Addressing Data Imbalance in Transformer-Based Multi-Label Emotion Detection with Weighted Loss

Xia Cui
7/15/2025
cs.CL

No official code found. Best implementation: summer1278/semeval2025-task11 (0 stars, CC0-1.0, last commit 2026-02-04).

Abstract

This paper explores the application of a simple weighted loss function to Transformer-based models for multi-label emotion detection in SemEval-2025 Shared Task 11. Our approach addresses data imbalance by dynamically adjusting class weights, thereby enhancing performance on minority emotion classes without the computational burden of traditional resampling methods. We evaluate BERT, RoBERTa, and BART on the BRIGHTER dataset, using evaluation metrics such as Micro F1, Macro F1, ROC-AUC, Accuracy, and Jaccard similarity coefficients. The results demonstrate that the weighted loss function improves performance on high-frequency emotion classes but shows limited impact on minority classes. These findings underscore both the effectiveness and the challenges of applying this approach to imbalanced multi-label emotion detection.

View on arXivView PDF

Code Implementations(1)

summer1278/semeval2025-task11Community100%
CC0-1.0

multi-emotion

00Jupyter NotebookDec 18, 20248 months agoCC0-1.0

Similar Papers

Fine-Grained Emotion Detection on GoEmotions: Experimental Comparison of Classical Machine Learning, BiLSTM, and Transformer Models

83% match2026

Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement

81% match2025

Emotion Detection with Transformers: A Comparative Study

80% match2024

Emotion Detection From Tweets Using a BERT and SVM Ensemble Model

80% match1 repo32022

Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function

79% match1 repo2024

Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction

79% match2025

Cite this paper

@article{cui2025addressing,
  title  = {Addressing Data Imbalance in Transformer-Based Multi-Label Emotion Detection with Weighted Loss},
  author = {Xia Cui},
  year   = {2025},
  eprint = {2507.11384},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.11384v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.11384.svg)](https://codeofpaper.com/paper/2507.11384)

Discussion