Opinion Extraction using Hybrid Learning Algorithm with Feature Set Optimization Approach

Abstract

Evolution in engineering and technology added large size of data storage and transmission through the web application over the internet. This huge amount of data primarily used for exchange of information in between users and devices and in secondary aspects it has utilization as feedback, ratings and reviews that is supporting in generation of useful information of products, services, incidents etc. The data as opinion, feedback, view & suggestion is explored, organized & analyzed for selection of appropriate options. Sentiment analysis using the opinion extraction is a challenging task that is based on feature extraction and the concepts of Natural Language Processing that is applied in identification of the opinions of a user in terms of positive, neutral or negative ratings hidden in the form of comments typed as the text. Presently many data-processing based feature evaluation techniques for opinion extraction are used for solving the issues faced under sentiment classification applications. This article is based on development and application of algorithms for opinion extraction from text data available on web resources by K-Nearest Neighbor (KNN), Support vector machine (SVM) and hybrid of both named as SVM+KNN for classification of multi-label opinions from extracted text from review data of Twitter and Amazon. The performance of all the classification models (KNN, SVM and SVM+KNN) on both datasets is evaluated in terms of different parameters.