---
title: "Can You be More Social? Injecting Politeness and Positivity into"
description: "The authors study customer-service chats in which human representatives guide drivers through… 77 references, cited by 4 papers here."
authors: ["Yi-Chia Wang", "Alexandros Papangelis", "Runze Wang", "Zhaleh Feizollahi", "Gokhan Tur", "Robert Kraut"]
year: 2020
venue: "arXiv:2012.14653"
source: "https://arxiv.org/abs/2012.14653"
doi: "10.48550/arxiv.2012.14653"
arxiv: "2012.14653"
licence: "arXiv non-exclusive distribution licence (read only, no redistribution)"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2020-more-social-injecting-politeness-positivity/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2020-more-social-injecting-politeness-positivity/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/7/) / Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents

# Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents

**Authors:** [Yi-Chia Wang](https://md.research.elamur.ai/free/en/authors/yi-chia-wang/), [Alexandros Papangelis](https://md.research.elamur.ai/free/en/authors/alexandros-papangelis/), Runze Wang, Zhaleh Feizollahi, [Gokhan Tur](https://md.research.elamur.ai/free/en/authors/gokhan-tur/) and Robert Kraut · **Year:** 2020 · **Venue:** arXiv:2012.14653 · **Licence:** [arXiv non-exclusive distribution licence (read only, no redistribution)](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2012.14653) · [PDF](https://arxiv.org/pdf/2012.14653) · [DOI 10.48550/arxiv.2012.14653](https://doi.org/10.48550/arxiv.2012.14653) · [arXiv 2012.14653](https://arxiv.org/abs/2012.14653) · [OpenAlex](https://openalex.org/W3116880344)

**Citations:** 6 citations (OpenAlex, 2026-10-14) · [4](https://md.research.elamur.ai/free/en/papers/wang-2020-more-social-injecting-politeness-positivity/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Task-oriented dialogue systems are usually built to deliver correct content and mostly ignore the social side of language. The authors study customer-service chats in which human representatives guide drivers through registering with a ride-sharing company. They first ask whether conversational style matters. Representative messages are scored for politeness and positivity with off-the-shelf pretrained classifiers, and statistical models relate these scores to two outcomes: whether drivers replied within a day and whether they finished their first trip. Politeness predicted both outcomes favorably. Positivity, measured as positive sentiment, predicted trip completion but, unexpectedly, lower responsiveness. In a second study, a seq2seq generator is extended with a social-language understanding component, so the politeness or positivity level of a reply can be steered while its task content stays fixed. Automatic measures showed that both styles could be shifted without losing content. Crowdworkers confirmed the politeness gain but not the positivity one. The work links measurable style to real task outcomes, and it shows how a weak proxy measure can distort conclusions.

## Key points
- Domain: driver-onboarding chats between drivers and customer service representatives (CSRs) at a ride-sharing provider. The outcomes were a binary "driver replied within 24 hours" and completion of the first trip.
- Politeness in CSR messages correlated positively with both responsiveness and first-trip completion.
- Positivity correlated positively with first-trip completion but negatively with responsiveness. This held even after excluding congratulatory milestone messages and messages without a question mark.
- The generation model ("Lexical+Social") is a seq2seq architecture. The lexical part governs content and a social-language component governs politeness or positivity level.
- Human evaluation used three crowdworkers, three questions, and a majority vote:
  - No difference in appropriateness (Q1, Q2) between enhanced and unenhanced replies.
  - Politeness-enhanced replies were judged more polite 44% of the time; unenhanced replies were judged more polite only 13% of the time.
  - Positivity enhancement was not perceived.
  - Kappa was fair to moderate: politeness .5/.4/.3, positivity .3/.4/.2.

## Interesting ideas
- Pretrained style classifiers can serve as measuring instruments, and their scores can be regressed against real behavioral outcomes rather than just reported as labels.
- Content and style are kept in separate channels during generation, so style can be changed while appropriateness is checked separately.
- The authors stress-tested a surprising correlation by removing obvious confounding message types (congratulations, messages without questions) and rerunning the analysis.
- The positivity failure is traced to a gap between the intended concept and its proxy (sentiment), and both measurement and manipulation inherited that gap.
- The human evaluation combines a pairwise "which is more X" question with separate appropriateness questions, and reports inter-rater agreement for each one.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): Politeness and positivity scores could be attached as explainable attributes of speech acts in prag, and tested on whether they predict how a dialogue continues.
- **I2** (back): The graph → text generator could take a register parameter (neutral or polite) applied only at surface realization, with a check that the regenerated graph is unchanged.
- **I3** (learn): Evaluation with negative controls could routinely drop suspected confound subsets to see whether a metric gain survives.
- **I4** (frames): When modeling irony or implicature, Mova should not treat a sentiment score as the pragmatic stance itself, and should flag where proxy and concept diverge.
- **I5** (back): Generated or translated text could be judged pairwise for style and separately for content fidelity, with agreement reported to expose unclear guidelines.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 365 works · 158,048 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 401 works

## Cite

Cite as: Yi-Chia Wang, Alexandros Papangelis, Runze Wang, Zhaleh Feizollahi, Gokhan Tur and Robert Kraut. 2020. Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents. arXiv:2012.14653.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{wang2020can,
  title = {{Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents}},
  author = {Yi-Chia Wang, Alexandros Papangelis, Runze Wang, Zhaleh Feizollahi, Gokhan Tur and Robert Kraut},
  year = {2020},
  doi = {10.48550/arxiv.2012.14653},
  eprint = {2012.14653},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2012.14653}
}
```

- [← previous Automated Phonological Transcription of Akkadian Cuneiform Text](https://md.research.elamur.ai/free/en/papers/sahala-2020-automated-phonological-transcription-akkadian-cuneiform/)
- [next → Functional structure in the noun phrase: revisiting Hebrew nominals](https://md.research.elamur.ai/free/en/papers/preminger-2020-functional-structure-noun-phrase-revisiting/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/7/)

## References

77 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Frank J Bernieri and Robert Rosenthal. 1991. Interpersonal coordination: Behavior matching and interactional synchrony. (1991). [find](https://scholar.google.com/scholar?q=Frank+J+Bernieri+and+Robert+Rosenthal%2E+1991%2E+Interpersonal+coordination%3A+Behavior+matching+and+interactional+synchrony%2E+%281991%29%2E)
2. Elisabetta Bevacqua, Maurizio Mancini, Radoslaw Niewiadomski, and Catherine Pelachaud. 2007. An expressive ECA showing complex emotions. In Proceedings of the AISB annual convention, Newcastle, UK. 208–216. [find](https://scholar.google.com/scholar?q=Elisabetta+Bevacqua%2C+Maurizio+Mancini%2C+Radoslaw+Niewiadomski%2C+and+Catherine+Pelachaud%2E+2007%2E+An+expressive+ECA+showing+complex+emotions%2E+In+Proceedings+of+the+AISB+annual+convention%2C+Newcastle%2C+UK%2E+20)
3. Timothy Bickmore and Justine Cassell. 2001. Relational Agents: A Model and Implementation of Building User Trust. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’01). ACM, New York, NY, USA, 396–403. DOI: http://dx.doi.org/10.1145/365024.365304 [↗](https://doi.org/10.1145/365024.365304)
4. Timothy W. Bickmore, Laura M. Pfeifer, and Brian W. Jack. 2009. Taking the Time to Care: Empowering Low Health Literacy Hospital Patients with Virtual Nurse Agents. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’09). ACM, New York, NY, USA, 1265–1274. DOI: http://dx.doi.org/10.1145/1518701.1518891 [↗](https://doi.org/10.1145/1518701.1518891)
5. Timothy W. Bickmore and Rosalind W. Picard. 2005. Establishing and Maintaining Long-term Human-computer Relationships. ACM Trans. Comput.-Hum. Interact. 12, 2 (June 2005), 293–327. DOI: http://dx.doi.org/10.1145/1067860.1067867 [↗](https://doi.org/10.1145/1067860.1067867)
6. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python (1st ed.). O’Reilly Media, Inc. [find](https://scholar.google.com/scholar?q=Steven+Bird%2C+Ewan+Klein%2C+and+Edward+Loper%2E+2009%2E+Natural+Language+Processing+with+Python+%281st+ed%2E%29%2E+O%E2%80%99Reilly+Media%2C+Inc%2E)
7. Lois Bloom and Margaret Lahey. 1978. Language development and language disorders. ERIC. [↗](https://doi.org/10.7916/d8qz2gq5)
8. Jacqueline Brixey and David Novick. 2019. Building rapport with extraverted and introverted agents. In Advanced Social Interaction with Agents. Springer, 3–13. [↗](https://doi.org/10.1007/978-3-319-92108-2_1)
9. Justine Cassell and Timothy Bickmore. 2003. Negotiated Collusion: Modeling Social Language and its Relationship Effects in Intelligent Agents. User Modeling and User-Adapted Interaction 13, 1 (01 Feb 2003), 89–132. DOI: http://dx.doi.org/10.1023/A:1024026532471 [↗](https://doi.org/10.1023/a:1024026532471)
10. Praveen Chandar, Yasaman Khazaeni, Matthew Davis, Michael Muller, Marco Crasso, Q Vera Liao, N Sadat Shami, and Werner Geyer. 2017. Leveraging conversational systems to assists new hires during onboarding. In IFIP Conference on Human-Computer Interaction. Springer, 381–391. [find](https://scholar.google.com/scholar?q=Praveen+Chandar%2C+Yasaman+Khazaeni%2C+Matthew+Davis%2C+Michael+Muller%2C+Marco+Crasso%2C+Q+Vera+Liao%2C+N+Sadat+Shami%2C+and+Werner+Geyer%2E+2017%2E+Leveraging+conversational+systems+to+assists+new+hires+during+onboar)
11. Sumit Chopra, Michael Auli, and Alexander M Rush. 2016. [Abstractive sentence summarization with attentive recurrent neural networks](https://md.research.elamur.ai/free/en/papers/chopra-2016-abstractive-sentence-summarization-attentive-recurrent/). In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 93–98.
12. Herbert H Clark. 1996. Using Language. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Herbert+H+Clark%2E+1996%2E+Using+Language%2E+Cambridge+University+Press%2E)
13. Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20, 1 (1960), 37–46. [↗](https://doi.org/10.1177/001316446002000104)
14. Nancy L Collins and Lynn Carol Miller. 1994. Self-disclosure and liking: a meta-analytic review. Psychological bulletin 116, 3 (1994), 457. [↗](https://doi.org/10.1037//0033-2909.116.3.457)
15. Anthony J Conger. 1980. Integration and generalization of kappas for multiple raters. Psychological Bulletin 88, 2 (1980), 322. [↗](https://doi.org/10.1037//0033-2909.88.2.322)
16. Marianne Dainton, Laura Stafford, and Daniel J Canary. 1994. Maintenance strategies and physical affection as predictors of love, liking, and satisfaction in marriage. Communication Reports 7, 2 (1994), 88–98. [↗](https://doi.org/10.1080/08934219409367591)
17. Cristian Danescu-Niculescu-Mizil, Moritz Sudhof, Dan Jurafsky, Jure Leskovec, and Christopher Potts. 2013. [A computational approach to politeness with application to social factors](https://md.research.elamur.ai/free/en/papers/mizil-2013-computational-approach-politeness-application-social/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 1: Long Papers. 250–259. http://aclweb.org/anthology/P/P13/P13-1025.pdf [↗](https://aclanthology.org/P13-1025/)
18. David DeVault, Ron Artstein, Grace Benn, Teresa Dey, Ed Fast, Alesia Gainer, Kallirroi Georgila, Jon Gratch, Arno Hartholt, Margaux Lhommet, and others. 2014. SimSensei Kiosk: A virtual human interviewer for healthcare decision support. In Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 1061–1068. [find](https://scholar.google.com/scholar?q=David+DeVault%2C+Ron+Artstein%2C+Grace+Benn%2C+Teresa+Dey%2C+Ed+Fast%2C+Alesia+Gainer%2C+Kallirroi+Georgila%2C+Jon+Gratch%2C+Arno+Hartholt%2C+Margaux+Lhommet%2C+and+others%2E+2014%2E+SimSensei+Kiosk%3A+A+virtual+human+intervie)
19. Sidney D’mello and Art Graesser. 2012. AutoTutor and affective AutoTutor: Learning by talking with cognitively and emotionally intelligent computers that talk back. ACM Transactions on Interactive Intelligent Systems (TiiS) 2, 4 (2012), 23. [find](https://scholar.google.com/scholar?q=Sidney+D%E2%80%99mello+and+Art+Graesser%2E+2012%2E+AutoTutor+and+affective+AutoTutor%3A+Learning+by+talking+with+cognitively+and+emotionally+intelligent+computers+that+talk+back%2E+ACM+Transactions+on+Interactive+Int)
20. Aimee L Drolet and Michael W Morris. 2000. Rapport in conflict resolution: Accounting for how face-to-face contact fosters mutual cooperation in mixed-motive conflicts. Journal of Experimental Social Psychology 36, 1 (2000), 26–50. [↗](https://doi.org/10.1006/jesp.1999.1395)
21. Dana Garbarski, Nora Cate Schaeffer, and Jennifer Dykema. 2016. Interviewing practices, conversational practices, and rapport: responsiveness and engagement in the standardized survey interview. Sociological methodology 46, 1 (2016), 1–38. [↗](https://doi.org/10.1177/0081175016637890)
22. Howard Giles, Nikolas Coupland, and IUSTINE Coupland. 1991. 1. Accommodation theory: Communication, context, and. Contexts of accommodation: Developments in applied sociolinguistics 1 (1991). [find](https://scholar.google.com/scholar?q=Howard+Giles%2C+Nikolas+Coupland%2C+and+IUSTINE+Coupland%2E+1991%2E+1%2E+Accommodation+theory%3A+Communication%2C+context%2C+and%2E+Contexts+of+accommodation%3A+Developments+in+applied+sociolinguistics+1+%281991%29%2E)
23. Ulrich Gnewuch, Stefan Morana, and Alexander Maedche. 2017. Towards designing cooperative and social conversational agents for customer service. (2017). [find](https://scholar.google.com/scholar?q=Ulrich+Gnewuch%2C+Stefan+Morana%2C+and+Alexander+Maedche%2E+2017%2E+Towards+designing+cooperative+and+social+conversational+agents+for+customer+service%2E+%282017%29%2E)
24. R. Gockley, A. Bruce, J. Forlizzi, M. Michalowski, A. Mundell, S. Rosenthal, B. Sellner, R. Simmons, K. Snipes, A. C. Schultz, and Jue Wang. 2005. Designing robots for long-term social interaction. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems. 1338–1343. DOI: http://dx.doi.org/10.1109/IROS.2005.1545303 [↗](https://doi.org/10.1109/iros.2005.1545303)
25. Jonathan Gratch, Ning Wang, Jillian Gerten, Edward Fast, and Robin Duffy. 2007. Creating rapport with virtual agents. In International workshop on intelligent virtual agents. Springer, 125–138. [find](https://scholar.google.com/scholar?q=Jonathan+Gratch%2C+Ning+Wang%2C+Jillian+Gerten%2C+Edward+Fast%2C+and+Robin+Duffy%2E+2007%2E+Creating+rapport+with+virtual+agents%2E+In+International+workshop+on+intelligent+virtual+agents%2E+Springer%2C+125%E2%80%93138%2E)
26. H Paul Grice. 1975. Logic and conversation. 1975 (1975), 41–58. [↗](https://doi.org/10.1163/9789004368811_003)
27. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780. [↗](https://doi.org/10.1162/neco.1997.9.8.1735)
28. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. [Toward controlled generation of text](https://md.research.elamur.ai/free/en/papers/hu-2017-toward-controlled-generation-text/). arXiv preprint arXiv:1703.00955 (2017). [↗](https://arxiv.org/abs/1703.00955)
29. Bernd Huber, Daniel McDuff, Chris Brockett, Michel Galley, and Bill Dolan. 2018. Emotional Dialogue Generation Using Image-Grounded Language Models. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). ACM, New York, NY, USA, Article 277, 12 pages. DOI: http://dx.doi.org/10.1145/3173574.3173851 [↗](https://doi.org/10.1145/3173574.3173851)
30. Clayton J. Hutto and Eric Gilbert. 2014. VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. In Proceedings of the Eighth International Conference on Weblogs and Social Media, ICWSM 2014, Ann Arbor, Michigan, USA, June 1-4, 2014. [http://www.aaai.org/ocs/index.php/ICWSM/ICWSM14/paper/view/8109](http://www.aaai.org/ocs/index.php/ICWSM/ICWSM14/paper/view/8109) [↗](http://www.aaai.org/ocs/index.php/ICWSM/ICWSM14/paper/view/8109)
31. Barbara Johnstone. 1989. Linguistic strategies and cultural styles for persuasive discourse. Language, communication, and culture (1989), 139–156. [find](https://scholar.google.com/scholar?q=Barbara+Johnstone%2E+1989%2E+Linguistic+strategies+and+cultural+styles+for+persuasive+discourse%2E+Language%2C+communication%2C+and+culture+%281989%29%2C+139%E2%80%93156%2E)
32. Sin-Hwa Kang, Jonathan Gratch, Candy Sidner, Ron Artstein, Lixing Huang, and Louis-Philippe Morency. 2012. Towards building a virtual counselor: modeling nonverbal behavior during intimate self-disclosure. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1. International Foundation for Autonomous Agents and Multiagent Systems, 63–70. [find](https://scholar.google.com/scholar?q=Sin%2DHwa+Kang%2C+Jonathan+Gratch%2C+Candy+Sidner%2C+Ron+Artstein%2C+Lixing+Huang%2C+and+Louis%2DPhilippe+Morency%2E+2012%2E+Towards+building+a+virtual+counselor%3A+modeling+nonverbal+behavior+during+intimate+self%2Ddisclo)
33. Chandra Khatri, Anu Venkatesh, Behnam Hedayatnia, Ashwin Ram, Raefer Gabriel, and Rohit Prasad. 2018. Alexa Prize-State of the Art in Conversational AI. AI Magazine 39, 3 (2018), 40–55. [↗](https://doi.org/10.1609/aimag.v39i3.2810)
34. Bart P Knijnenburg and Martijn C Willemsen. 2016. Inferring capabilities of intelligent agents from their external traits. ACM Transactions on Interactive Intelligent Systems (TiiS) 6, 4 (2016), 28. [↗](https://doi.org/10.1145/2963106)
35. Adam DI Kramer, Jamie E Guillory, and Jeffrey T Hancock. 2014. Experimental evidence of massive-scale emotional contagion through social networks. Proceedings of the National Academy of Sciences (2014), 201320040. [↗](https://doi.org/10.1073/pnas.1320040111)
36. Iolanda Leite, Carlos Martinho, and Ana Paiva. 2013. Social robots for long-term interaction: a survey. International Journal of Social Robotics 5, 2 (2013), 291–308. [↗](https://doi.org/10.1007/s12369-013-0178-y)
37. Penelope Levinson, Penelope Brown, Stephen C Levinson, and Stephen C Levinson. 1987. [Politeness](https://md.research.elamur.ai/free/en/papers/brown-1987-politeness-some-universals-language-usage/): Some universals in language usage. Vol. 4. Cambridge university press.
38. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. [A Diversity-Promoting Objective Function for Neural Conversation Models](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/). In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 110–119. DOI: http://dx.doi.org/10.18653/v1/N16-1014 [↗](https://doi.org/10.18653/v1/n16-1014)
39. Q. Vera Liao, Matthew Davis, Werner Geyer, Michael Muller, and N. Sadat Shami. 2016. What Can You Do?: Studying Social-Agent Orientation and Agent Proactive Interactions with an Agent for Employees. In Proceedings of the 2016 ACM Conference on Designing Interactive Systems (DIS ’16). ACM, New York, NY, USA, 264–275. DOI: http://dx.doi.org/10.1145/2901790.2901842 [↗](https://doi.org/10.1145/2901790.2901842)
40. Richard J Light. 1971. Measures of response agreement for qualitative data: some generalizations and alternatives. Psychological bulletin 76, 5 (1971), 365. [↗](https://doi.org/10.1037/h0031643)
41. Yoichi Matsuyama, Arjun Bhardwaj, Ran Zhao, Oscar Romeo, Sushma Akoju, and Justine Cassell. 2016. Socially-aware animated intelligent personal assistant agent. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 224–227. [find](https://scholar.google.com/scholar?q=Yoichi+Matsuyama%2C+Arjun+Bhardwaj%2C+Ran+Zhao%2C+Oscar+Romeo%2C+Sushma+Akoju%2C+and+Justine+Cassell%2E+2016%2E+Socially%2Daware+animated+intelligent+personal+assistant+agent%2E+In+Proceedings+of+the+17th+Annual+Meetin)
42. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. [Efficient estimation of word representations in vector space](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). arXiv preprint arXiv:1301.3781 (2013). [↗](https://arxiv.org/abs/1301.3781)
43. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013b. [Distributed Representations of Words and Phrases and Their Compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2 (NIPS’13). Curran Associates Inc., USA, 3111–3119. http://dl.acm.org/citation.cfm?id=2999792.2999959 [↗](https://doi.org/10.48550/arxiv.1310.4546)
44. Youngme Moon. 2000. Intimate exchanges: Using computers to elicit self-disclosure from consumers. Journal of consumer research 26, 4 (2000), 323–339. [↗](https://doi.org/10.1086/209566)
45. Youngme Moon. 2003. Don’t blame the computer: When self-disclosure moderates the self-serving bias. Journal of Consumer Psychology 13, 1-2 (2003), 125–137. [↗](https://doi.org/10.1207/153276603768344843)
46. Janice Nadler. 2003. Rapport in negotiation and conflict resolution. Marq. L. Rev. 87 (2003), 875. [find](https://scholar.google.com/scholar?q=Janice+Nadler%2E+2003%2E+Rapport+in+negotiation+and+conflict+resolution%2E+Marq%2E+L%2E+Rev%2E+87+%282003%29%2C+875%2E)
47. Clifford Nass and Youngme Moon. 2000. Machines and mindlessness: Social responses to computers. Journal of social issues 56, 1 (2000), 81–103. [↗](https://doi.org/10.1111/0022-4537.00153)
48. Radoslaw Niewiadomski, Magalie Ochs, and Catherine Pelachaud. 2008. Expressions of empathy in ECAs. In International Workshop on Intelligent Virtual Agents. Springer, 37–44. [find](https://scholar.google.com/scholar?q=Radoslaw+Niewiadomski%2C+Magalie+Ochs%2C+and+Catherine+Pelachaud%2E+2008%2E+Expressions+of+empathy+in+ECAs%2E+In+International+Workshop+on+Intelligent+Virtual+Agents%2E+Springer%2C+37%E2%80%9344%2E)
49. Shereen Oraby, Lena Reed, Shubhangi Tandon, Sharath T.S., Stephanie Lukin, and Marilyn Walker. 2018. Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, 180–190. http://aclweb.org/anthology/W18-5019 [↗](https://aclanthology.org/W18-5019/)
50. Alexandros Papangelis, Ran Zhao, and Justine Cassell. 2014. Towards a computational architecture of dyadic rapport management for virtual agents. In International Conference on Intelligent Virtual Agents. Springer, 320–324. [find](https://scholar.google.com/scholar?q=Alexandros+Papangelis%2C+Ran+Zhao%2C+and+Justine+Cassell%2E+2014%2E+Towards+a+computational+architecture+of+dyadic+rapport+management+for+virtual+agents%2E+In+International+Conference+on+Intelligent+Virtual+Age)
51. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [BLEU: A Method for Automatic Evaluation of Machine Translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics (ACL ’02). Association for Computational Linguistics, Stroudsburg, PA, USA, 311–318. DOI: http://dx.doi.org/10.3115/1073083.1073135 [↗](https://doi.org/10.3115/1073083.1073135)
52. Bhargavi Paranjape, Yubin Ge, Zhen Bai, Jessica Hammer, and Justine Cassell. 2018. Towards Automatic Generation of Peer-Targeted Science Talk in Curiosity-Evoking Virtual Agent. In Proceedings of the 18th International Conference on Intelligent Virtual Agents. ACM, 71–78. [find](https://scholar.google.com/scholar?q=Bhargavi+Paranjape%2C+Yubin+Ge%2C+Zhen+Bai%2C+Jessica+Hammer%2C+and+Justine+Cassell%2E+2018%2E+Towards+Automatic+Generation+of+Peer%2DTargeted+Science+Talk+in+Curiosity%2DEvoking+Virtual+Agent%2E+In+Proceedings+of+the+)
53. 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. [find](https://scholar.google.com/scholar?q=James+W+Pennebaker%2C+Martha+E+Francis%2C+and+Roger+J+Booth%2E+2001%2E+Linguistic+inquiry+and+word+count%3A+LIWC+2001%2E+Mahway%3A+Lawrence+Erlbaum+Associates+71%2C+2001+%282001%29%2C+2001%2E)
54. Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. 2018. [Style Transfer Through Back-Translation](https://md.research.elamur.ai/free/en/papers/prabhumoye-2018-style-transfer-through-back-translation/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 866–876. http://aclweb.org/anthology/P18-1080 [↗](https://aclanthology.org/P18-1080/)
55. Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, and others. 2018. Conversational ai: The science behind the alexa prize. arXiv preprint arXiv:1801.03604 (2018). [↗](https://arxiv.org/abs/1801.03604)
56. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. [Controlling politeness in neural machine translation via side constraints](https://md.research.elamur.ai/free/en/papers/sennrich-2016-controlling-politeness-neural-machine-translation/). In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 35–40.
57. Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C Courville, and Joelle Pineau. 2016. [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/).. In AAAI, Vol. 16. 3776–3784. [↗](https://doi.org/10.1609/aaai.v30i1.9883)
58. Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. [Neural Responding Machine for Short-Text Conversation](https://md.research.elamur.ai/free/en/papers/shang-2015-neural-responding-machine-short-text/). In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 1577–1586. DOI: http://dx.doi.org/10.3115/v1/P15-1152 [↗](https://doi.org/10.3115/v1/p15-1152)
59. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. [Style transfer from non-parallel text by cross-alignment](https://md.research.elamur.ai/free/en/papers/shen-2017-style-transfer-non-parallel-text/). In Advances in Neural Information Processing Systems. 6830–6841. [↗](https://doi.org/10.48550/arxiv.1705.09655)
60. Heung-yeung Shum, Xiao-dong He, and Di Li. 2018. From Eliza to XiaoIce: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering 19, 1 (01 Jan 2018), 10–26. DOI: http://dx.doi.org/10.1631/FITEE.1700826 [↗](https://doi.org/10.1631/fitee.1700826)
61. Farhad Bin Siddique, Onno Kampman, Yang Yang, Anik Dey, and Pascale Fung. 2017. Zara returns: Improved personality induction and adaptation by an empathetic virtual agent. Proceedings of ACL 2017, system demonstrations (2017), 121–126. [find](https://scholar.google.com/scholar?q=Farhad+Bin+Siddique%2C+Onno+Kampman%2C+Yang+Yang%2C+Anik+Dey%2C+and+Pascale+Fung%2E+2017%2E+Zara+returns%3A+Improved+personality+induction+and+adaptation+by+an+empathetic+virtual+agent%2E+Proceedings+of+ACL+2017%2C+sys)
62. Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. 2015. [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://md.research.elamur.ai/free/en/papers/sordoni-2015-neural-network-approach-context-sensitive/). In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 196–205. DOI: http://dx.doi.org/10.3115/v1/N15-1020 [↗](https://doi.org/10.3115/v1/n15-1020)
63. Helen Spencer-Oatey. 2005. (Im) Politeness, face and perceptions of rapport: unpackaging their bases and interrelationships. (2005). [↗](https://doi.org/10.1515/jplr.2005.1.1.95)
64. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 3104–3112. http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks. pdf [↗](https://doi.org/10.48550/arxiv.1409.3215)
65. Jan Svennevig. 2000. Getting acquainted in conversation. John Benjamins. [↗](https://doi.org/10.1075/pbns.64)
66. David Sweetman and Fred Luthans. 2010. The power of positive psychology: Psychological capital and work engagement. Work engagement: A handbook of essential theory and research (2010), 54–68. [find](https://scholar.google.com/scholar?q=David+Sweetman+and+Fred+Luthans%2E+2010%2E+The+power+of+positive+psychology%3A+Psychological+capital+and+work+engagement%2E+Work+engagement%3A+A+handbook+of+essential+theory+and+research+%282010%29%2C+54%E2%80%9368%2E)
67. Linda Tickle-Degnen and Robert Rosenthal. 1990. The nature of rapport and its nonverbal correlates. Psychological inquiry 1, 4 (1990), 285–293. [↗](https://doi.org/10.1207/s15327965pli0104_1)
68. Oriol Vinyals and Quoc V. Le. 2015. [A Neural Conversational Model](https://md.research.elamur.ai/free/en/papers/vinyals-2015-neural-conversational-model/). CoRR abs/1506.05869 (2015). http://arxiv.org/abs/1506.05869 [↗](https://arxiv.org/abs/1506.05869)
69. Marilyn A Walker, Janet E Cahn, and Stephen J Whittaker. 1997. Improvising linguistic style: Social and affective bases for agent personality. In Proceedings of the first international conference on Autonomous agents. ACM, 96–105. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9702015)
70. Joseph Weizenbaum. 1966. ELIZA&Mdash;a Computer Program for the Study of Natural Language Communication Between Man and Machine. Commun. ACM 9, 1 (Jan. 1966), 36–45. DOI: http://dx.doi.org/10.1145/365153.365168 [↗](https://doi.org/10.1145/365153.365168)
71. Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. 2005. [Recognizing Contextual Polarity in Phrase-level Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wilson-2005-recognizing-contextual-polarity-phrase-level/). In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT ’05). Association for Computational Linguistics, Stroudsburg, PA, USA, 347–354. DOI: http://dx.doi.org/10.3115/1220575.1220619 [↗](https://doi.org/10.3115/1220575.1220619)
72. Genta Indra Winata, Onno Kampman, Yang Yang, Anik Dey, and Pascale Fung. 2017. Nora the Empathetic Psychologist.. In INTERSPEECH. 3437–3438. [find](https://scholar.google.com/scholar?q=Genta+Indra+Winata%2C+Onno+Kampman%2C+Yang+Yang%2C+Anik+Dey%2C+and+Pascale+Fung%2E+2017%2E+Nora+the+Empathetic+Psychologist%2E%2E+In+INTERSPEECH%2E+3437%E2%80%933438%2E)
73. Jun Yin, Xin Jiang, Zhengdong Lu, Lifeng Shang, Hang Li, and Xiaoming Li. 2016. Neural Generative Question Answering. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI’16). AAAI Press, 2972–2978. http://dl.acm.org/citation.cfm?id=3060832.3061037 [↗](https://doi.org/10.60692/y5y81-5aw90)
74. Zhou Yu, Alexandros Papangelis, and Alexander Rudnicky. 2015. TickTock: A non-goal-oriented multimodal dialog system with engagement awareness. In 2015 AAAI Spring symposium series. [find](https://scholar.google.com/scholar?q=Zhou+Yu%2C+Alexandros+Papangelis%2C+and+Alexander+Rudnicky%2E+2015%2E+TickTock%3A+A+non%2Dgoal%2Doriented+multimodal+dialog+system+with+engagement+awareness%2E+In+2015+AAAI+Spring+symposium+series%2E)
75. Ran Zhao, Alexandros Papangelis, and Justine Cassell. 2014. Towards a dyadic computational model of rapport management for human-virtual agent interaction. In International Conference on Intelligent Virtual Agents. Springer, 514–527. [find](https://scholar.google.com/scholar?q=Ran+Zhao%2C+Alexandros+Papangelis%2C+and+Justine+Cassell%2E+2014%2E+Towards+a+dyadic+computational+model+of+rapport+management+for+human%2Dvirtual+agent+interaction%2E+In+International+Conference+on+Intelligent+V)
76. Ran Zhao, Oscar J Romero, and Alex Rudnicky. 2018. SOGO: A Social Intelligent Negotiation Dialogue System. In Proceedings of the 18th International Conference on Intelligent Virtual Agents. ACM, 239–246. [find](https://scholar.google.com/scholar?q=Ran+Zhao%2C+Oscar+J+Romero%2C+and+Alex+Rudnicky%2E+2018%2E+SOGO%3A+A+Social+Intelligent+Negotiation+Dialogue+System%2E+In+Proceedings+of+the+18th+International+Conference+on+Intelligent+Virtual+Agents%2E+ACM%2C+239%E2%80%932)
77. Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2018. The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. arXiv preprint arXiv:1812.08989 (2018). [↗](https://arxiv.org/abs/1812.08989)

*Updated 24 October 2026*