| --- | |
| title: ACSA Clothing Sentiment | |
| emoji: "👕" | |
| colorFrom: blue | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| python_version: "3.10" | |
| app_file: app.py | |
| pinned: false | |
| # Aspect-Level Sentiment Analysis for Clothing Reviews | |
| Interactive demo and research dashboard for a BERT metadata-fusion ACSA model trained on 30,000 clothing reviews. | |
| ## Included inference artifacts | |
| - Proposed metadata-fusion checkpoint and tokenizer | |
| - Matching `meta_encoder.pkl` | |
| - Overall, aspect-level, and ablation evaluation reports |