现代情报2025，Vol.45Issue(6)：3-13,45,12.DOI:10.3969/j.issn.1008-0821.2025.06.001
基于大语言模型微调的少样本方面级情感分析研究
Research on Few-Shot Aspect-Based Sentiment Analysis Based on Large Language Model Fine Tuning
摘要
Abstract
[Purpose/Significance]To address the issues of insufficient datasets and difficulty in cross-domain trans-fer in Chinese aspect-based sentiment analysis(ABSA),the paper explores the application and performance of Chinese large language models in ABSA tasks.[Method/Process]The paper utilized the ChatGLM model,employing prompt engi-neering and fine-tuning techniques of LoRa and P-Tuning,to conduct ABSA tasks on the Chinese open aspect-level senti-ment analysis dataset,ASAP.[Result/Conclusion]Compared with baseline models,ChatGLM based on few-shot prompts has performance close to that of full-sample deep learning models,while models combined with LoRa and P-Tun-ing achieve the best results and show good classification ability in the actual ASAP dataset.The paper verifies the effective-ness and feasibility of aspect-based sentiment analysis of Chinese large language models in the Chinese context and provides new solutions and references for the field of Chinese ABSA.关键词
大语言模型/方面级情感分析/提示工程/微调/少样本学习Key words
large language model/aspect-based sentiment analysis/prompt engineering/fine tuning/few-shot learning分类
计算机与自动化引用本文复制引用
朱侯,谭雅文,魏文韬..基于大语言模型微调的少样本方面级情感分析研究[J].现代情报,2025,45(6):3-13,45,12.基金项目
教育部人文社会科学研究项目"人群—算法互动的智媒舆论演化机制及风险控制"(项目编号:23YJC630270) （项目编号:23YJC630270）
国家自然科学基金项目"基于计算实验的社会化媒体隐私多源互动泄露机理研究"(项目编号:71801229). （项目编号:71801229）
