Open AccessHybrid Classification Technique for Sentiment Analysis of the Twitter Data
Author(s) -
Vinayak Khajuria,
Dilbag Singh
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.j9116.0881019
Subject(s) - sentiment analysis , computer science , random forest , social media , classifier (uml) , feature extraction , artificial intelligence , data mining , data science , machine learning , natural language processing , world wide web
Sentiment can be described in the form of any type of approach, thought or verdict which results because of the occurrence of certain emotions. This approach is also known as opinion extraction. In this approach, emotions of different peoples with respect to meticulous rudiments are investigated. For the attainment of opinion related data, social media platforms are the best origins. Twitter may be recognized as a social media platform which is socially accessible to numerous followers. When these followers post some message on twitter, then this is recognized as tweet. The sentiment of twitter data can be analyzed with the feature extraction and classification approach. The hybrid classification is designed in this work which is the combination of KNN and random forest. The KNN classifier extract features of the dataset and random forest will classify data. The approach of hybrid classification is applied in this research work for the sentiment analysis. The performance of the proposed model is tested in terms of accuracy and execution time.