Reproduce “We Don't Speak the Same Language: Interpreting Polarization through Machine Translation” 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
Ashiqur R. KhudaBukhsh, Rupak Sarkar, Mark S. Kamlet, Tom M. Mitchell
The authors treat discussions on different news channels as separate languages, aligning FastText word embeddings with identical stopwords and finding words used in similar contexts. They inspect mismatched word pairs and aggregate self-translation rates. In 2020, CNN translated more similarly toward MSNBC (94.20%) than Fox News (90.20%), but the result describes these corpora, not all political beliefs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.