Beyond Sentiment Classification: A Generative Framework for Emotion Intensity Evaluation in Text
Beyond Sentiment Classification: A Generative Framework for Emotion Intensity Evaluation in Text
超越情感分类：一种用于文本情感强度评估的生成式框架
Abstract: 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. 摘要： 我们引入了一种情感建模的新方法，将重点从“识别”转向“评估”，旨在解决离散分类在金融等应用领域中的局限性。
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. 通过构建一个情感强度评分数据集，并对开源权重生成式语言模型进行微调以输出 0-100 之间的连续数值，我们展示了一个在情感和情绪分析方面更具表现力和通用性的框架。
Our findings not only outperform classification baselines but also reveal surprising generalization capabilities and transfer effects to related constructs such as sentiment and arousal. 我们的研究结果不仅优于分类基准，还揭示了该模型在情感和唤醒度等相关概念上令人惊喜的泛化能力和迁移效应。
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. 这项工作通过引入情感强度评估作为分类的替代方案，为自然语言处理（NLP）的跨学科重构做出了贡献。我们认为，这种转变更好地契合了金融等领域的需求，在这些领域中，情感内容的程度对于解读和决策至关重要。
Paper Details:
- Authors: Francesco A. Fabozzi, Dasol Kim, William N. Goetzmann
- Submission Date: 15 May 2026
- Subjects: Computation and Language (cs.CL); General Economics (econ.GN); General Finance (q-fin.GN)
- DOI: 10.48550/arXiv.2605.16613
论文详情：
- 作者： Francesco A. Fabozzi, Dasol Kim, William N. Goetzmann
- 提交日期： 2026年5月15日
- 学科分类： 计算与语言 (cs.CL)；一般经济学 (econ.GN)；一般金融学 (q-fin.GN)
- 数字对象标识符 (DOI)： 10.48550/arXiv.2605.16613