基于支持向量机的微博评论舆情分析  

Public Opinion Analysis of Microblog Comments Based on Support Vector Machine

作　　者：李绍华[1,2] 冯晶莹 张皓泓 马若驰 LI Shao-hua;FENG Jing-ying;ZHANG Hao-hong;MA Ruo-chi(School of Innovation and Entrepreneurship,Dalian University of Foreign Languages,Dalian 116044,China;School of Software Technology,Dalian University of Technology,Dalian 116024,China;Police Information Department,Liaoning PoliceAcademy,Dalian 116036,China;School of Software,Dalian University of Foreign Languages,Dalian 116044,China)

机构地区：[1]大连外国语大学创新创业学院,116044 [2]大连理工大学软件学院,116024 [3]辽宁警察学院公安信息系,大连116036 [4]大连外国语大学软件学院,116044

出　　处：《大学图书情报学刊》2021年第5期110-116,共7页Journal of Academic Library and Information Science

基　　金：国家自然科学基金项目“面向社交媒体的多语种文本情感分析方法研究”(61806038);辽宁省社会科学规划基金项目“基于大数据的高等院校科研类项目信息化集成管理平台的研究与实践”(L15CGL009);大连外国语大学大学生创新创业训练计划“东北亚新闻舆情信息分析平台研究及应用”(202110172A243)。

摘　　要：建立微博评论舆论监督机制,对突发事件进行及时的舆情研判,提供科学的舆论引导,是构建和谐社会的必要条件。人工舆情监督效率低、时间滞后,此外,情感分析的粗粒度和忽视情感演化趋势都会影响舆情分析研判的准确性。针对上述问题,文章提出一种基于爬虫和支持向量机的微博评论舆情分析模型。利用Word2Vec模型对样本用例进行训练,再对微博热门新闻评论使用request库进行爬取,接着使用jieba分词并带入模型进行判断,然后使用层次向量机进行情感判断,最后根据统计数据判断舆情趋势走向。通过案例分析,验证微博评论舆情分析模型的有效性。It is necessary to establish a microblog review and public opinion supervision mechanism,conduct timely public opinion research and judgment on emergencies,and provide scientific public opinion guidance for building a harmonious society.Manual public opinion supervision is inefficient and time lagging.In addition,the coarse-grained sentiment analysis and ignoring the trend of sentiment evolution will affect the accuracy of public opinion analysis and judgment.In response to the above problems,the article proposes a microblog comment public opinion analysis model based on crawlers and Support Vector Machine(SVM).The paper uses the Word2Vec model to train the sample use cases,and then uses the request library to crawl the hot news comments on Weibo,then uses the jieba word segmentation for word segmentation and brings it into the model for judgment,then uses the hierarchical vector machine for emotional judgment,and finally judges according to statistical data the trend of public opinion.Through case analysis,the paper verifies the effectiveness of the microblog comment public opinion analysis model.

关 键 词：舆情分析 微博评论 支持向量机 Word2Vec 爬虫 

分 类 号：C912.63[经济管理] G206[社会学]