Reproduce “GET-Tok: A GenAI-Enriched Multimodal TikTok Dataset Documenting the 2022 Attempted Coup in Peru” 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

Gabriela Pinto, Keith Burghardt, Kristina Lerman, Emilio Ferrara

GET-Tok turns sampled TikTok posts from Peru’s political crisis into records combining speech transcripts with descriptions of video scenes and visible text. It uses these inputs to generate stance labels toward Pedro Castillo. The collection contains 43,697 videos across 102 days, with annotations for 2,345. Transcript word-count correlation was 0.9816 across 182 pairs, not accuracy; stance labels lacked human validation.

Summary by alphaXiv.

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