indolem/IndoBERTweet
IndoBERTweet is the first large-scale pretrained model for Indonesian Twitter. Published at EMNLP 2021 (main conference)
Analyze and understand discussions on Indonesian Twitter, such as public opinion on brands or political topics. It takes raw Indonesian tweets and helps classify their sentiment, emotions, or identify named entities within the text. This tool is designed for data analysts, marketers, social scientists, or anyone monitoring public discourse in Indonesian on social media.
No commits in the last 6 months.
Use this if you need to extract meaningful insights like sentiment, emotions, or specific entities from large volumes of Indonesian Twitter data.
Not ideal if your primary data source is not Indonesian Twitter or if you need to analyze highly informal, non-standard text from other social media platforms.
Stars
71
Forks
6
Language
Python
License
—
Category
Last pushed
Sep 13, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/indolem/IndoBERTweet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DerwenAI/pytextrank
Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
Tiiiger/bert_score
BERT score for text generation
BrikerMan/Kashgari
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for...
asyml/texar
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. ...
yohasebe/wp2txt
A command-line tool to extract plain text from Wikipedia dumps with category and section filtering