lamanhnguyen at SemEval-2026 Task 2: Uncovering Lexical Bias and Momentum Lag in Longitudinal Emotion Prediction using Multi-task DeBERTa
Year: 2026
Type: conference-paper
Abstract: This paper describes our system for SemEval-2026 Task 2: Predicting Variation in Emotional Valence and Arousal.We approached the task by fine-tuning a weighted ensemble of DeBERTa-v3-base models.Our system achieved the second-highest Valence composite correlation (r = 0.687) and ranked 5th in the overall V&A average in Subtask 1.More importantly, we provide an empirical analysis of our model's performance on longitudinal tasks, where it exhibited significant inverse correlations.We quantify the "Venting Effect," showing a systematic tendency for the model to over-index on negative lexical cues despite self-reported relief.Furthermore, we analyze the structural trade-off between Mean Absolute Error (MAE) and Pearson correlation (r) induced by smoothing techniques.
Author: Lam Anh Nguyen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166817304