🤖 AI Summary
This work addresses the limitation of large language models (LLMs) in sentiment analysis—namely, their neglect of the inherent ambiguity of human emotions, including polysemy, co-occurrence, and graduality. We propose the first LLM-based sentiment recognition framework explicitly modeling emotional ambiguity. Our method introduces a context-enhanced zero-shot/few-shot prompting paradigm that incorporates historical dialogue context to enable fine-grained, hierarchical, and continuous emotion perception. To rigorously evaluate performance under varying ambiguity levels, we design a novel quantitative assessment framework for emotional ambiguity. Extensive experiments on three benchmark datasets demonstrate significant improvements over prior approaches: accuracy exceeds 92% in low-ambiguity settings and remains robust in high-ambiguity scenarios. These results empirically validate that contextual modeling substantially enhances LLMs’ capability to recognize ambiguous emotions.
📝 Abstract
Recent advancements in Large Language Models (LLMs) have demonstrated great success in many Natural Language Processing (NLP) tasks. In addition to their cognitive intelligence, exploring their capabilities in emotional intelligence is also crucial, as it enables more natural and empathetic conversational AI. Recent studies have shown LLMs' capability in recognizing emotions, but they often focus on single emotion labels and overlook the complex and ambiguous nature of human emotions. This study is the first to address this gap by exploring the potential of LLMs in recognizing ambiguous emotions, leveraging their strong generalization capabilities and in-context learning. We design zero-shot and few-shot prompting and incorporate past dialogue as context information for ambiguous emotion recognition. Experiments conducted using three datasets indicate significant potential for LLMs in recognizing ambiguous emotions, and highlight the substantial benefits of including context information. Furthermore, our findings indicate that LLMs demonstrate a high degree of effectiveness in recognizing less ambiguous emotions and exhibit potential for identifying more ambiguous emotions, paralleling human perceptual capabilities.