Multilingual Sentiment Mining System to Prognosticate Governance
作者机构:COMSATS University IslamabadLahore CampusLahorePakistan Computer Science DepartmentUniversity of TabukTabukSaudi Arabia
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2022年第71卷第4期
页 面:389-406页
核心收录:
学科分类:08[工学] 0805[工学-材料科学与工程(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)]
主 题:Multilingual NLP artificial intelligence government sentiment analysis NLP NLTK ensemble technique multilingual twitter data science
摘 要:In the age of the internet,social media are connecting us all at the tip of our *** are linkedthrough different social *** social network,Twitter,allows people to tweet their thoughts on any particular event or a specific political body which provides us with a diverse range of political *** paper serves the purpose of text processing of a multilingual dataset including Urdu,English,and Roman *** machine learning solutions for sentiment analysis and train models,collect the data on government from Twitter,apply sentiment analysis,and provide a python library that classifies text *** data contained tweets in three languages:English:200k,Urdu:200k and Roman Urdu:*** different classification models are applied to determine sentiments,and eventually,the use of ensemble technique to move forward with the acquired results is *** Logistic Regression model performed best with an accuracy of 75%,followed by the Linear Support Vector classifier and Stochastic Gradient Descent model,both having 74%***,Multinomial Naïve Bayes and Complement Naïve Bayes models both achieved 73%accuracy.