一种基于混合词特征表示的在线评论情感分析方法及应用  

Sentiment Analysis Method and Application of Online Comments Based on UBG

作　　者：杨成伟[1,2,3,4] 李希茹 祝翠玲 YANG Cheng-wei;LI Xi-ru;ZHU Cui-ling(School of Management Science and Engineering,Shandong University of Finance and Economics;Big Data and Artificial Intelligence Lab,Shandong University of Finance and Economics;Intelligent Elderly Care and Big Data Engineering Laboratory of Shandong Province;Shandong Provincial Emergency Management and Social Governance Big Data Development and Innovation Laboratory,Ji’nan 250014,China;Ji′nan Software Research Institute of China United Network Communications Co.,Ltd.,Ji’nan 250100,China)

机构地区：[1]山东财经大学管理科学与工程学院 [2]山东财经大学大数据与人工智能研究院 [3]山东省智慧养老与大数据工程实验室 [4]山东省应急管理与社会治理大数据发展创新实验室,山东济南250014 [5]中国联合网络通信有限公司济南软件研究院,山东济南250100

出　　处：《软件导刊》2023年第4期48-53,共6页Software Guide

基　　金：山东省自然科学基金项目(ZR2019MG037);山东省重点研发计划(重大科技创新工程)项目(2020CXGC010110);山东省重点研发计划(重大科技示范工程)项目(2021SFGC0102);山东省重点研发计划(软科学项目)(2020RKB01431)软著编号:计算机软件著作权(2021SR1391331)。

摘　　要：大数据给企业数字化运营管理带来了新的机遇,数据中蕴藏着用户真实的情感反馈,有利于企业及时掌握产品服务质量、调整企业营销策略、优化产品性能,对于提升企业竞争力、加速企业数字化转型极其重要。提出一种基于混合词特征表示(UBG)的在线评论数据情感分类方法,利用情感大数据分类技术进行数据预处理、数据探索和情感建模,实现情感精准分类,再通过大数据可视化帮助管理决策者洞悉运营管理中存在的问题以制定解决方案。以R酒店数字化运营管理提升问题为例,建立基于混合词特征表示的多项式朴素贝叶斯情感分类模型,并结合所提方法开发原型系统,为企业运营科学管理、数字管理提供了一种新的思路和方法。Big data has brought new opportunities for enterprise digital operation and management.The data contains the real emotional feed⁃back of users,which is conducive to enterprises to timely grasp their product service quality,adjust enterprise marketing strategy and optimize product performance.It is important to improve the competitiveness of enterprises in their peers and accelerate the digital transformation of en⁃terprises.Thus,the method of enterprise intelligent operation management based on sentiment analysis on the user comments is proposed which can help the enterprise decision makers understand existing problems and formulate its solutions through data prepossessing,data explo⁃ration,data classification modeling for user comments by big data sentiment classification technology and data visualization.Taking the com⁃petitiveness of R Hotel as an example,a polynomial Naive Bayesian sentiment classification model based on Unigram and Bigram is estab⁃lished.And the corresponding prototype system is developed,and the feasibility of the method proposed is verified after putting it into practice which provides a new idea and method for enterprise scientific digital operation and management.

关 键 词：数据驱动 情感分类 企业运营管理 在线评论 机器学习 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]