RA-FinBERT：面向低资源金融情感分类的规则感知LoRA适配
RA-FinBERT: Rule-aware LoRA adaptation for low-resource financial sentiment classification
浏览论文内容
中文总结 AI 辅助
本研究提出规则感知FinBERT（RA-FinBERT），将LoRA与VADER衍生特征结合，仅增1024个参数，在金融情感分类任务中较基线模型准确率、宏F1值及中性类召回率均显著提升，适配低资源场景。
中文摘要 AI 辅助
金融情感分析将非结构化金融新闻转换为可支撑市场分析与决策的定量信号。现有面向资源高效型金融NLP的研究大多聚焦于压缩或适配预训练语言模型，较少关注将上下文表征与轻量型规则衍生特征相结合。本研究开发了规则感知FinBERT（RA-FinBERT），这是一种参数高效型框架，它将低秩适配（LoRA）与三个源自VADER的连续情感比例（正面、负面、中性）以及一个源级元数据特征相融合。标准化的四维特征向量被直接与768维的FinBERT最终层<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>表征拼接，并送入轻量型分类头。与结构匹配的仅文本FinBERT模型相比，该设计仅引入了1024个额外可训练权重。RA-FinBERT在金融新闻标题与描述的三类情感分类任务中，与仅文本FinBERT及轻量型DistilBERT基线进行了对比评估。在保留的测试集上，RA-FinBERT取得了69.89%的准确率和0.634的宏F1值，而仅文本FinBERT分别为63.44%和0.526；中性类召回率从18.18%提升至45.45%。该框架支持CPU与GPU执行，为计算资源受限场景下的金融情感分类提供了轻量且实用的方案。这些发现表明，规则衍生的情感信息与源元数据可作为FinBERT上下文表征的补充信号，以极小的额外模型复杂度提升性能。
英文摘要
Financial sentiment analysis converts unstructured financial news into quantitative signals that can support market analysis and decision-making. Existing work on resource-efficient financial NLP has largely focused on compressing or adapting pretrained language models, with less attention to combining contextual representations with lightweight rule-derived features. This study develops Rule-Aware FinBERT (RA-FinBERT), a parameter-efficient framework that integrates low-rank adaptation (LoRA) with three continuous VADER-derived sentiment proportions (positive, negative, and neutral) and a source-level metadata feature. The standardized four-dimensional feature vector is directly concatenated with the 768-dimensional final-layer FinBERT [CLS] representation and passed through a lightweight classification head. This design introduces only 1,024 additional trainable weights relative to a structurally matched text-only FinBERT model. RA-FinBERT was evaluated against text-only FinBERT and a lightweight DistilBERT baseline for three-class sentiment classification of financial-news titles and descriptions. On the held-out test set, RA-FinBERT achieved 69.89% accuracy and a macro F1 score of 0.634, compared with 63.44% and 0.526 for text-only FinBERT. Neutral-class recall increased from 18.18% to 45.45%. The framework supports both CPU and GPU execution, offering a lightweight and practical approach to financial sentiment classification under constrained computational resources. These findings indicate that rule-derived sentiment information and source metadata can provide complementary signals to contextual FinBERT representations and improve performance with minimal additional model complexity.
发表机构
- Northern Arizona University（北亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。
