面向汽车领域对象级知识增强情感分析模型研究  

Research on Object-level Knowledge-enhanced Sentiment Analysis Model in the Automotive Field

作　　者：骆仕杰 韩抒真 金日泽 汪剑鸣[2] 李轩冰 LUO Shijie;HAN Shuzhen;JIN Rize;WANG Jianming;LI Xuanbing(Office of the Cyberspace Affairs,Tiangong University,Tianjin 300387,China;School of Computer Science and Technology,Tiangong University,Tianjin 300387,China;Library,Tianjin University of Traditional Chinese Medicine,Tianjin 301617,China)

机构地区：[1]天津工业大学网络安全和信息化办公室,天津300387 [2]天津工业大学计算机科学与技术学院,天津300387 [3]天津中医药大学图书馆,天津301617

出　　处：《小型微型计算机系统》2025年第1期135-142,共8页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61806142)资助;天津市科学技术局项目(19PTZWHZ00020)资助;中国学位与研究生教育学会项目(2020MSA50)资助。

摘　　要：面对汽车评论中对各项指标情感分类分析的需求,本研究提出了两部分任务:一是识别汽车评价对象并抽取情感要素;二是进行基于情感知识增强的情感分类分析.本文借助点互信息方法(PMI),探究对象词语与情绪词语的联系,进一步运用文本情感要素分析方法,构建了一种基于情感知识增强的汽车评论对象级情感分析模型(OLSCA).该模型首先采用PMI方法确定汽车评价关键指标与情绪词语极性的关系,接着通过自动情感词语掩盖及情感对象预测分析,形成词语、词语极性、对象级情感关系三部分的预测目标,生成针对标记对象的情感分类结果.实验证明,OLSCA在汽车评价领域对短文本评论进行情感分类分析,相较于传统文本语义情感分析有更大实际价值,有助于根据用户评价意图,全面构建汽车综合评价体系.In response to the need for sentiment classification analysis across various indices in automobile reviews,this study introduces two tasks:identifying the objects of car evaluations and extracting emotional components,and conducting sentiment classification analysis augmented by emotional knowledge.Leveraging the Point Mutual Information(PMI)method,the study elucidates the relationship between object words and emotional words,further utilizing textual emotional component analysis to establish an emotion-knowledge-enhanced Object-Level Sentiment Analysis Model(OLSCA).Initially,the model employs PMI to discern the relationship between key evaluation indicators and the polarity of emotional words.Subsequently,it generates predictive targets for words,word polarity,and object-level emotional relations via automated emotional word masking and emotional object predictive analysis,yielding sentiment classification outcomes for tagged objects.Experimental results demonstrate that OLSCA,when executing sentiment classification analysis on succinct reviews in the car evaluation domain,offers substantial practical utility compared to traditional text semantic sentiment analysis,facilitating the comprehensive development of a car evaluation framework grounded in user evaluation intent.

关 键 词：PMI 对象级情感分析 情感知识增强 用户评价意图 汽车评价体系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]