Abstract

Abstract: - Aspect-based sentiment analysis is divided into two tasks aspect extraction and related sentiment identification. To carry out this task, features play an important role to determine the accuracy of the model. Feature extraction and feature selection techniques contribute to increase classification accuracy. Feature selection strategies reduce computation time, improve prediction performance, and provide a higher understanding of the information in machine learning or pattern recognition applications. This work focuses on aspect extraction from restaurant review dataset. In this system, we proposed a hybrid approach of feature selection which works on lemma features. Initially, the extracted features undergo pre-processing and then the term frequency matrix is generated which contains the occurrence count of features with respect to aspect category. In the next phase, different feature selection strategies are applied which includes selecting features based on correlation, weighted term frequency and weighted term frequency with the correlation coefficient. The performance of weighted term frequency with correlation coefficient approach is compared with the existing system and shows improvement classification accuracy of system.Keywords: Aspect-Based Sentiment Analysis (ABSA), Natural Language Processing (NLP), Term Frequency-Inverse Document Frequency (TF-IDF), feature extraction, feature selection, correlation coefficient.