skip to main content

Title: Persuasion of the Undecided: Language vs. the Listener.
This paper examines the factors that govern persuasion for a priori UNDECIDED versus DECIDED audience members in the context of on-line debates. We separately study two types of influences: linguistic factors — features of the language of the debate itself; and audience factors — features of an audience member encoding demographic information, prior beliefs, and debate platform behavior. In a study of users of a popular debate platform, we find first that different combinations of linguistic features are critical for predicting persuasion outcomes for UNDECIDED versus DECIDED members of the audience. We additionally find that audience factors have more influence on predicting the side (PRO/CON) that persuaded UNDECIDED users than for DECIDED users that flip their stance to the opposing side. Our results emphasize the importance of considering the undecided and decided audiences separately when studying linguistic factors of persuasion.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the 6th Workshop on Argument Mining
Page Range / eLocation ID:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Debate is a process that gives individuals the opportunity to express, and to be exposed to, diverging viewpoints on controversial issues; and the existence of online debating platforms makes it easier for individuals to participate in debates and obtain feedback on their debating skills. But understanding the factors that contribute to a user’s success in debate is complicated: while success depends, in part, on the characteristics of the language they employ, it is also important to account for the degree to which their beliefs and personal traits are compatible with that of the audience. Friendships and previous interactions among users on the platform may further influence success. In this work, we aim to better understand the mechanisms behind success in online debates. In particular, we study the relative effects of debaters’ language, their prior beliefs and personal traits, and their social interactions with other users. We find, perhaps surprisingly, that characteristics of users’ social interactions play the most important role in determining their success in debates although the best predictive performance is achieved by combining social interaction features with features 
    more » « less
  2. Identifying persuasive speakers in an adversarial environment is a critical task. In a national election, politicians would like to have persuasive speakers campaign on their behalf. When a company faces adverse publicity, they would like to engage persuasive advocates for their position in the presence of adversaries who are critical of them. Debates represent a common platform for these forms of adversarial persuasion. This paper solves two problems: the Debate Outcome Prediction (DOP) problem predicts who wins a debate while the Intensity of Persuasion Prediction (IPP) problem predicts the change in the number of votes before and after a speaker speaks. Though DOP has been previously studied, we are the first to study IPP. Past studies on DOP fail to leverage two important aspects of multimodal data: 1) multiple modalities are often semantically aligned, and 2) different modalities may provide diverse information for prediction. Our M2P2 (Multimodal Persuasion Prediction) framework is the first to use multimodal (acoustic, visual, language) data to solve the IPP problem. To leverage the alignment of different modalities while maintaining the diversity of the cues they provide, M2P2 devises a novel adaptive fusion learning framework which fuses embeddings obtained from two modules -- an alignment module that extracts shared information between modalities and a heterogeneity module that learns the weights of different modalities with guidance from three separately trained unimodal reference models. We test M2P2 on the popular IQ2US dataset designed for DOP. We also introduce a new dataset called QPS (from Qipashuo, a popular Chinese debate TV show) for IPP - we plan to release this dataset when the paper is published. M2P2 significantly outperforms 3 recent baselines on both datasets. 
    more » « less
  3. Public debate forums provide a common platform for exchanging opinions on a topic of interest. While recent studies in natural language processing (NLP) have provided empirical evidence that the language of the debaters and their patterns of interaction play a key role in changing the mind of a reader, research in psychology has shown that prior beliefs can affect our interpretation of an argument and could therefore constitute a competing alternative explanation for resistance to changing one’s stance. To study the actual effect of language use vs. prior beliefs on persuasion, we provide a new dataset and propose a controlled setting that takes into consideration two reader-level factors: political and religious ideology. We find that prior beliefs affected by these reader-level factors play a more important role than language use effects and argue that it is important to account for them in NLP studies of persuasion. 
    more » « less
  4. This study aims to identify the linguistic feature characteristics of multiple writing assignments completed by engineering undergraduates, including entry-level engineering laboratory reports and writing produced in non-engineering courses. We used Biber’s multidimensional analysis (MDA) method as the analysis tool for the student writing artifacts. MDA is a corpus-analysis methodology that utilizes language processing software to analyze text by parts of speech (e.g. nouns, verbs, prepositions, etc.). MDA typically identifies six “dimensions” of linguistic features that a text may perform in, and each dimension is rated along a continuum. The dimensions used in this study include Dimension 1: Informational vs involved, Dimension 3: Context dependence, Dimension 4: Overt persuasion, and Dimension 5: Abstract vs. non-abstract information. In AY 2019-2020, total of 97 student artifacts (N = 97) were collected. For this analysis, we grouped documents into similar assignment genres: research-papers (n = 45), technical reports and analyses (n = 7) and engineering laboratory reports (n = 35), with individual engineering students represented at least once in the laboratory report and once in another category. Findings showed that engineering lab reports are highly informational, minimally-persuasive, and used deferred elaboration. Students’ research papers in academic writing courses, conversely, were highly involved, highly persuasive, and featured more immediate elaboration on claims and data. The analyses above indicate that students are generally performing as expected in lab report writing in entry-level engineering lab classes, and that this performance is markedly different from their earlier academic writing courses, such as first-year-composition (FYC) and technical communication/writing, indicating that students are not merely “writing like engineers” from their first day at college. However, similarities in context dependence suggest that engineering students must still learn to modulate their languages in writing dramatically depending on the writing assignment. While some students show little growth from one context to another, others are able to change their register or other linguistic/structural features to meet the needs of their audience. 
    more » « less
  5. Cognitive and psychological studies on morality have proposed underlying linguistic and semantic factors. However, laboratory experiments in the philosophical literature often lack the nuances and complexity of real life. This paper examines how well the findings of these cognitive studies generalize to a corpus of over 30,000 narratives of tense social situations submitted to a popular social media forum. These narratives describe interpersonal moral situations or misgivings; other users judge from the post whether the author (protagonist) or the opposing side (antagonist) is morally culpable. Whereas previous work focuses on predicting the polarity of normative behaviors, we extend and apply natural language processing (NLP) techniques to understand the effects of descriptions of the people involved in these posts. We conduct extensive experiments to investigate the effect sizes of features to understand how they affect the assignment of blame on social media. Our findings show that aggregating psychology theories enables understanding real-life moral situations. Moreover, our results suggest that there exist biases in blame assignment on social media, such as males are more likely to receive blame no matter whether they are protagonists or antagonists. 
    more » « less