面向多源社交网络舆情的情感分析算法研究  

Research on sentiment analysis algorithm for public opinion of multi-source social networks

作　　者：彭浩[1] 朱望鹏 赵丹丹[1] 吴松洋[3] PENG Hao;ZHU Wang-peng;ZHAO Dan-dan;WU Song-yang(Department of computer science and Engineering,Zhejiang Normal University,Jinhua 321004,Zhejiang Province,China;School of Computer Engineering and Science,Shanghai 201900,China;The Third Research Institute of Ministry of Public Security,Shanghai 201204,China)

机构地区：[1]浙江师范大学计算机科学与工程系,浙江金华321004 [2]上海大学计算机工程与科学学院,上海201900 [3]公安部第三研究所,上海201204

出　　处：《信息技术》2019年第2期43-48,共6页Information Technology

基　　金：国家自然科学基金项目(61602418);教育部人文社科研究项目(15YJCZH125);浙江省公益技术研究社会发展项目(2016C33168);浙江省自然科学基金(LQ16F02-0002);信息网络安全公安部重点实验室开放课题(C15610);上海市信息安全综合管理技术研究重点实验室开放课题(AGK2018001)

摘　　要：随着互联网技术的快速发展,社交媒体的多元化也应运而生,因此如何有效分析多源社交网络舆情成为当前研究的热点。文中结合舆情信息的抓取、分词、过滤停用词等三个核心处理模块,基于舆情的情感及趋向性分析,提出了一种面向多源社交网络舆情的情感分析算法。仿真结果表明,该算法在多源社交网络舆情的分析处理中检测效果良好,说明该算法有效。文中的算法研究,可为该领域的进一步研究提供有价值的参考。With the rapid development of Internet technology,the diversification of social media has also emerged.Therefore,how to effectively analyze the multi-source social network public opinion has become a hot topic of current research.This paper combines three core processing modules of lyric information,such as crawling,word segmentation and filtering stop words,proposes a sentiment analysis algorithm for multi-source social networks based on lyric emotion and trend analysisi.The simulation results show that the proposed algorithm performs well in the analysis and processing of multi-source social network public opinion,which indicates that the algorithm is effective,and can provide valuable reference for further research in this field.

关 键 词：社交网络 舆情分析 情感发现 

分 类 号：TN915.03[电子电信—通信与信息系统]