Research Insight | Who Shares Fake News? Insights from Social Media Users' Post Histories
This study addresses the challenge of identifying and understanding the characteristics of social media users who share fake news. Researchers utilize the text in users’ past social media posts to extract insights into their traits that can help predict fake news sharing and mitigate the spread of misinformation. The authors examine the language patterns of fake news sharers by analyzing their Twitter post histories, categorizing these individuals on the basis of the type of fake news shared—political or nonpolitical—using sources like Snopes and Hoaxy. By comparing these sharers to various other groups, including random Twitter users and users with similar demographics or political leanings, they identify unique textual cues, such as the frequent use of words related to anger and power, which significantly enhance the predictive models’ accuracy in identifying who shares fake news. Marketers and managers can leverage the findings to develop targeted interventions that reduce the sharing of fake news by identifying key linguistic and psychological traits of fake news sharers and crafting messages that resonate with these users.
For more Research Insights, click here.
What You Need to Know
- Social media users who share fake news exhibit distinctive linguistic patterns, such as higher usage of anger and power-related words, which may reflect their psychological traits.
- The linguistic patterns uncovered from past social media posts can also be incorporated into predictive models to better predict potential fake news sharers.
- Building profiles of fake news sharers using post history data can be useful in identifying promising interventions. For example, using empowering language in advertisements for fact-checking tools can encourage their adoption.
Abstract
We propose that social-media users’ own post histories are an underused yet valuable resource for studying fake-news sharing. By extracting textual cues from their prior posts, and contrasting their prevalence against random social-media users and others (e.g., those with similar socio-demographics, political news-sharers, and fact-check sharers), researchers can identify cues that distinguish fake-news sharers, predict those most likely to share fake news, and identify promising constructs to build interventions. Our research includes studies along these lines. In Study 1, we explore the distinctive language patterns of fake-news sharers, highlighting elements such as their higher use of anger and power-related words. In Study 2, we show that adding textual cues into predictive models enhances their accuracy in predicting fake-news sharers. In Study 3, we explore the contrasting role of trait and situational anger, and show trait anger is associated with a greater propensity to share both true and fake news. In Study 4, we introduce a way to authenticate Twitter accounts in surveys, before using it to explore how crafting an ad copy that resonates with users’ sense of power encourages the adoption of fact-checking tools. We hope to encourage the use of novel research methods for marketers and misinformation researchers.
Verena Schoenmueller, Simon J. Blanchard, and Gita Venkataramani Johar, “Who Shares Fake News? Uncovering Insights from Social Media Users’ Post Histories,” Journal of Marketing Research. doi:10.1177/00222437241281873.