Few-shot text-based emotion detection

2025-07-08

AI Summary

This work addresses low-resource multilingual few-shot sentiment classification, targeting English, Portuguese, and the low-resource language Emakhuwa. We propose a large language model (LLM) approach integrating prompt learning with lightweight fine-tuning for multi-label sentiment classification. Our method introduces cross-lingual prompt templates and a language-adaptive fine-tuning strategy to enhance generalization under data scarcity. Experiments demonstrate state-of-the-art performance: our model achieves a macro-F1 score of 0.3250 on the Emakhuwa subset—the first breakthrough for few-shot sentiment recognition in this language—and 0.7546 on the English subset, confirming both effectiveness and robustness across languages. The framework provides a scalable, language-agnostic technical pathway for sentiment analysis in low-resource settings.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Language and Vision

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

This paper describes the approach of the Unibuc - NLP team in tackling the SemEval 2025 Workshop, Task 11: Bridging the Gap in Text-Based Emotion Detection. We mainly focused on experiments using large language models (Gemini, Qwen, DeepSeek) with either few-shot prompting or fine-tuning. With our final system, for the multi-label emotion detection track (track A), we got an F1-macro of $0.7546$ (26/96 teams) for the English subset, $0.1727$ (35/36 teams) for the Portuguese (Mozambican) subset and $0.325$ ( extbf{1}/31 teams) for the Emakhuwa subset.

Problem

• Few-shot text-based emotion detection challenge
• Multi-label emotion detection in diverse languages
• Performance evaluation using large language models

Innovation

• Used large language models
• Few-shot prompting technique
• Fine-tuning for emotion detection