pith. sign in

arxiv: 1906.09774 · v1 · pith:KYMTTKGEnew · submitted 2019-06-24 · 💻 cs.CL

Emotionally-Aware Chatbots: A Survey

Endang Wahyu Pamungkas This is my paper

Pith reviewed 2026-05-25 17:46 UTC · model grok-4.3

classification 💻 cs.CL
keywords emotionally-aware chatbotsEAC surveyneural approachesemotion classifieraffective resourcesconversational agentschatbot evolutionrule-based systems
0
0 comments X

The pith

Emotionally-aware chatbots have shifted from rule-based systems to neural networks that include dedicated emotion classifiers using affective resources.

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

This survey examines the development of emotionally-aware chatbots to make conversational agents more human-like for improved user engagement in services like customer support. It addresses three questions on the field's history and evolution, the main approaches taken in prior work, and the resources such as datasets and classifiers that support them. The review concludes that early systems relied on simple rules while recent ones predominantly use neural methods, and that most architectures now embed an emotion classifier component. These patterns indicate how emotion integration has become central to chatbot design. The authors also note growing research activity through new datasets in multiple languages.

Core claim

The paper establishes that emotionally-aware chatbots evolved from simple rule-based approaches in their early development to predominantly neural-based approaches in current work, with most systems incorporating an emotion classifier that draws on available affective resources to detect and respond to user emotions.

What carries the argument

The three research questions on history/evolution, approaches to building EAC, and available affective resources that structure the survey and lead to the observed shift and architectural patterns.

If this is right

  • Early EAC development relied on simple rule-based approaches.
  • Current EAC systems mostly adopt neural-based approaches.
  • Most EAC architectures include an emotion classifier.
  • These classifiers depend on existing affective resources for training and operation.
  • New datasets in various languages will support further EAC growth.

Where Pith is reading between the lines

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

  • Widespread adoption of neural EAC with emotion classifiers could raise engagement levels in commercial chatbot services.
  • Dependence on current affective resources highlights a potential gap in coverage for non-English languages or niche emotion types.
  • The documented shift suggests hybrid rule-neural systems might remain practical for low-complexity applications.

Load-bearing premise

That the studies examined through the three research questions give a representative picture of the entire field of emotionally-aware chatbots.

What would settle it

A count of recent EAC papers showing that a majority still rely only on rule-based methods without any emotion classifier component.

read the original abstract

Textual conversational agent or chatbots' development gather tremendous traction from both academia and industries in recent years. Nowadays, chatbots are widely used as an agent to communicate with a human in some services such as booking assistant, customer service, and also a personal partner. The biggest challenge in building chatbot is to build a humanizing machine to improve user engagement. Some studies show that emotion is an important aspect to humanize machine, including chatbot. In this paper, we will provide a systematic review of approaches in building an emotionally-aware chatbot (EAC). As far as our knowledge, there is still no work focusing on this area. We propose three research question regarding EAC studies. We start with the history and evolution of EAC, then several approaches to build EAC by previous studies, and some available resources in building EAC. Based on our investigation, we found that in the early development, EAC exploits a simple rule-based approach while now most of EAC use neural-based approach. We also notice that most of EAC contain emotion classifier in their architecture, which utilize several available affective resources. We also predict that the development of EAC will continue to gain more and more attention from scholars, noted by some recent studies propose new datasets for building EAC in various languages.

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 / 2 minor

Summary. The paper claims to provide the first systematic review of emotionally-aware chatbots (EAC). It proposes three research questions covering the history/evolution of EAC, approaches to building them, and available affective resources. Based on the authors' investigation, it concludes that early EAC relied on rule-based methods while current systems predominantly use neural approaches, and that most EAC architectures incorporate an emotion classifier drawing on affective resources. The paper also predicts growing scholarly attention to the topic.

Significance. If the underlying literature corpus were assembled via a documented, reproducible process and shown to be representative, the work would constitute a useful first survey of EAC trends, highlighting the shift toward neural methods and the centrality of emotion classification components.

major comments (2)
  1. [Abstract] Abstract: the statements that 'most of EAC use neural-based approach' and 'most of EAC contain emotion classifier' rest on an undocumented sample; no search strategy, databases, date bounds, inclusion criteria, screening process, or total number of papers examined is supplied anywhere in the manuscript, so the prevalence claims cannot be evaluated.
  2. [Introduction] Introduction / Research Questions section: the claim that 'there is still no work focusing on this area' is asserted without evidence of a prior-survey search or citation analysis that would establish novelty.
minor comments (2)
  1. [Abstract] Abstract: the forward-looking prediction sentence is speculative and would be strengthened by explicit citation of the 'recent studies' that motivate it.
  2. [Throughout] Notation: the acronym EAC is used repeatedly but the expansion 'emotionally-aware chatbot' is not restated on first use in every major section.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. We agree that greater methodological transparency is needed to support the survey's claims and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the statements that 'most of EAC use neural-based approach' and 'most of EAC contain emotion classifier' rest on an undocumented sample; no search strategy, databases, date bounds, inclusion criteria, screening process, or total number of papers examined is supplied anywhere in the manuscript, so the prevalence claims cannot be evaluated.

    Authors: We acknowledge this limitation. The original manuscript does not document the literature search process. We will add a dedicated 'Methodology' section describing the systematic review protocol, including databases searched, search strings, date range, inclusion/exclusion criteria, screening steps, and the final corpus size. This will allow readers to assess the basis for the statements on neural approaches and emotion classifiers. revision: yes

  2. Referee: [Introduction] Introduction / Research Questions section: the claim that 'there is still no work focusing on this area' is asserted without evidence of a prior-survey search or citation analysis that would establish novelty.

    Authors: The novelty claim was made based on the authors' knowledge at submission. To address the concern, we will revise the introduction to include a brief account of our search for prior surveys on emotionally-aware chatbots or affective dialogue systems (e.g., via targeted queries in academic databases) and either cite any relevant prior work or document the absence of such surveys to substantiate the claim. revision: yes

Circularity Check

0 steps flagged

No circularity: survey summarizes external literature without internal derivations

full rationale

This is a literature survey paper whose central claims consist of observations drawn from prior external work on emotionally-aware chatbots. No equations, fitted parameters, predictions derived from the paper's own inputs, or self-referential uniqueness theorems appear. The statements about evolution from rule-based to neural approaches and the presence of emotion classifiers are presented as findings from the authors' review of outside sources, not as results that reduce by construction to any definition or fit internal to the manuscript. The forward-looking prediction is a qualitative remark, not a statistical or definitional output. The paper therefore contains no load-bearing steps that match the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a literature survey paper. It introduces no free parameters, mathematical axioms, or invented entities as it contains no original models or derivations.

pith-pipeline@v0.9.0 · 5752 in / 939 out tokens · 29073 ms · 2026-05-25T17:46:40.711162+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

68 extracted references · 68 canonical work pages · 5 internal anchors

  1. [1]

    Hadeel Al-Zubaide and Ayman A Issa. 2011. Ontbot: Ontolo gy based chatbot. In International Symposium on Innovations in Information and Communications Technology. IEEE, 7–12

    work page 2011

  2. [2]

    Nabiha Asghar, Pascal Poupart, Jesse Hoey, Xin Jiang, an d Lili Mou. 2018. Affec- tive neural response generation. In European Conference on Information Retrieval. Springer, 154–166

    work page 2018

  3. [3]

    Gilbert Badaro, Hussein Jundi, Hazem Hajj, and Wassim El -Hajj. 2018. EmoWordNet: Automatic Expansion of Emotion Lexicon Using E nglish Word- Net. In Proceedings of the Seventh Joint Conference on Lexical and Co mputational Semantics. 86–93

    work page 2018

  4. [4]

    Margaret M Bradley and Peter J Lang. 1999. Affective norms for English words (ANEW): Instruction manual and affective ratings . Technical Report. Technical Report C-1, The Center for Research in Psychophysiology, University of Florida

    work page 1999

  5. [5]

    Erik Cambria, Catherine Havasi, and Amir Hussain. 2012. Senticnet 2: A seman- tic and affective resource for opinion mining and sentiment a nalysis. In Twenty- Fifth International FLAIRS Conference

    work page 2012

  6. [6]

    Fabio Catania, Micol Spitale, Davide Fisicaro, and Fran ca Garzotto. 2019. CORK: A COnversational agent framewoRK exploiting both rational and emotional in- telligence. (2019)

    work page 2019

  7. [7]

    David Cohen and Ian Lane. 2016. An Oral Exam for Measuring a Dialog Sys- temâĂŹs Capabilities. In Thirtieth AAAI Conference on Artificial Intelligence

    work page 2016

  8. [8]

    Kenneth Mark Colby. 2013. Artificial paranoia: A computer simulation of paranoid processes. Vol. 49. Elsevier

    work page 2013

  9. [9]

    Pierre Colombo, Wojciech Witon, Ashutosh Modi, James Kennedy, and Mubbasir Kapadia. 2019. Affect-Driven Dialog Generation. arXiv preprint arXiv:1904.02793 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  10. [10]

    Lei Cui, Shaohan Huang, Furu Wei, Chuanqi Tan, Chaoqun D uan, and Ming Zhou. 2017. Superagent: A customer service chatbot for e-co mmerce websites. Proceedings of ACL 2017, System Demonstrations (2017), 97–102

    work page 2017

  11. [11]

    Jorge Carrillo de Albornoz, Laura Plaza, and Pablo Gerv ás. 2012. SentiSense: An easily scalable concept-based affective lexicon for sentim ent analysis.. In LREC. 3562–3567

    work page 2012

  12. [12]

    Aditya Deshpande, Alisha Shahane, Darshana Gadre, Mru nmayi Deshpande, and Prachi M Joshi. 2017. A Survey of Various Chatbot Impleme ntation Tech- niques. International Journal of Computer Engineering and Applica tions 11 (2017)

    work page 2017

  13. [13]

    M v Eeuwen. 2017. Mobile conversational commerce: messenger chatbots as the next interface between businesses and consumers . Master’s thesis. University of Twente

    work page 2017

  14. [14]

    Paul Ekman. 1992. An argument for basic emotions. Cognition & emotion 6, 3-4 (1992), 169–200

    work page 1992

  15. [15]

    Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari H oltzman, Yejin Choi, Noah A Smith, and Mari Ostendorf. 2018. Sounding Board: A Use r-Centric and Content-Driven Social Chatbot. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Ling uistics: Demonstra- tions. 96–100

    work page 2018

  16. [16]

    Eun Go and S Shyam Sundar. 2019. Humanizing Chatbots: Th e effects of vi- sual, identity and conversational cues on humanness percep tions. Computers in Human Behavior (2019)

    work page 2019

  17. [17]

    Braden Hancock, Antoine Bordes, Pierre-Emmanuel Maza re, and Jason Weston

    work page

  18. [18]

    Learning from Dialogue after Deployment: Feed Yourse lf, Chatbot! arXiv preprint arXiv:1901.05415 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 1901

  19. [19]

    Tianran Hu, Anbang Xu, Zhe Liu, Quanzeng You, Yufan Guo, Vibha Sinha, Jiebo Luo, and Rama Akkiraju. 2018. Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems . ACM, 415

    work page 2018

  20. [20]

    Chieh-Yang Huang and Lun-Wei Ku. 2018. EmotionPush: Emotion and Response Time Prediction Towards Human-Like Chatbots. In 2018 IEEE Global Communi- cations Conference (GLOBECOM) . IEEE, 206–212

    work page 2018

  21. [21]

    Minlie Huang, Zuoxian Ye, and Hao Zhou. 2017. Overview o f the NLPCC 2017 Shared Task: Emotion Generation Challenge. InNational CCF Conference on Nat- ural Language Processing and Chinese Computing . Springer, 926–936

    work page 2017

  22. [22]

    Shafquat Hussain, Omid Ameri Sianaki, and Nedal Ababne h. 2019. A Survey on Conversational Agents/Chatbots Classification and Desi gn Techniques. In Workshops of the International Conference on Advanced Info rmation Networking and Applications. Springer, 946–956

    work page 2019

  23. [23]

    Kothari, J

    A. Kothari, J. Hoover, and R. Zyane. 2017. Chatbots for ECommerce: Learn how to Build a Virtual Shopping Assistant . Bleeding Edge Press. https://books.google.it/books?id=DZ7cswEACAAJ

    work page 2017

  24. [24]

    Jia Li, Xiao Sun, Xing Wei, Changliang Li, and Jianhua Ta o. 2019. Reinforcement Learning Based Emotional Editing Constraint Conversation Generation. arXiv preprint arXiv:1904.08061 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  25. [25]

    Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, a nd Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) . 986–995

    work page 2017

  26. [26]

    Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Resp onse Generation. In Proceedings of the 2016 Conference on Empirical Methods in Na tural Language Processing. 2122–2132

    work page 2016

  27. [27]

    Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, and Sat oshi Nakamura. 2018. Elic- iting positive emotion through affect-sensitive dialogue r esponse generation: A neural network approach. In Thirty-Second AAAI Conference on Artificial Intelli- gence

    work page 2018

  28. [28]

    Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, and Sat oshi Nakamura. 2019. Pos- itive Emotion Elicitation in Chat-Based Dialogue Systems. IEEE/ACM Transac- tions on Audio, Speech, and Language Processing 27, 4 (2019), 866–877

    work page 2019

  29. [29]

    Bilyana Martinovski and David Traum. 2003. Breakdown i n human-machine interaction: the error is the clue. In Proceedings of the ISCA tutorial and research workshop on Error handling in dialogue systems . 11–16. Conference’17, July 2017, Washington, DC, USA Pamungkas

    work page 2003

  30. [30]

    Gary McKeown, Michel Valstar, Roddy Cowie, Maja Pantic , and Marc Schroder

    work page

  31. [31]

    IEEE Transactions on Affective Computing 3, 1 (2012), 5–17

    The semaine database: Annotated multimodal records o f emotionally col- ored conversations between a person and a limited agent. IEEE Transactions on Affective Computing 3, 1 (2012), 5–17

    work page 2012

  32. [32]

    MO Meira and AMP Canuto. 2015. Evaluation of Emotional A gents’ Architec- tures: an Approach Based on Quality Metrics and the Influence of Emotions on Users. In Proceedings of the World Congress on Engineering , Vol. 1

    work page 2015

  33. [33]

    Adam S Miner, Arnold Milstein, Stephen Schueller, Rosh ini Hegde, Christina Mangurian, and Eleni Linos. 2016. Smartphone-based conversational agents and responses to questions about mental health, interpersonal violence, and physical health. JAMA internal medicine 176, 5 (2016), 619–625

    work page 2016

  34. [34]

    Saif Mohammad. 2018. Obtaining reliable human ratings of valence, arousal, and dominance for 20,000 English words. InProceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: L ong Papers). 174–184

    work page 2018

  35. [35]

    Saif Mohammad and Felipe Bravo-Marquez. 2017. W ASSA-2 017 Shared Task on Emotion Intensity. In Proceedings of the 8th Workshop on Computational Ap- proaches to Subjectivity, Sentiment and Social Media Analy sis. 34–49

    work page 2017

  36. [36]

    Saif Mohammad, Felipe Bravo-Marquez, Mohammad Salame h, and Svetlana Kir- itchenko. 2018. Semeval-2018 task 1: Affect in tweets. In Proceedings of The 12th International Workshop on Semantic Evaluation . 1–17

    work page 2018

  37. [37]

    Saif M Mohammad and Peter D Turney. 2013. Crowdsourcing a word–emotion association lexicon. Computational Intelligence 29, 3 (2013), 436–465

    work page 2013

  38. [38]

    Kellie Morrissey and Jurek Kirakowski. 2013. âĂŸRealn essâĂŹ in Chatbots: Es- tablishing Quantifiable Criteria. In International Conference on Human-Computer Interaction. Springer, 87–96

    work page 2013

  39. [39]

    Osgood, G.J

    C.E. Osgood, G.J. Suci, and P.H. Tenenbaum. 1957. The Measurement of meaning. University of Illinois Press, Urbana:

    work page 1957

  40. [40]

    Baolin Peng, Xiujun Li, Lihong Li, Jianfeng Gao, Asli Ce likyilmaz, Sungjin Lee, and Kam-Fai Wong. 2017. Composite Task-Completion Dialogu e Policy Learn- ing via Hierarchical Deep Reinforcement Learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Process ing. 2231–2240

    work page 2017

  41. [41]

    James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates 71, 2001 (2001), 2001

    work page 2001

  42. [42]

    Robert Plutchik. 2001. The Nature of Emotions Human emo tions have deep evolutionary roots, a fact that may explain their complexit y and provide tools for clinical practice. American scientist 89, 4 (2001), 344–350

    work page 2001

  43. [43]

    Thomas S Polzin and Alexander Waibel. 2000. Emotion-se nsitive human- computer interfaces. In ISCA tutorial and research workshop (ITRW) on speech and emotion

    work page 2000

  44. [44]

    Soujanya Poria, Alexander Gelbukh, Amir Hussain, Newt on Howard, Dipankar Das, and Sivaji Bandyopadhyay. 2013. Enhanced SenticNet wi th affective labels for concept-based opinion mining. IEEE Intelligent Systems 28, 2 (2013), 31–38

    work page 2013

  45. [45]

    Helmut Prendinger and Mitsuru Ishizuka. 2005. The empa thic companion: A character-based interface that addresses users’affective states. Applied Artificial Intelligence 19, 3-4 (2005), 267–285

    work page 2005

  46. [46]

    Minghui Qiu, Feng-Lin Li, Siyu Wang, Xing Gao, Yan Chen, Weipeng Zhao, Haiqing Chen, Jun Huang, and Wei Chu. 2017. Alime chat: A sequ ence to se- quence and rerank based chatbot engine. In Proceedings of the 55th Annual Meet- ing of the Association for Computational Linguistics (Volume 2: Short Papers). 498– 503

    work page 2017

  47. [47]

    Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y- Lan Boureau. 2018. I know the feeling: Learning to converse with empathy. arXiv preprint arXiv:1811.00207 (2018)

    work page arXiv 2018

  48. [48]

    Alan Ritter, Colin Cherry, and William B Dolan. 2011. Da ta-driven response generation in social media. In Proceedings of the conference on empirical methods in natural language processing . Association for Computational Linguistics, 583– 593

    work page 2011

  49. [49]

    Iulian V Serban, Chinnadhurai Sankar, Mathieu Germain , Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Piep er, Sarath Chan- dar, Nan Rosemary Ke, et al. 2017. A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  50. [50]

    Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aa ron Courville, and Joelle Pineau. 2016. Building end-to-end dialogue systems using g enerative hierar- chical neural network models. In Thirtieth AAAI Conference on Artificial Intelli- gence

    work page 2016

  51. [51]

    Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural Re sponding Machine for Short-Text Conversation. In Proceedings of the 53rd Annual Meeting of the As- sociation for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) , Vol. 1. 1577–1586

    work page 2015

  52. [52]

    Roman Shantala, Gennadiv Kyselov, and Anna Kyselova. 2 018. Neural Dialogue System with Emotion Embeddings. In 2018 IEEE First International Conference on System Analysis & Intelligent Computing (SAIC) . IEEE, 1–4

    work page 2018

  53. [53]

    Bayan Abu Shawar and Eric Atwell. 2007. Chatbots: are th ey really useful?. In Ldv forum, Vol. 22. 29–49

    work page 2007

  54. [54]

    Alessandro Sordoni, Michel Galley, Michael Auli, Chri s Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dol an. 2015. A Neu- ral Network Approach to Context-Sensitive Generation of Co nversational Re- sponses. In Proceedings of the 2015 Conference of the North American Chap - ter of the Association for Computational Linguist...

    work page doi:10.3115/v1/n15-1020 2015

  55. [55]

    Jacopo Staiano and Marco Guerini. 2014. Depeche Mood: a Lexicon for Emo- tion Analysis from Crowd Annotated News. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics ( Volume 2: Short Papers), Vol. 2. 427–433

    work page 2014

  56. [56]

    Carlo Strapparava, Alessandro Valitutti, et al. 2004. Wordnet affect: an affective extension of wordnet.. In LREC, Vol. 4. Citeseer, 40

    work page 2004

  57. [57]

    Xiao Sun, Xinmiao Chen, Zhengmeng Pei, and Fuji Ren. 201 8. Emotional Hu- man Machine Conversation Generation Based on SeqGAN. In 2018 First Asian Conference on Affective Computing and Intelligent Interact ion (ACII Asia) . IEEE, 1–6

    work page 2018

  58. [58]

    Andree Thieltges, Florian Schmidt, and Simon Hegelich . 2016. The devilâĂŹs triangle: Ethical considerations on developing bot detect ion methods. In 2016 AAAI Spring Symposium Series

    work page 2016

  59. [59]

    Alan M Turing. 2009. Computing machinery and intellige nce. In Parsing the Turing Test. Springer, 23–65

    work page 2009

  60. [60]

    Joseph Weizenbaum. 1966. ELIZA—a computer program for the study of natural language communication between man and machine. Commun. ACM 9, 1 (1966), 36–45

    work page 1966

  61. [61]

    Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M Rojas Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A Network-based End-to-End Trainable Task-oriented Dialogue System. In Proceedings of the 15th Conference of the European Chapter of the Association for Co mputational Linguis- tics: Volume 1, Long Papers . 438–449

    work page 2017

  62. [62]

    Cynthia Whissell. 2009. Using the revised dictionary o f affect in language to quantify the emotional undertones of samples of natural language. Psychological reports 105, 2 (2009), 509–521

    work page 2009

  63. [63]

    Zhou Yu, Alexandros Papangelis, and Alexander Rudnick y. 2015. TickTock: A non-goal-oriented multimodal dialog system with engageme nt awareness. In 2015 AAAI Spring symposium series

    work page 2015

  64. [64]

    Rui Zhang, Zhenyu Wang, and Dongcheng Mai. 2017. Buildi ng emotional con- versation systems using multi-task Seq2Seq learning. InNational CCF Conference on Natural Language Processing and Chinese Computing . Springer, 612–621

    work page 2017

  65. [65]

    Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szla m, Douwe Kiela, and Jason Weston. 2018. Personalizing Dialogue Agents: I have a dog, do you have pets too?. In Proceedings of the 56th Annual Meeting of the Association for Com- putational Linguistics (Volume 1: Long Papers) . 2204–2213

    work page 2018

  66. [66]

    Peixiang Zhong, Di Wang, and Chunyan Miao. 2018. An Affec t-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss. arXiv preprint arXiv:1811.07078 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  67. [67]

    Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, an d Bing Liu. 2018. Emotional chatting machine: Emotional conversation gener ation with internal and external memory. In Thirty-Second AAAI Conference on Artificial Intelli- gence

    work page 2018

  68. [68]

    sample-franklin.png

    Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2018 . The Design and Implementation of XiaoIce, an Empathetic Social Chatbo t. arXiv preprint arXiv:1812.08989 (2018). This figure "sample-franklin.png" is available in "png" format from: http://arxiv.org/ps/1906.09774v1

    work page arXiv 2018