iamaziz/ar-embeddings

Sentiment Analysis for Arabic Text (tweets, reviews, and standard Arabic) using word2vec

47
/ 100
Emerging

Implements document-level sentiment classification by converting tokenized Arabic text to dense vectors using pre-trained word2vec embeddings (159K vocabulary, 300 dimensions trained on news corpora), then evaluates multiple scikit-learn classifiers (LinearSVC, LogisticRegressionCV, etc.) on benchmark datasets like LABR book reviews. Includes pre-computed Arabic embeddings and standardized train/test splits, enabling reproducible sentiment classification across formal and informal Arabic text variants.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

95

Forks

48

Language

Python

License

MIT

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/iamaziz/ar-embeddings"

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