index / uran-lajci/albanian-sentiment-analysis-jev
albanian-sentiment-analysis-jev
Sentiment classification of Albanian COVID-19 Facebook comments with TypeSafe's Jev, using no training data. Compared with the 20 models of Kastrati et al. (2021), re-trained on the paper's own split: Jev reaches 75.7 weighted F1 on the test set, against 72.1 for the best re-trained model (mBERT). Includes data, code and report.
Research and EvalsFeature ScoringListedPython
Repository
Stars0
LanguagePython
LicenseMIT
Created2026-10-07
Last pushed2026-10-07
Officialno
Judgment
Genuine Jev project0.87
gate 0.5
Uses Jev at runtime0.84
Is a meta list0.03
Is a reimplementation0.11
Quality scales
Substance1.40 / 3
gate 0.5
Docs2.57 / 3
Novelty1.55 / 3
Composite score0.58
Category distribution
Research and Evals1.00
Games and Simulation0.00
Integrations0.00
Applications0.00
Other0.00
Learning0.00
SDKs and Clients0.00
Agent and Dev Tooling0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternFeature Scoring
Pattern confidence0.50
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-10-07
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-10-07 12:39 UTC