Splitting a logic program”. In:Proceedings of the 11th International Conference on Logic Programming (ICLP 1994). MIT Press, 1994, pp. 23–37

    work page 1994

  40. [40]

    A Qualitative Theory of Cognitive Attitudes and their Change

    Emiliano Lorini. “A Qualitative Theory of Cognitive Attitudes and their Change”. In:Theory and Practice of Logic Programming21.4 (2021), pp. 428–458

    work page 2021

  41. [41]

    A logic for reasoning about coun- terfactual emotions

    Emiliano Lorini and Fran¸ cois Schwarzentruber. “A logic for reasoning about coun- terfactual emotions”. In:Artificial Intelligence175.3-4 (2011), pp. 814–847

    work page 2011

  42. [42]

    Cognitive planning in motivational interviewing

    Emiliano Lorini et al. “Cognitive planning in motivational interviewing”. In:14th International Conference on Agents and Artificial Intelligence (ICAART 2022). 2022, pp. 1–11

    work page 2022

  43. [43]

    Suicide prevention and depression apps’ suicide risk as- sessment and management: a systematic assessment of adherence to clinical guide- lines

    Laura Martinengo et al. “Suicide prevention and depression apps’ suicide risk as- sessment and management: a systematic assessment of adherence to clinical guide- lines”. In:BMC medicine17.1 (2019), pp. 1–12

    work page 2019

  44. [44]

    Preface to the special issue on personalization and behavior change

    Judith Masthoff, Floriana Grasso, and Jaap Ham. “Preface to the special issue on personalization and behavior change”. In:User Modeling and User-Adapted Interaction24.5 (2014), pp. 345–350

    work page 2014

  45. [45]

    Topic propagation in conversational search

    Ida Mele et al. “Topic propagation in conversational search”. In:Proceedings of the 43rd International ACM conference on research and development in Information Retrieval (SIGIR). 2020, pp. 2057–2060

    work page 2020

  46. [46]

    Nonlinear appraisal modeling: An applica- tion of machine learning to the study of emotion production

    Ben Meuleman and Klaus R Scherer. “Nonlinear appraisal modeling: An applica- tion of machine learning to the study of emotion production”. In:IEEE Transac- tions on Affective Computing4.4 (2013), pp. 398–411

    work page 2013

  47. [47]

    Using facial expres- siveness of a virtual agent to induce empathy in users

    Anne-Sophie Milcent, Abdelmajid Kadri, and Simon Richir. “Using facial expres- siveness of a virtual agent to induce empathy in users”. In:International Journal of Human–Computer Interaction38.3 (2022), pp. 240–252

    work page 2022

  48. [48]

    Towards an artificially empathic conversational agent for mental health applications: system design and user perceptions

    Robert R Morris et al. “Towards an artificially empathic conversational agent for mental health applications: system design and user perceptions”. In:Journal of medical Internet research20.6 (2018), e10148

    work page 2018

  49. [49]

    Planning for goal-oriented dialogue systems

    Christian Muise et al. “Planning for goal-oriented dialogue systems”. In:arXiv preprint arXiv:1910.08137(2019). Human Emotion Verification55

    work page arXiv 1910

  50. [50]

    Possibilistic uncertainty handling for answer set program- ming

    Pascal Nicolas et al. “Possibilistic uncertainty handling for answer set program- ming”. In:Annals of Mathematics and Artificial Intelligence47 (2006), pp. 139– 181

    work page 2006

  51. [51]

    Computational models of emotion inference in theory of mind: A review and roadmap

    Desmond C Ong, Jamil Zaki, and Noah D Goodman. “Computational models of emotion inference in theory of mind: A review and roadmap”. In:Topics in cognitive science11.2 (2019), pp. 338–357

    work page 2019

  52. [52]

    The roles of hedonic and eudaimonic motives in emo- tion regulation

    Catherine NM Ortner et al. “The roles of hedonic and eudaimonic motives in emo- tion regulation”. In:Personality and Individual Differences120 (2018), pp. 209– 212

    work page 2018

  53. [53]

    AI deception: A survey of examples, risks, and potential solu- tions

    Peter S Park et al. “AI deception: A survey of examples, risks, and potential solu- tions”. In:Patterns5.5 (2024)

    work page 2024

  54. [54]

    The functional utility of negative emotions

    W Gerrod Parrott. “The functional utility of negative emotions.” In: (2002)

    work page 2002

  55. [55]

    Self-accountability emotions and fear appeals: Motivating behavior

    Kirsten Passyn and Mita Sujan. “Self-accountability emotions and fear appeals: Motivating behavior”. In:Journal of Consumer Research32.4 (2006), pp. 583–589

    work page 2006

  56. [56]

    Formal modelling of emo- tions in BDI agents

    David Pereira, Eug´ enio Oliveira, and Nelma Moreira. “Formal modelling of emo- tions in BDI agents”. In:International Workshop on Computational Logic in Multi- Agent Systems. Springer. 2007, pp. 62–81

    work page 2007

  57. [57]

    Towards socially intelligent agents with mental state transition and human value

    Liang Qiu et al. “Towards socially intelligent agents with mental state transition and human value”. In:Proceedings of the 23rd Annual Meeting of the Special In- terest Group on Discourse and Dialogue. 2022, pp. 146–158

    work page 2022

  58. [58]

    MyBehavior: automatic personalized health feedback from user behaviors and preferences using smartphones

    Mashfiqui Rabbi et al. “MyBehavior: automatic personalized health feedback from user behaviors and preferences using smartphones”. In:Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2015, pp. 707–718

    work page 2015

  59. [59]

    Plan recognition as planning

    Miquel Ramırez and Hector Geffner. “Plan recognition as planning”. In:Proceed- ings of the 21st international joint conference on Artifical intelligence. Morgan Kaufmann Publishers Inc. 2009, pp. 1778–1783

    work page 2009

  60. [60]

    BDI agents: from theory to practice

    Anand S Rao and Michael Georgeff. “BDI agents: from theory to practice.” In: Proceedings of the First International Conference on Multiagent Systems. Vol. 95. 1995, pp. 312–319

    work page 1995

  61. [61]

    Appraisal determinants of emotions: Constructing a more accurate and comprehensive theory

    Ira J Roseman. “Appraisal determinants of emotions: Constructing a more accurate and comprehensive theory”. In:Cognition & Emotion10.3 (1996), pp. 241–278

    work page 1996

  62. [62]

    Phenomenology, behaviors, and goals differentiate discrete emotions

    Ira J Roseman, Cynthia Wiest, and Tamara S Swartz. “Phenomenology, behaviors, and goals differentiate discrete emotions.” In:Journal of personality and social psychology67.2 (1994), p. 206

    work page 1994

  63. [63]

    ABC-EBDI: An affective framework for BDI agents

    Yanet S´ anchez et al. “ABC-EBDI: An affective framework for BDI agents”. In: Cognitive Systems Research58 (2019), pp. 195–216

    work page 2019

  64. [64]

    Designing emotional BDI agents: good practices and open questions

    Yanet S´ anchez-L´ opez and Eva Cerezo. “Designing emotional BDI agents: good practices and open questions”. In:The Knowledge Engineering Review34 (2019)

    work page 2019

  65. [65]

    Self-regulation through goal setting

    Dale H Schunk. “Self-regulation through goal setting”. In: (2001)

    work page 2001

  66. [66]

    Towards Empathetic Planning

    Maayan Shvo and Sheila A McIlraith. “Towards Empathetic Planning”. In:arXiv preprint arXiv:1906.06436(2019)

    work page internal anchor Pith review Pith/arXiv arXiv 1906

  67. [67]

    Active goal recognition

    Maayan Shvo and Sheila A. McIlraith. “Active goal recognition”. In:Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020). 2020, pp. 9957– 9966. 56Human Emotion Verification

    work page 2020

  68. [68]

    Modeling appraisal in theory of mind reasoning

    Mei Si, Stacy C Marsella, and David V Pynadath. “Modeling appraisal in theory of mind reasoning”. In:Autonomous Agents and Multi-Agent Systems20.1 (2010), pp. 14–31

    work page 2010

  69. [69]

    How a Chatbot Encouraged a Man Who Wanted to Kill the Queen

    Tom Singleton, Tom Gerken, and Liv McMahon. “How a Chatbot Encouraged a Man Who Wanted to Kill the Queen”. In:BBC News(2023)

    work page 2023

  70. [70]

    Sentiment analysis and topic recognition in video transcrip- tions

    Lukas Stappen et al. “Sentiment analysis and topic recognition in video transcrip- tions”. In:IEEE Intelligent Systems36.2 (2021), pp. 88–95

    work page 2021

  71. [71]

    A formal model of emotion triggers: an approach for BDI agents

    Bas R Steunebrink, Mehdi Dastani, and John-Jules Ch Meyer. “A formal model of emotion triggers: an approach for BDI agents”. In:Synthese185 (2012), pp. 83– 129

    work page 2012

  72. [72]

    Business or pleasure? Utilitar- ian versus hedonic considerations in emotion regulation

    Maya Tamir, Chi-Yue Chiu, and James J Gross. “Business or pleasure? Utilitar- ian versus hedonic considerations in emotion regulation.” In:Emotion7.3 (2007), p. 546

    work page 2007

  73. [73]

    Choosing to be afraid: preferences for fear as a function of goal pursuit

    Maya Tamir and Brett Q Ford. “Choosing to be afraid: preferences for fear as a function of goal pursuit.” In:Emotion9.4 (2009), p. 488

    work page 2009

  74. [74]

    Hedonic and instrumental motives in anger regulation

    Maya Tamir, Christopher Mitchell, and James J Gross. “Hedonic and instrumental motives in anger regulation”. In:Psychological science19.4 (2008), pp. 324–328

    work page 2008

  75. [75]

    Towards emotion classification using appraisal modeling

    Gert-Jan de Vries et al. “Towards emotion classification using appraisal modeling”. In:International Journal of Synthetic Emotions (IJSE)6.1 (2015), pp. 40–59

    work page 2015

  76. [76]

    Towards a Formal- ization of the Critical Friend and Socio-Moral Decision-Making in Autonomous Systems

    Joel Wester, Andreas Br¨ annstr¨ om, and Juan Carlos Nieves. “Towards a Formal- ization of the Critical Friend and Socio-Moral Decision-Making in Autonomous Systems”. In:CHAI’22: Workshop on Communication in Human-AI Interaction@ IJCAI, Vienna, Austria, July 24, 2022. 2022

    work page 2022

  77. [77]

    A computational model of coping for simulating human behavior in high-stress situations

    Nutchanon Yongsatianchot and Stacy Marsella. “A computational model of coping for simulating human behavior in high-stress situations”. In:Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021). 2021

    work page 2021

  78. [78]

    Integrating empathy and interpersonal emotion regulation

    Jamil Zaki. “Integrating empathy and interpersonal emotion regulation”. In:An- nual Review of Psychology71 (2020), pp. 517–540

    work page 2020