Elamur Research
☰
home / papers / 2019 / Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/P19-1566.pdf

Summary

The paper addresses the lack of data and theory for building dialogue agents that persuade people toward socially beneficial actions and adapt to the individual they are talking to. The authors ran a two-person task on Amazon Mechanical Turk, built with ParlAI. One randomly assigned participant tried to convince the other to give part of their pay to Save the Children. The result is PERSUASIONFORGOOD, a corpus of 1,017 dialogues with real monetary stakes. Each participant also completed psychological and sociodemographic surveys. The authors designed a scheme of 10 persuasion strategies, hand-labelled a 300-dialogue subset, and trained a Recurrent-CNN classifier. Its inputs were sentence embeddings, dialogue context and sentence-level features, and the authors report good strategy prediction. Statistical analyses linked personal traits to donation behaviour. They also showed that a strategy's effectiveness can depend on who is being persuaded. This evidence of heterogeneity justifies tailoring strategy choice to user profiles. The work therefore provides both a resource and a starting point for personalized persuasive systems. It also sets out ethical guidelines on transparency, consent and non-discriminatory output.

Key points

  • Corpus statistics: PERSUASIONFORGOOD contains 1,017 dialogues from 1,285 participants. Dialogues average 10.43 turns and 19.36 words per utterance, with 8,141 unique tokens. The average donation was $0.35. The annotated subset (ANNSET) has 300 dialogues. Data and code are released on GitLab.
  • Pre-task survey: Participants completed the Big-Five (25 items), Moral Foundations (23), Schwartz Portrait Value (10) and Decision-Making style (4) questionnaires. These were condensed into a 23-dimension psychological vector per person.
  • Donation rates and utterance length: 54% of persuadees and 42% of persuaders donated. Persuaders wrote longer turns than persuadees, at 22.96 versus 15.65 words.
  • Strategy-by-trait interactions:
    • Source-related inquiry significantly raised donation likelihood among more open persuadees (p < 0.05).
    • Personal-related inquiry helped with people who value freedom and care, but showed a negative association for those endorsing fairness and authority.
  • Gap between promises and actual donations: Among ANNSET persuadees who agreed to donate, 43% (88) gave nothing and 11% (22) gave less than promised. Higher agreeableness tended to mean greater consistency, though this result was not statistically significant.

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

Fields: Natural language processing

Cited by

148 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 144 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1566

@inproceedings{wang2019persuasion,
  title = {{Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good}},
  author = {Wang, Xuewei and Shi, Weiyan and Kim, Richard and Oh, Yoojung and Yang, Sijia and Zhang, Jingwen and Yu, Zhou},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1566},
  url = {https://doi.org/10.18653/v1/p19-1566}
}

References

41 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Elisabeth André, Thomas Rist, Susanne Van Mulken, Martin Klesen, and Stefan Baldes. 2000. The automated design of believable dialogues for animated presentation teams. Embodied conversational agents, pages 220–255. find
  2. Timothy W Bickmore, Dina Utami, Robin Matsuyama, and Michael K Paasche-Orlow. 2016. Improving access to online health information with conversational agents: a randomized controlled experiment. Journal of medical Internet research, 18(1). find
  3. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146. find
  4. Chandrakant Bothe, Sven Magg, Cornelius Weber, and Stefan Wermter. 2018. Conversational analysis using utterance-level attention-based bidirectional recurrent neural networks. find
  5. Proc. Interspeech 2018, pages 996–1000. find
  6. J. Cieciuch and E. Davidov. 2012. A comparison of the invariance properties of the pvq-40 and the pvq-21 to measure human values across german and polish samples. Survey Research Methods, 6(1):37–48. find
  7. Arie Dijkstra. 2008. The psychology of tailoring-ingredients in computer-tailored persuasion. Social and personality psychology compass, 2(2):765–784. find
  8. Brian J Fogg. 2002. Persuasive technology: using computers to change what we think and do. Ubiquity, 2002(December):5. find
  9. CJ Hutto Eric Gilbert. 2014. Vader: A parsimonious rule-based model for sentiment analysis of social media text. In Eighth International Conference on Weblogs and Social Media (ICWSM-14). Available at (20/04/16) http://comp. social. gatech. edu/papers/icwsm14. vader. hutto. pdf. find
  10. Lewis R. Goldberg. 1992. The development of markers for the big-five factor structure. Psychological Assessment, 4(1):26–42. find
  11. Thomas F Gordon. 1993. The pleadings game. Artificial Intelligence and Law, 2(4):239–292. find
  12. Arthur C Graesser, Haiying Li, and Carol Forsyth. 2014. Learning by communicating in natural language with conversational agents. Current Directions in Psychological Science, 23(5):374–380. find
  13. J. Graham, B. A. Nosek, J. Haidt, R. Iyer, S. Koleva, and P. H. Ditto. 2011. Mapping the moral domain. Journal of Personality and Social Psychology, 101(2):366–385. find
  14. Jesse Graham, Jonathan Haidt, Sena Koleva, Matt Motyl, Ravi Iyer, Sean P Wojcik, and Peter H Ditto. 2013. Moral foundations theory: The pragmatic validity of moral pluralism. In Advances in experimental social psychology, volume 47, pages 55–130. Elsevier. find
  15. Shih S. I. Hamilton, K. and S. Mohammed. 2016. The development and validation of the rational and intuitive decision styles scale. Journal of personality assessment, 98(5):523–535. find
  16. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. Decoupling strategy and generation in negotiation dialogues. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2333–2343. find
  17. Sally Hibbert, Andrew Smith, Andrea Davies, and Fiona Ireland. 2007. Guilt appeals: Persuasion knowledge and charitable giving. Psychology & Marketing, 24(8):723–742. find
  18. Christopher Hidey, Elena Musi, Alyssa Hwang, Smaranda Muresan, and Kathy McKeown. 2017. Analyzing the semantic types of claims and premises in an online persuasive forum. In Proceedings of the 4th Workshop on Argument Mining, pages 11–21. find
  19. Christopher Thomas Hidey and Kathleen McKeown. 2018. Persuasive influence detection: The role of argument sequencing. In Thirty-Second AAAI Conference on Artificial Intelligence. find
  20. Joe Hoover, Kate Johnson, Reihane Boghrati, Jesse Graham, and Morteza Dehghani. 2018. Moral framing and charitable donation: Integrating exploratory social media analyses and confirmatory experimentation. Collabra: Psychology, 4(1). find
  21. Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882. find our card
  22. Matthew W Kreuter, Victor J Strecher, and Bernard Glassman. 1999. One size does not fit all: the case for tailoring print materials. Annals of behavioral medicine, 21(4):276. find
  23. Klaus Krippendorff. 2004. Reliability in content analysis: Some common misconceptions and recommendations. Human communication research, 30(3):411–433. find
  24. Siwei Lai, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Recurrent convolutional neural networks for text classification. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, pages 2267–2273. AAAI Press. find
  25. Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or no deal? end-to-end learning of negotiation dialogues. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2443–2453. find
  26. Ewa Luger and Abigail Sellen. 2016. Like having a really bad pa: the gulf between user expectation and experience of conversational agents. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pages 5286–5297. ACM. find
  27. Stephanie Lukin, Pranav Anand, Marilyn Walker, and Steve Whittaker. 2017. Argument strength is in the eye of the beholder: Audience effects in persuasion. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, volume 1,… find
  28. Alexander Miller, Will Feng, Dhruv Batra, Antoine Bordes, Adam Fisch, Jiasen Lu, Devi Parikh, and Jason Weston. 2017. Parlai: A dialog research software platform. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 79–84. find our card
  29. Rita Orji and Karyn Moffatt. 2018. Persuasive technology for health and wellness: State-of-the-art and emerging trends. Health informatics journal, 24(1):66–91. find
  30. Richard E Petty and John T Cacioppo. 1986. The elaboration likelihood model of persuasion. In Communication and persuasion, pages 1–24. Springer. find
  31. Alec Radford, Rafal Jozefowicz, and Ilya Sutskever. 2017. Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444. find our card
  32. Zhou Yu, Xinrui He, Alan W Black, and Alexander I Rudnicky. 2016a. User engagement study with virtual agents under different cultural contexts. In International Conference on Intelligent Virtual Agents, pages 364–368. Springer. find
  33. Zhou Yu, Ziyu Xu, Alan W Black, and Alexander Rudnicky. 2016b. Strategy and policy learning for non-task-oriented conversational systems. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 404– 412. find
  34. Tangming Yuan, David Moore, and Alec Grierson. 2008. A human-computer dialogue system for educational debate: A computational dialectics approach. International Journal of Artificial Intelligence in Education, 18(1):3–26. find
  35. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, 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 Computational Linguistics (Volume 1: Long Papers), volume 1, pages 2204–22… find our card
  36. Barbara K Rimer and Matthew W Kreuter. 2006. Advancing tailored health communication: A persuasion and message effects perspective. Journal of communication, 56:S184–S201. find
  37. Carol A Scott. 1977. Modifying socially-conscious behavior: The foot-in-the-door technique. Journal of Consumer Research, 4(3):156–164. find
  38. Weiyan Shi and Zhou Yu. 2018. Sentiment adaptive end-to-end dialog systems. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1509–1519. find
  39. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15:1929–1958. find
  40. Chenhao Tan, Vlad Niculae, Cristian Danescu-Niculescu-Mizil, and Lillian Lee. 2016. Winning arguments: Interaction dynamics and persuasion strategies in good-faith online discussions. In Proceedings of the 25th international conference on world wide web, pages 613–624. International World Wide Web C… find
  41. Diyi Yang, Jiaao Chen, Zichao Yang, Dan Jurafsky, and Eduard Hovy. 2019. Lets make your request more persuasive: Modeling persuasive strategies via semi-supervised neural nets on crowdfunding platforms. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Comput… find