AI for Social Science
Research Methods

Who Talks to Whom? Measuring Segregation in Informal Interactions at Academic Conferences Using Images and Vision–Language Models

When Responses Are Assisted: Identifying AI Assistance and Agents in Surveys

Mitigating Confounding Bias in Observational Visual Media Research: An LLM-Informed, Machine Learning-Based Inference Framework

Using Large Language Models as a Source of Human Behavioral Data in Social Science Experiments

Scaling Reproducibility: An AI-Assisted Workflow for Large-Scale Reanalysis

Data Annotation with Large Language Models: Lessons from a Large Empirical Evaluation

How Should Experimenters Construct Image Stimuli? A Framework for Controlled Image Construction

AI-Assisted Conversational Interviewing: Effects on Data Quality and Respondent Experience

Social Science Simulator: A Tool for Simulating Experiments with LLMs

Prompt Degrees of Freedom in LLM-Based Social Science: A Specification Curve Framework for Transparent Reporting

Same Prompt, Different Outcomes: Evaluating the Reproducibility of Data Analysis by LLMs

Reasoning Models Generate Societies of Thought

The Cross-Context Design: An AI-Enabled Method for Testing Behavioral Hypotheses across Archival Datasets

From Annotation to Measurement: Traceable Workflows for LLM Inference

Four Paradigms for AI-Enabled Social Science Research

Using Sparse Autoencoders to Measure Social Biases in Podcast Data

Improving AI for Scientific Discovery with 6749 Scientists

Survey as Life-course Annotation: Extracting Life Histories from Survey Data Using Large Language Models

The Hidden Costs of AI Diagnosis: Safety Tradeoffs and Demographic Disparities in Chatbot Performance

AI as Measurement Infrastructure: Adaptive Survey Design in Verbal Autopsy

Measuring Hidden Conceptual Change with AI: A Dual-Embedding Framework for Political Text

The Geopolitical Determinants of Economic Growth, 1960–2024

Agentic Retrieval Models for Elite Network Data Collection: Application to the Israeli Case

Can AI Predict Life Outcomes? Large Language Models and the Birth Lottery

iKON in Colombia: Hybrid Human–AI Data Collection for Historical Climate Impacts via WhatsApp Pairwise Comparisons

When the Black Box Enters Leisure: A Cognitive–Affective Dual-Path Model of AI-Generated Video and Recovery

Yolov5-based Computer Vision Model Measures Political Polarization: Visible Interactions Between Religious and Non-religious Citizens

LLM-Assisted Replication as Social Science Infrastructure

An LLM-enabled Hermeneutics of Fictional Personality: Social Difference and the Moral Structure of the American Literary Field, 1860–1900

Copyright and Competition: Estimating Supply and Demand with Unstructured Data

What is Actually Being Annotated? Inter-Prompt Reliability as a Measurement Problem in LLM-Based Social Science Labeling

Hearing Democracy: Audio-Based Classification of Speakers in City Council Meetings Using Multimodal LLMs, Temporal Context, and Multi-Agent Deliberation

Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback

Reconstructing Gridded Historical Particulate Matter Concentrations: A Deep Learning Approach

1. Limits of Literature-Conditioned Large Language Models for Predicting Behavioral Experiments

2. Simulating Institutions with Borrowed Populations: Cross-Study Behavioral Portability via LLM-Mediated Simulation

(How) Do We Teach Emotions?

Counterfactual LLM-based Framework for Measuring Rhetorical Style

The Diffusion of Large Language Models in Published Academic Articles

From Pixels to Evidence: AI and Satellite Data as Social Science Tools in the Rohingya Crisis

Gendered Signals in LLM-Masked Adolescents' Writing: An Embedding-Based Index and Later-life Outcomes for a UK Cohort

Human–AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment

Rethinking Codebook Development in Framing Analysis with LLMs

Using AI Predictions to Augment Rather Than Replace Surveys

Measuring Meaning on Video at Scale: From Classifier to Theory Interpreter in AI-Based Humor Annotation

Task Dependence, Communication Networks, and Small Group Coordination: A Multi-Agent AI Experiment of the PCANS Model

Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace Social Scientists?

Agentic Framework for Political Biography Extraction