Reproduce “A Unified Choice Model of News Selection: Experimental Evidence on Stance, Rank, and Engagement Cues” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jacopo D'Ignazi, Andreas Kaltenbrunner, Michele Starnini, Vicenç Gómez

The authors model news article choices by combining political stance, rank, and visible engagement counts in a conditional multinomial logit framework. In a controlled study, engagement counts improve model fit, and the model predicts held-out choices. In E2, swapping extreme counts raises predicted click probability from 3.9–8.4% to 12.5–24.4%; these are counterfactual predictions, not evidence that cue visibility causes clicks.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.