Aspect Based Sentiment Analysis using POS Tagging and TFIDF
Kotagiri. Srividya1, A.Mary Sowjanya2

1Kotagiri.Srividya, Department of CSE, GMRIT, Rajam, India.
2A. Mary Sowjanya, Department of CS&SE, Andhra University College of Engineering , Visakhapatnam, A.P, India
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 1960-1963 | Volume-8 Issue-6, August 2019. | Retrieval Number:F7935088619/2019©BEIESP | DOI: 10.35940/ijeat.F7935.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Social media content on the internet is increasing day by day. Since media knowledge helps people in making decisions, web based businesses give their clients an opportunity to express their opinions about items available on the web in the form of surveys and reviews. Sentiment analysis can be used on product reviews or tweets, comments, blogs to infer individual’s feelings or attitudes. Here Aspect Based Sentiment Analysis is used to extract most interesting aspect of a particular product from unlabeled text. We have developed two models for aspect/feature extraction.Model1 uses POS tagging whereas Model2 utilizes TFIDF .In Model 1 we start with noun phrase algorithm and extend it to adjectives and adverbs to extract all the aspect terms. In model2 after data preprocessing TDIDF technique is used. The relative importances of the aspects are calculated and the most important positive, negative and neutral aspects are presented to the user. Naïve Bayes, Support Vector machine, Decision Tree, KNN were used to classify the sentiment polarity of the generated aspects.
Keywords: Aspects, Opinion Mining, Naïve Bayes, Support Vector Machine, KNN, Decision tree, Polarity