arXiv subjects

Christopher Bail

Publications and source records attributed to Christopher Bail.

5 recordsLinked to original sources

arXiv2026

A\"ira: Rethinking AI Research Assistants for Interdisciplinary Science

Scientific discovery increasingly depends on interdisciplinary teams whose members contribute distinct expertise, conceptual frameworks, vocabularies, assumptions, and standards of evidence. Today's AI research assistants are largely designed to support individual researchers through literature review, writing assistance, coding, and data analysis. While these capabilities improve personal productivity, they provide little support for the collaborative reasoning required to integrate knowledge across disciplines. We argue that AI research assistants should evolve from tools that optimize individual workflows to systems designed for interdisciplinary teams. We introduce a\"ira, an AI research assistant built around this idea. Rather than focusing solely on summarization or question answering, a\"ira identifies disciplinary perspectives, translates terminology, highlights assumptions, and synthesizes collaborative research opportunities. We describe the design principles underlying a\"ira, present its system architecture, illustrate its outputs through interdisciplinary research meetings, and outline future research directions for AI systems that support collaborative scholarship.

cs.HC↗

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↗

arXiv2023

Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms

Social media is often criticized for amplifying toxic discourse and discouraging constructive conversations. But designing social media platforms to promote better conversations is inherently challenging. This paper asks whether simulating social media through a combination of Large Language Models (LLM) and Agent-Based Modeling can help researchers study how different news feed algorithms shape the quality of online conversations. We create realistic personas using data from the American National Election Study to populate simulated social media platforms. Next, we prompt the agents to read and share news articles - and like or comment upon each other's messages - within three platforms that use different news feed algorithms. In the first platform, users see the most liked and commented posts from users whom they follow. In the second, they see posts from all users - even those outside their own network. The third platform employs a novel "bridging" algorithm that highlights posts that are liked by people with opposing political views. We find this bridging algorithm promotes more constructive, non-toxic, conversation across political divides than the other two models. Though further research is needed to evaluate these findings, we argue that LLMs hold considerable potential to improve simulation research on social media and many other complex social settings.

cs.SI↗

arXiv2021

Author Clustering and Topic Estimation for Short Texts

Analysis of short text, such as social media posts, is extremely difficult because of their inherent brevity. In addition to classifying topics of such posts, a common downstream task is grouping the authors of these documents for subsequent analyses. We propose a novel model that expands on the Latent Dirichlet Allocation by modeling strong dependence among the words in the same document, with user-level topic distributions. We also simultaneously cluster users, removing the need for post-hoc cluster estimation and improving topic estimation by shrinking noisy user-level topic distributions towards typical values. Our method performs as well as -- or better -- than traditional approaches, and we demonstrate its usefulness on a dataset of tweets from United States Senators, recovering both meaningful topics and clusters that reflect partisan ideology. We also develop a novel measure of echo chambers among these politicians by characterizing insularity of topics discussed by groups of Senators and provide uncertainty quantification.

cs.IR↗