Model: answerdotai/ModernBERT-base fine-tuned for binary sequence classification (2 labels)
Context length: 2048 tokens
Task: Binary classification (positive vs. negative)
Intended use: Classifying review texts for presence of emotionally impactful experiences
Summary:
This model is a fine-tuned ModernBERT-base supporting 2048-token inputs. Training used weighted cross-entropy to handle class imbalance (≈30% positives), AdamW with a conservative learning rate, and early stopping based on validation average precision (AUPRC). The best checkpoint by validation AUPRC was reloaded and saved for release. The model targets robust performance across long-text reviews.
Intended use: Binary classification of review-like texts. Positive class corresponds to an expression of an emotionally impactful experience, which includes emotionally moving/challengin/discomforting experiences. See associated paper for a more detailed discussion and definition of the concept and review annotation.
Not …
