A Novel Framework for Sentiment Analysis and Opinion Mining

Abstract

Internet has become a platform for online learning, exchanging ideas and sharing opinions. Due to the sheer volume of opinion rich web resources such as discussion forum, review sites, blogs and news corporate available in digital form, much of the current research is focusing on the area of sentiment analysis. Social  networking sites are rapidly gaining popularity as they allow people to share and express their views about topics, have discussion with different communities, or post messages across the world. There has been lot of work in the field of sentiment analysis of social networking data. This study focuses mainly on sentiment analysis of data which is helpful to analyze the information in the wordnet where opinions are highly unstructured, heterogeneous and are either positive or negative, or neutral in some cases. In this paper, we provide a study for opinion mining like Feature extraction is a crucial step for opinion mining which been used to collect the useful information from user reviews and one that takes as input these features, assigns ranks to them and decides the final classification of the review as positive, neutral, or negative. The algorithm we propose to identify the features is called the Improved High Adjective Count (IHAC). This will be done by Artificial Bee Colony (ABC) optimization algorithm. The main idea behind the algorithm is the nouns for which reviewers express a lot of opinions are most likely to be the important and distinguishing than those for which users don’t express such opinions. After processing all reviews the algorithm will score for each noun. The ranking will be used to filter to find which scores above a threshold, and the second proposed algorithm is Max opinion score algorithm which ranks the extracted features using opinion scores assigned from previous method. Till now, there are few different problems predominating in this research community, namely, sentiment classification, feature based classification and handling negations. This paper presents a study covering the techniques and methods in sentiment analysis and challenges appear in the field.