Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategies

Intelligent conversational agents, or chatbots, can take on various identities and are increasingly engaging in more human-centered conversations with persuasive goals. However, little is known about how identities and inquiry strategies influence the conversation's effectiveness. We conducted an online study involving 790 participants to be persuaded by a chatbot for charity donation. We designed a two by four factorial experiment (two chatbot identities and four inquiry strategies) where participants were randomly assigned to different conditions. Findings showed that the perceived identity of the chatbot had significant effects on the persuasion outcome (i.e., donation) and interpersonal perceptions (i.e., competence, confidence, warmth, and sincerity). Further, we identified interaction effects among perceived identities and inquiry strategies. We discuss the findings for theoretical and practical implications for developing ethical and effective persuasive chatbots. Our published data, codes, and analyses serve as the first step towards building competent ethical persuasive chatbots.

[1]  Ilya Sutskever,et al.  Learning to Generate Reviews and Discovering Sentiment , 2017, ArXiv.

[2]  Harri Oinas-Kukkonen,et al.  Persuasive Systems Design: Key Issues, Process Model, and System Features , 2009, Commun. Assoc. Inf. Syst..

[3]  L. R. Goldberg.  THE DEVELOPMENT OF MARKERS FOR THE BIG-FIVE FACTOR STRUCTURE , 1992 .

[4]  Siddharth Suri,et al.  Conducting behavioral research on Amazon’s Mechanical Turk , 2010, Behavior research methods.

[5]  G. Bodenhausen,et al.  Personalized Persuasion , 2012, Psychological science.

[6]  P. Sherman,et al.  The Meaning of Nepotism , 1980, The American Naturalist.

[7]  Elena Musi,et al.  Analyzing the Semantic Types of Claims and Premises in an Online Persuasive Forum , 2017, ArgMining@EMNLP.

[8]  Peter A. Gloor,et al.  Muse Headband: Measuring Tool or a Collaborative Gadget? , 2018 .

[9]  Tangming Yuan,et al.  A Human-Computer Dialogue System for Educational Debate: A Computational Dialectics Approach , 2008, Int. J. Artif. Intell. Educ..

[10]  Eun Go,et al.  Humanizing chatbots: The effects of visual, identity and conversational cues on humanness perceptions , 2019, Comput. Hum. Behav..

[11]  J. Cacioppo,et al.  Who Sees Human? , 2010, Perspectives on psychological science : a journal of the Association for Psychological Science.

[12]  C. Nass,et al.  Trust in Computers: The Computers-Are-Social-Actors (CASA) Paradigm and Trustworthiness Perception in Human-Computer Communication , 2010 .

[13]  Patric R. Spence,et al.  Is that a bot running the social media feed? Testing the differences in perceptions of communication quality for a human agent and a bot agent on Twitter , 2014, Comput. Hum. Behav..

[14]  Rita Orji,et al.  Personalizing Persuasive Strategies in Gameful Systems to Gamification User Types , 2018, CHI.

[15]  Chrysanne Di Marco,et al.  Towards Personality-driven Persuasive Health Games and Gamified Systems , 2017, CHI.

[16]  Zhou Yu,et al.  How to Build User Simulators to Train RL-based Dialog Systems , 2019, EMNLP.

[17]  C. P. Leblond,et al.  Electron microscopic identification of three classes of oligodendrocytes and a preliminary study of their proliferative activity in the corpus callosum of young rats , 1970, The Journal of comparative neurology.

[18]  J. Pennebaker,et al.  The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods , 2010 .

[19]  A. Gillespie,et al.  Revisiting Milgram’s Cyranoid Method: Experimenting With Hybrid Human Agents , 2015, The Journal of social psychology.

[20]  Jason Weston,et al.  ParlAI: A Dialog Research Software Platform , 2017, EMNLP.

[21]  Vicki G. Morwitz,et al.  The question–behavior effect: What we know and where we go from here , 2006 .

[22]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[23]  Carol A. Scott.  Modifying Socially-Conscious Behavior: The Foot-in-the-Door Technique , 1977 .

[24]  Min Kyung Lee,et al.  A Human-Centered Approach to Algorithmic Services: Considerations for Fair and Motivating Smart Community Service Management that Allocates Donations to Non-Profit Organizations , 2017, CHI.

[25]  Zhou Yu,et al.  Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good , 2019, ACL.

[26]  Zhou Yu,et al.  Sentiment Adaptive End-to-End Dialog Systems , 2018, ACL.

[27]  Sally Hibbert,et al.  Guilt appeals: persuasion knowledge and charitable giving , 2007 .

[28]  Kathleen McKeown,et al.  Persuasive Influence Detection: The Role of Argument Sequencing , 2018, AAAI.

[29]  Brian A. Nosek,et al.  Mapping the moral domain. , 2011, Journal of personality and social psychology.

[30]  Jun Zhao,et al.  Recurrent Convolutional Neural Networks for Text Classification , 2015, AAAI.

[31]  Adam S. Miner,et al.  Psychological, Relational, and Emotional Effects of Self-Disclosure After Conversations With a Chatbot , 2018, The Journal of communication.

[32]  Eldad Davidov,et al.  A comparison of the invariance properties of the PVQ-40 and the PVQ-21 to measure human values across German and Polish Samples , 2012 .

[33]  Thomas Rist,et al.  The automated design of believable dialogues for animated presentation teams , 2001 .

[34]  Shin-I Shih,et al.  The Development and Validation of the Rational and Intuitive Decision Styles Scale , 2016, Journal of personality assessment.

[35]  Julita Vassileva,et al.  Modeling the efficacy of persuasive strategies for different gamer types in serious games for health , 2014, User Modeling and User-Adapted Interaction.

[36]  Cristian Danescu-Niculescu-Mizil,et al.  Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions , 2016, WWW.

[37]  Mark Conner,et al.  Asking questions changes behavior: mere measurement effects on frequency of blood donation. , 2008, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[38]  Derek Chen,et al.  Decoupling Strategy and Generation in Negotiation Dialogues , 2018, EMNLP.

[39]  Diyi Yang,et al.  Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms , 2019, NAACL.

[40]  D. Wegner,et al.  Feeling robots and human zombies: Mind perception and the uncanny valley , 2012, Cognition.

[41]  Antonella De Angeli,et al.  The unfriendly user: exploring social reactions to chatterbots , 2001 .

[42]  Gavan J. Fitzsimons,et al.  Simply asking questions about health behaviors increases both healthy and unhealthy behaviors , 2006 .

[43]  Harri Oinas-Kukkonen,et al.  Towards Deeper Understanding of Persuasion in Software and Information Systems , 2008, First International Conference on Advances in Computer-Human Interaction.

[44]  James W. Pennebaker,et al.  Linguistic Inquiry and Word Count (LIWC2007) , 2007 .

[45]  Zhou Yu,et al.  User Engagement Study with Virtual Agents Under Different Cultural Contexts , 2016, IVA.

[46]  Frank Bentley,et al.  Comparing the Reliability of Amazon Mechanical Turk and Survey Monkey to Traditional Market Research Surveys , 2017, CHI Extended Abstracts.

[47]  C. Nass,et al.  Machines and Mindlessness , 2000 .

[48]  Michael D. Buhrmester,et al.  Amazon's Mechanical Turk , 2011, Perspectives on psychological science : a journal of the Association for Psychological Science.

[49]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[50]  B. J. Fogg,et al.  Persuasive technology: using computers to change what we think and do , 2002, UBIQ.