Beyond Sentiment Classification: A Generative Framework for Emotion Intensity Evaluation in Text
It addresses the need for more nuanced emotion analysis in domains like finance, where emotional intensity matters for decision-making.
The paper introduces a generative framework for emotion intensity evaluation, moving from discrete classification to continuous scoring (0-100) using fine-tuned language models, and demonstrates superior performance over classification baselines with generalization to sentiment and arousal.
We introduce a novel approach to emotion modeling that shifts the focus from identification to evaluation, addressing the limitations of discrete classification in applied domains such as finance. By constructing a dataset of emotional intensity scores and fine-tuning open-weight generative language models to output continuous values from 0-100, we demonstrate a more expressive, generalizable framework for sentiment and emotion analysis. Our findings not only outperform classification baselines but also reveal surprising generalization capabilities and transfer effects to related constructs such as sentiment and arousal. This work contributes to the interdisciplinary recontextualization of NLP by introducing emotion intensity evaluation as an alternative to classification, arguing that this shift better aligns with the needs of domains--such as finance--where the degree of emotional content is central to interpretation and decision-making.