Exploring the Role of Prior Beliefs for Argument Persuasion
22283Authors
nan
Abstract
AbstractPublic 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.
Keywords
Full Content
Proceedings of NAACL-HLT 2018, pages 1035–1045 New Orleans, Louisiana, June 1 - 6, 2018. c⃝2018 Association for Computational Linguistics Exploring the Role of Prior Beliefs for Argument Persuasion Esin Durmus Cornell University ed459@cornell.edu Claire Cardie Cornell University cardie@cs.cornell.edu Abstract Public debate forums provide a common plat- form for exchanging opinions on a topic of interest. While recent studies in natural lan- guage processing (NLP) have provided em- pirical evidence that the language of the de- baters 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 ar- gument and could therefore constitute a com- peting alternative explanation for resistance to changing one’s stance. To study the actual ef- fect of language use vs. prior beliefs on persua- sion, 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 impor- tant role than language use effects and argue that it is important to account for them in NLP studies of persuasion. 1 Introduction Public debate forums provide to participants a common platform for expressing their point of view on a topic; they also present to participants the different sides of an argument. The latter can be particularly important: awareness of divergent points of view allows one, in theory, to make a fair and informed decision about an issue; and expo- sure to new points of view can furthermore possi- bly persuade a reader to change his overall stance on a topic. Research in natural language processing (NLP) has begun to study persuasive writing and the role of language in persuasion. Tan et al. (2016) and Zhang et al. (2016), for example, have shown that the language of opinion holders or debaters and their patterns of interaction play a key role in changing the mind of a reader. At the same time, research in psychology has shown that prior be- liefs can affect our interpretation of an argument even when the argument consists of numbers and empirical studies that would seemingly belie mis- interpretation (Lord et al., 1979; Vallone et al., 1985; Chambliss and Garner, 1996). We hypothesize that studying the actual effect of language on persuasion will require a more controlled experimental setting — one that takes into account any potentially confounding user- level (i.e., reader-level) factors1 that could cause a person to change, or keep a person from chang- ing, his opinion. In this paper we study one such type of factor: the prior beliefs of the reader as impacted by their political or religious ideology. We adopt this focus since it has been shown that ideologies play an important role for an individual when they form beliefs about controversial topics, and potentially affect how open the individual is to being persuaded (Stout and Buddenbaum, 1996; Goren, 2005; Croucher and Harris, 2012). We first present a …
Content truncated to 500 words
Labeled Text
AbstractPublic 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.
Publication Details
- Paper ID:
- 22283
- Year:
- 2018
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan