arXiv subjects

Sunshine Hillygus

Publications and source records attributed to Sunshine Hillygus.

2 recordsLinked to original sources

arXiv2026

Can Platform Design Encourage Curiosity? Evidence from an Independent Social Media Experiment

Social media platforms are often criticized for fostering antisocial behavior rather than prosocial behavior. Yet, testing interventions to encourage prosocial dispositions, such as open-mindedness, has been hindered by researchers' limited ability to manipulate platform features and isolate causal effects in commercial environments. We address this challenge through a randomized controlled trial with 2,282 U.S. adults conducted on a new research platform we developed that uses AI bots to replicate live social media dynamics while enabling controlled experimentation. Participants engaged in 15-minute discussions about energy and climate topics, with treatment groups exposed to curiosity priming either through modified on-platform social norms, interface affordances, or both. Results demonstrate that curiosity priming significantly increased question-asking behavior and textual measures of curiosity in user posts, while also reducing toxicity. Although interventions decreased generic engagement behaviors like liking and commenting, they had no significant negative impact on reported app enjoyment or time spent writing posts and replies. Leveraging experimental control over platform features, our findings suggest that platform designs prioritizing curiosity can promote prosocial behaviors among users without compromising user experience.

cs.SI↗

arXiv2025

A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?

Many social science questions ask how linguistic properties causally affect an audience's attitudes and behaviors. Because text properties are often interlinked (e.g., angry reviews use profane language), we must control for possible latent confounding to isolate causal effects. Recent literature proposes adapting large language models (LLMs) to learn latent representations of text that successfully predict both treatment and the outcome. However, because the treatment is a component of the text, these deep learning methods risk learning representations that actually encode the treatment itself, inducing overlap bias. Rather than depending on post-hoc adjustments, we introduce a new experimental design that handles latent confounding, avoids the overlap issue, and unbiasedly estimates treatment effects. We apply this design in an experiment evaluating the persuasiveness of expressing humility in political communication. Methodologically, we demonstrate that LLM-based methods perform worse than even simple bag-of-words models using our real text and outcomes from our experiment. Substantively, we isolate the causal effect of expressing humility on the perceived persuasiveness of political statements, offering new insights on communication effects for social media platforms, policy makers, and social scientists.

stat.ME↗