Understanding User Resistance Strategies in Persuasive Conversations

29624

Authors

nan

Abstract

AbstractPersuasive dialog systems have various usages, such as donation persuasion and physical exercise persuasion. Previous persuasive dialog systems research mostly focused on analyzing the persuader’s strategies and paid little attention to the persuadee (user). However, understanding and addressing users’ resistance strategies is an essential job of a persuasive dialog system. So, we adopt a preliminary framework on persuasion resistance in psychology and design a fine-grained resistance strategy annotation scheme. We annotate the PersuasionForGood dataset with the scheme. With the enriched annotations, we build a classifier to predict the resistance strategies. Furthermore, we analyze the relationships between persuasion strategies and persuasion resistance strategies. Our work lays the ground for developing a persuasive dialogue system that can understand and address user resistance strategy appropriately. The code and data will be released.

Keywords

nan

Full Content

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4794–4798 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4794 Understanding User Resistance Strategies in Persuasive Conversations Youzhi Tian1, Weiyan Shi1, Chen Li2, Zhou Yu1 1University of California, Davis, 2Tencent {yotian, wyshi, joyu}@ucdavis.edu ailabchenli@tencent.com Abstract Persuasive dialog systems have various usages, such as donation persuasion and physical ex- ercise persuasion. Previous persuasive dia- log systems research mostly focused on ana- lyzing the persuader’s strategies, and paid lit- tle attention to the persuadee (user). How- ever, understanding and addressing users’ re- sistance strategies is an essential job of a per- suasive dialog system. So, we adopt a pre- liminary framework on persuasion resistance in psychology, and design a fine-grained resis- tance strategy annotation scheme. We anno- tate the PERSUASIONFORGOOD dataset with the scheme (Wang et al., 2019). With the en- riched annotations, we build a classifier to pre- dict the resistance strategies. Furthermore, we analyze the relationships between persuasion strategies and persuasion resistance strategies. Our work lays the ground for developing a per- suasive dialogue system that can understand and address user resistance strategy appropri- ately. The code and data will be released. 1 Introduction and Related Work Persuasion plays a prominent role in human com- munication and has attracted more and more at- tentions in the NLP community (Tan et al., 2016; Hidey et al., 2017; Hidey and McKeown, 2018; Wang et al., 2019; Yang et al., 2019). During per- suasion, the persuader attempts to convince the per- suadee to change his/her attitude, opinion or behav- ior. Previous research on persuasive dialogs mainly study the persuader’s strategies (Wang et al., 2019; Shi et al., 2020; Li et al., 2019), which is helpful when the persuadee shows positive altitude towards the persuasion; but in other situations, the per- suadees resists rather than embrace the persuasive attempt. For instance, in PERSUASIONFORGOOD (Wang et al., 2019), 166 out of 1,017 persuasive dialogs contains resistance strategy; although indi- viduals resist persuasive attempts with different tac- Resistance Strategy Avoidance Contesting Biased Processing Empowerment Contesting the content Contesting the source Contesting the strategies used Weighting attributes Reducing impact Optimism Bias Attitude Bolstering Social Validation Self Assertions Figure 1: The preliminary resistance strategy frame- work Fransen et al. (2015) tics, these resistant utterances all collapse into one dialog-act “negative-reactions-towards-persuasion” in the provided annotation scheme, which makes it harder for the persuasive system to respond ac- cordingly. Therefore, to achieve more efficient persuasion, we propose to study the resistance to persuasion in more details. Persuasion resistance has been studied in so- cial psychology, marketing and so on (Knowles and Linn, 2004; Dal Cin et al., 2004; Petty and Cacioppo, 1977; Ahluwalia, 2000; Haugtvedt and Petty, 1992). Rucker et al. (2004) showed that there exist individual differences in persuasion resistance dependent on their beliefs. Further, one preliminary framework in psychology (Fransen et al., 2015) cat- egorized the resistance behaviors into four main cat- egories: Avoidance, Contesting, Biased processing, and Empowerment, as shown in Figure 1. In our …

Content truncated to 500 words

Labeled Text

AbstractPersuasive dialog systems have various usages, such as donation persuasion and physical exercise persuasion. Previous persuasive dialog systems research mostly focused on analyzing the persuader’s strategies and paid little attention to the persuadee (user). However, understanding and addressing users’ resistance strategies is an essential job of a persuasive dialog system. So, we adopt a preliminary framework on persuasion resistance in psychology and design a fine-grained resistance strategy annotation scheme. We annotate the PersuasionForGood dataset with the scheme. With the enriched annotations, we build a classifier to predict the resistance strategies. Furthermore, we analyze the relationships between persuasion strategies and persuasion resistance strategies. Our work lays the ground for developing a persuasive dialogue system that can understand and address user resistance strategy appropriately. The code and data will be released.

Publication Details

Paper ID:
29624
Year:
2020
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan