(Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys

Kenneth Joseph, Sarah Shugars, Ryan Gallagher, Jon Green, Alexi Quintana Mathé, Zijian An, David Lazer


Abstract
Stance detection, which aims to determine whether an individual is for or against a target concept, promises to uncover public opinion from large streams of social media data. Yet even human annotation of social media content does not always capture “stance” as measured by public opinion polls. We demonstrate this by directly comparing an individual’s self-reported stance to the stance inferred from their social media data. Leveraging a longitudinal public opinion survey with respondent Twitter handles, we conducted this comparison for 1,129 individuals across four salient targets. We find that recall is high for both “Pro’’ and “Anti’’ stance classifications but precision is variable in a number of cases. We identify three factors leading to the disconnect between text and author stance: temporal inconsistencies, differences in constructs, and measurement errors from both survey respondents and annotators. By presenting a framework for assessing the limitations of stance detection models, this work provides important insight into what stance detection truly measures.
Anthology ID:
2021.emnlp-main.27
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
312–324
Language:
URL:
https://aclanthology.org/2021.emnlp-main.27
DOI:
10.18653/v1/2021.emnlp-main.27
Bibkey:
Cite (ACL):
Kenneth Joseph, Sarah Shugars, Ryan Gallagher, Jon Green, Alexi Quintana Mathé, Zijian An, and David Lazer. 2021. (Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 312–324, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
(Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys (Joseph et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.27.pdf
Software:
 2021.emnlp-main.27.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.27.mp4