Reproduce “Characterizing User Susceptibility to COVID-19 Misinformation on Twitter” 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
Xian Teng, Yu-Ru Lin, Wen-Ting Chung, Ang Li, Adriana Kovashka
The authors examine COVID-era Twitter sharing of links from sources flagged by journalists or fact-checkers, and predict next-week sharing from users’ recent links and friends’ exposure. At Botometer threshold 0.5, bots accounted for 10.3% of sharers and 13.1% of problematic shares. The model modestly outperformed logistic regression on F1 and recall; flagged-source status does not verify article claims.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.