Multi-Class Sentiment Analysis of Social Media Data with Machine Learning Algorithms
作者机构:Al-Farabi Kazakh National UniversityAlmaty050040Kazakhstan
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2021年第69卷第10期
页 面:913-930页
核心收录:
学科分类:0808[工学-电气工程] 0809[工学-电子科学与技术(可授工学、理学学位)] 07[理学] 08[工学] 071102[理学-系统分析与集成] 0831[工学-生物医学工程(可授工学、理学、医学学位)] 0711[理学-系统科学] 0805[工学-材料科学与工程(可授工学、理学学位)] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0801[工学-力学(可授工学、理学学位)] 0812[工学-计算机科学与技术(可授工学、理学学位)] 081103[工学-系统工程]
主 题:Social media sentiment analysis imbalanced classes machine learning oversampling undersampling SMOTE russian Kazakh
摘 要:The volume of social media data on the Internet is constantly *** has created a substantial research field for data *** diversity of articles,posts,and comments on news websites and social networks astonishes ***,most researchers focus on posts on Twitter that have a specific format and length *** majority of them are written in the English *** relatively few works have paid attention to sentiment analysis in the Russian and Kazakh languages,this article thoroughly analyzes news posts in the Kazakhstan media *** amassed datasets include texts labeled according to three sentiment classes:positive,negative,and *** datasets are highly imbalanced,with a significant predominance of the positive *** resampling techniques(undersampling,oversampling,and synthetic minority oversampling(SMOTE))are used to resample the datasets to deal with this ***,the texts are vectorized with the TF-IDF metric and classified with seven machine learning(ML)algorithms:naïve Bayes,support vector machine,logistic regression,k-nearest neighbors,decision tree,random forest,and *** results reveal that oversampling and SMOTE with logistic regression,decision tree,and random forest achieve the best classification *** models are effectively employed in the developed social analytics platform.