m-newhauser/distilbert-senator-tweets

A guide to fine-tuning DistilBERT on the tweets of American Senators with snscrape, SQLite, and Transformers (PyTorch) on Google Colab.

21
/ 100
Experimental

This project helps political analysts and researchers understand the prevailing sentiment and political leanings in the public statements of U.S. Senators. By analyzing a dataset of senator tweets, it provides insights into communication patterns and political positions. The output is a refined model capable of classifying the political sentiment or topic of new tweets, useful for those studying political discourse.

No commits in the last 6 months.

Use this if you are a political scientist, communication specialist, or researcher interested in analyzing the sentiment and characteristics of official political communication, specifically U.S. Senator tweets.

Not ideal if you need to analyze private communications, perform deep linguistic analysis beyond classification, or require real-time monitoring of a wide variety of political figures outside of U.S. Senators.

political-science sentiment-analysis public-policy political-communication social-media-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

HTML

License

GPL-3.0

Last pushed

Jan 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/m-newhauser/distilbert-senator-tweets"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.