Title: Nearest neighbour-based feature selection and classification approach for analysing sentiments

Authors: Rajalaxmi Hegde; S. Seema

Addresses: M S Ramaiah Institute of Technology, MSR Nagar, 560054, Bengaluru, Karnataka, India Affiliated to Visvesvaraya Technological University, Belagavi, Karnataka, India; Department of Computer Science and Engineering, NMAM Institute of Technology, Nitte, 574110, Karkala Taluk, Udupi District, India Affiliated to Visvesvaraya Technological University, Belagavi, Karnataka, India ' Department of Computer Science and Engineering, M S Ramaiah Institute of Technology, MSR Nagar, 560054, Bengaluru, Karnataka, India Affiliated to Visvesvaraya Technological University, Belagavi, Karnataka, India

Abstract: Sentiment analysis is considered as one of the most important aspect in the field of research. The aim of the paper is to select features and perform classification of data using positive and negative. The objective of the proposed work is to analyse sentiment and perform classification. In traditional feature selection methods, the word order in the given documents is not considered and hence it will be a tedious process to compute the features. Existing sentiment analysis techniques do not predict the context and the similarity among the words. The proposed method performs the feature selection of data using the nearest neighbour-based approach where initially the distance metrics and the cosine similarity of the data are calculated based on the pre-processed data. The main aim is to perform feature selection and tune the hyper parameters to get the optimal value for improving performance. Experiments have conducted using several feature vectorisation methods to obtain better accuracy.

Keywords: accuracy; classification; cosine; distance; neighbour; features; feature selection; pre-processing; reviews; sentiment analysis.

DOI: 10.1504/IJBRA.2022.10045867

International Journal of Bioinformatics Research and Applications, 2022 Vol.18 No.1/2, pp.16 - 29

Received: 02 Jul 2019
Accepted: 04 Feb 2020

Published online: 07 Apr 2022 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article