Problem
Research questions and friction points this paper is trying to address.
political news engagement
social media
partisan bias
news consumption
misinformation
Forecasting Political News Engagement on Social Media
🤖 AI Summary
This study addresses the prediction of future political leaning in news interactions among social media users to uncover long-term news consumption patterns and their associations with extreme partisanship, echo chambers, and misinformation. Leveraging over 60 million tweets spanning seven years, we propose a neural architecture that jointly models users’ temporal news interaction behavior and tweet semantics to forecast the political orientation of their subsequent news engagements. Learned user representations are further employed for unsupervised clustering. Our findings reveal that highly partisan users exhibit greater engagement; right-leaning users more frequently interact with left-leaning sources; and topics such as immigration, the pandemic, Islamophobia, and gun control are significantly associated with interactions involving low-quality news.
📝 Abstract
Understanding how political news consumption changes over time can provide insights into issues such as hyperpartisanship, filter bubbles, and misinformation. To investigate long-term trends of news consumption, we curate a collection of over 60M tweets from politically engaged users over seven years, annotating ~10% with mentions of news outlets and their political leaning. We then train a neural network to forecast the political lean of news articles Twitter users will engage with, considering both past news engagements as well as tweet content. Using the learned representation of this model, we cluster users to discover salient patterns of long-term news engagement. Our findings include the following: (1) hyperpartisan users are more engaged with news; (2) right-leaning users engage with contra-partisan sources more than left-leaning users; (3) topics such as immigration, COVID-19, Islamaphobia, and gun control are salient indicators of engagement with low quality news sources.
Innovation
Methods, ideas, or system contributions that make the work stand out.
neural forecasting
political news engagement
user representation learning
longitudinal social media analysis
partisan clustering
🔎 Similar Papers
No similar papers found.
