Enhancing sentiment analysis using enhanced whale optimisation algorithm. (26th August 2020)

• Record Type: Journal Article
• Authors: Mohammed, Abdul Salam; Shukla, Vishal; Pandey, Avinash Chandra
• Is Part Of: International journal of intelligent information and database systems. Volume 13:Number 2/4(2020)
• Page Start: 208
• Page End: 230
• Publication Date: 2020-08-26
• Subjects: sentiment analysis -- metaheuristic methods -- natural language processing -- NLP -- clustering; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

Sentiment analysis is discovers the opinion of users with respect to some sentimental topics commonly available at the online social platforms. Twitter is one of the popular social networking sites where people express their views about any topic in the form of tweets. These Twitter posts are analysed to obtain the viewpoints of users by using clustering-based methods. However, due to the subjective nature of the sentimental datasets metaheuristic clustering methods outruns the conventional methods for sentiment analysis. Therefore, in this paper, a new metaheuristic method based on the whale optimisation method has been introduced. The proposed method finds the optimal cluster centres from sentimental data. The performance of proposed method has been tested on Twitter datasets and compared in respect to mean accuracy, mean recall, and mean precision, mean fitness with state-of-the-art approaches. The proposed method attains the highest accuracy for most of the datasets compared to the state-of-the-art.