ahs95

BanglaBERT Fine-tuned for Bangla Sentiment Analysis This model is a fine-tuned version of `csebuetnlp/banglabert` on the SentiGOLD dataset for 5-class sentiment analysis in Bengali. It classifies text into: 1. 😠 Very Negative (SN) 2. 😞 Negative (WN) 3. 😐 Neutral (N) 4. 😊 Positive (WP) 5. 😍 Very Positive (SP) Key Features: - State-of-the-art Bangla language understanding - Handles both formal and informal Bengali text - Optimized for social media, reviews, and customer feedback - Requires text normalization using Bangla Normalizer Primary Use - Sentiment analysis of Bengali text - Social media monitoring - Customer feedback analysis - Product review classification Limitations - Performance may degrade on code-mixed text (Bengali-English) - May struggle with sarcasm and highly contextual expressions - Best for short to medium-length texts (up to 512 tokens) The model was fine-tuned on SentiGOLD, the largest gold-standard Bangla sentiment analysis dataset: | Feature | Value | |------------------------|---------------| | Total Samples | 70,000 | | Domains Covered | 30+ | | Source Diversity | Social media, news, blogs, reviews | | Class Distribution | Balanced across 5 classes | | Annotation Quality | Fleiss' kappa = 0.88 | | Parameter | Value | | --- | --- | | Learning Rate | 2e-5 → 1.05e-6 | | Batch Size | 48 | | Epochs | 5 | | Optimizer | AdamW | | Scheduler | ReduceLROnPlateau | | Weight Decay | 0.01 | | Gradient Accumulation | 4 steps | | Warmup Ratio | 5% | Class-weighted loss handling imbalance Early stopping (patience=3) Mixed precision (FP16) training Gradient checkpointing Text normalization using Bangla Normalizer | Epoch | F1 (Macro) | Accuracy | Very Neg F1 | Neg F1 | Neu F1 | Pos F1 | Very Pos F1 | | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | 0.6334 | 0.6331 | 0.6789 | 0.5834 | 0.6407 | 0.5635 | 0.7004 | | 5 | 0.6537 | 0.6551 | 0.7081 | 0.6157 | 0.6421 | 0.5789 | 0.7236 | | Metric | Score | | --- | --- | | Macro F1 | 0.6660 | | Accuracy | 0.6671 | Ethical Considerations - Bias: While SentiGOLD reduces bias through synthetic data, real-world validation is recommended - Use Cases: Suitable for: Product feedback analysis Social media monitoring Market research - Avoid: Critical decision systems without human oversight Contact For questions and support: [email protected]