Applying Machine Learning Techniques for Sentiment Analysis in the Case Study of Indian Politics

被引:1
作者
Patil, Annapurna P. [1 ]
Doshi, Dimple [1 ]
Dalsaniya, Darshan [1 ]
Rashmi, B. S. [1 ]
机构
[1] Ramaiah Inst Technol, Dept Comp Sci & Engn, Bengaluru 560054, India
来源
ADVANCES IN SIGNAL PROCESSING AND INTELLIGENT RECOGNITION SYSTEMS | 2018年 / 678卷
关键词
Subjective data; Polarity; Machine learning; Twitter; Sentiment analysis;
D O I
10.1007/978-3-319-67934-1_31
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the recent era, humans have become detached from their surroundings, immediate peers and more addicted to their social media platforms and micro-blogging sites. Technology is digitalizing at a very fast pace and this has led to man being social, but only on technological forefront. Social media platforms like twitter, facebook, whatsapp, instagram are in trend. In our paper, we will concentrate on data generated through Twitter (tweets). People express their opinions, perspectives within a 140 character tweet, which is subjective. We try to analyze their emotion by tweet classification followed by sentiment analysis. On an average, with 328 million Twitter users, 6000 tweets are generated every second. This tremendous amount of data can be used to assess general public's views in economy, politics, environment, product reviews, feedbacks etc. and so many other sectors. Here, we take into account the political data from Tweets. The data obtained can be images, videos, links, emoticons, text, etc. The results obtained could help the government function better, improve their flaws, plan out better strategies to empower the nation.
引用
收藏
页码:351 / 358
页数:8
相关论文
共 9 条
  • [1] [Anonymous], 2011, TECHNICAL REPORT
  • [2] Ibrahim M, 2015, 2015 IEEE 15 INT C D
  • [3] Jain Anurag P, 2015, 2015 INT C INF PROC
  • [4] Jyoti R, ELECTION RESUL UNPUB
  • [5] TOM: Twitter opinion mining framework using hybrid classification scheme
    Khan, Farhan Hassan
    Bashir, Saba
    Qamar, Usman
    [J]. DECISION SUPPORT SYSTEMS, 2014, 57 : 245 - 257
  • [6] Kharche S. R, 2015, INT J COMPUT SCI APP, V8, P53
  • [7] Ravikiran J, TWITTER SENTIM UNPUB
  • [8] Razzaq M. A, 2014, 2014 IEEE ACM INT C
  • [9] Rincy J, PREDICTION ELE UNPUB