More Like this

1. Cross-Partisan Discussions on YouTube: Conservatives Talk to Liberals but Liberals Don't Talk to Conservatives

   Wu, Siqi; Resnick, Paul (May 2021, Proceedings of the Fifteenth International AAAI Conference on Web and Social Media)

   Budak, Ceren; Cha, Meeyoung; Quercia, Daniele; Xie, Lexing (Ed.)

   We present the first large-scale measurement study of cross-partisan discussions between liberals and conservatives on YouTube, based on a dataset of 274,241 political videos from 973 channels of US partisan media and 134M comments from 9.3M users over eight months in 2020. Contrary to a simple narrative of echo chambers, we find a surprising amount of cross-talk: most users with at least 10 comments posted at least once on both left-leaning and right-leaning YouTube channels. Cross-talk, however, was not symmetric. Based on the user leaning predicted by a hierarchical attention model, we find that conservatives were much more likely to comment on left-leaning videos than liberals on right-leaning videos. Secondly, YouTube's comment sorting algorithm made cross-partisan comments modestly less visible; for example, comments from conservatives made up 26.3% of all comments on left-leaning videos but just over 20% of the comments were in the top 20 positions. Lastly, using Perspective API's toxicity score as a measure of quality, we find that conservatives were not significantly more toxic than liberals when users directly commented on the content of videos. However, when users replied to comments from other users, we find that cross-partisan replies were more toxic than co-partisan replies on both left-leaning and right-leaning videos, with cross-partisan replies being especially toxic on the replier's home turf. 

   more » « less
2. Polarization and tipping points

   https://doi.org/10.1073/pnas.2102144118  

   Macy, Michael W.; Ma, Manqing; Tabin, Daniel R.; Gao, Jianxi; Szymanski, Boleslaw K. (December 2021, Proceedings of the National Academy of Sciences)

   Research has documented increasing partisan division and extremist positions that are more pronounced among political elites than among voters. Attention has now begun to focus on how polarization might be attenuated. We use a general model of opinion change to see if the self-reinforcing dynamics of influence and homophily may be characterized by tipping points that make reversibility problematic. The model applies to a legislative body or other small, densely connected organization, but does not assume country-specific institutional arrangements that would obscure the identification of fundamental regularities in the phase transitions. Agents in the model have initially random locations in a multidimensional issue space consisting of membership in one of two equal-sized parties and positions on 10 issues. Agents then update their issue positions by moving closer to nearby neighbors and farther from those with whom they disagree, depending on the agents’ tolerance of disagreement and strength of party identification compared to their ideological commitment to the issues. We conducted computational experiments in which we manipulated agents’ tolerance for disagreement and strength of party identification. Importantly, we also introduced exogenous shocks corresponding to events that create a shared interest against a common threat (e.g., a global pandemic). Phase diagrams of political polarization reveal difficult-to-predict transitions that can be irreversible due to asymmetric hysteresis trajectories. We conclude that future empirical research needs to pay much closer attention to the identification of tipping points and the effectiveness of possible countermeasures. 

   more » « less
3. Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reporting

   https://doi.org/10.18653/v1/2023.findings-emnlp.45  

   Zou, Kaijian; Zhang, Xinliang; Wu, Winston; Beauchamp, Nicholas; Wang, Lu (November 2023, Findings of the Association for Computational Linguistics: EMNLP 2023)

   News media is expected to uphold unbiased reporting. Yet they may still affect public opinion by selectively including or omitting events that support or contradict their ideological positions. Prior work in NLP has only studied media bias via linguistic style and word usage. In this paper, we study to which degree media balances news reporting and affects consumers through event inclusion or omission. We first introduce the task of detecting both partisan and counter- partisan events: events that support or oppose the author’s political ideology. To conduct our study, we annotate a high-quality dataset, PAC, containing 8 , 511 (counter-)partisan event annotations in 304 news articles from ideologically diverse media outlets. We benchmark PAC to highlight the challenges of this task. Our findings highlight both the ways in which the news subtly shapes opinion and the need for large language models that better understand events within a broader context. Our dataset can be found at https://github.com/ launchnlp/Partisan-Event-Dataset. 

   more » « less
4. Polarizing Political Polls: How Visualization Design Choices Can Shape Public Opinion and Increase Political Polarization

   https://doi.org/10.1109/TVCG.2023.3326512  

   Holder, Eli; Bearfield, Cindy Xiong (January 2023, IEEE Transactions on Visualization and Computer Graphics)

   While we typically focus on data visualization as a tool for facilitating cognitive tasks (e.g. learning facts, making decisions), we know relatively little about their second-order impacts on our opinions, attitudes, and values. For example, could design or framing choices interact with viewers' social cognitive biases in ways that promote political polarization? When reporting on U.S. attitudes toward public policies, it is popular to highlight the gap between Democrats and Republicans (e.g. with blue vs red connected dot plots). But these charts may encourage social-normative conformity, influencing viewers' attitudes to match the divided opinions shown in the visualization. We conducted three experiments examining visualization framing in the context of social conformity and polarization. Crowdworkers viewed charts showing simulated polling results for public policy proposals. We varied framing (aggregating data as non-partisan “All US Adults,” or partisan “Democrat” / “Republican”) and the visualized groups' support levels. Participants then reported their own support for each policy. We found that participants' attitudes biased significantly toward the group attitudes shown in the stimuli and this can increase inter-party attitude divergence. These results demonstrate that data visualizations can induce social conformity and accelerate political polarization. Choosing to visualize partisan divisions can divide us further. 

   more » « less
5. Confidence in elections among U.S. local officials: Effects of social trust, partisanship and political ambition

   https://doi.org/10.1371/journal.pone.0324794  

   Plutzer, Eric; Adler, Gary; Sager, Rebecca; Coley, Jonathan S; Mayrl, Damon (June 2025, PLOS One)

   Han, Sung Min (Ed.)

   The U.S. public’s confidence in elections is intensively studied in the last decade but little is known about election confidence among locally elected officials, whose roles and community status may influence public opinion. Using a nationally representative survey of local election officials, we compare election confidence among local elected officials with that of the general public. Local elected officials are more likely to trust both local and national elections. We theorize factors that affect local officials’ trust in elections, including partisan context, state leadership election denial levels, and political ambition. We show how social trust, partisan identity, and ambition significantly influence local officials’ confidence that local and national results reflect the intention of voters. We conclude by showing how the relative lack of intensive partisan polarization among local elected officials is especially important at keeping election distrust low among local officials. 

   more » « less