Incentivizing news consumption on social media platforms using large language models and realistic bot accounts

Abstract

Polarization, misinformation, declining trust, and wavering support for democratic norms are pressing threats to the US Exposure to verified and balanced news may make citizens more resilient to these threats. This project examines how to enhance users’ exposure to and engagement with verified and ideologically balanced news in an ecologically valid setting. We rely on a 2-week long field experiment on 28,457 Twitter users. We created 28 bots utilizing GPT-2 that replied to users tweeting about sports, entertainment, or lifestyle with a contextual reply containing a URL to the topic-relevant section of a verified and ideologically balanced news organization and an encouragement to follow its Twitter account. To test differential effects by gender of the bots, the treated users were randomly assigned to receive responses by bots presented as female or male. We examine whether our intervention enhances the following of news media organizations, sharing and liking of news content (determined by our extensive list of news media outlets), tweeting about politics, and liking of political content (determined using our fine-tuned RoBERTa NLP transformer-based model). Although the treated users followed more news accounts and the users in the female bot treatment liked more news content than the control, these results were small in magnitude and confined to the already politically interested users, as indicated by their pretreatment tweeting about politics. In addition, the effects on liking and posting political content were uniformly null. These findings have implications for social media and news organizations and offer directions for pro-social computational interventions on platforms.