Feature-Based Opinion Mining for Amazon Product’s using MLT
Siva Kumar Pathuri1, ViswaGanesh.A2, Ravi Teja.P3, V. Rishi Chowdary4

1Siva Kumar Pathuri, Associate prof in the Dept of CSE at KLEF Vaddeswaram, Guntur.
2ViswaGanesh.Alapati, Scholar UG, Dept Of Compter Science & Engineering, K L University, Vaddeswaram, Guntur
3Ponnekanti. Ravi Teja, Scholar UG, Dept Of Compter Science & Engineering, K L University, Vaddeswaram, Guntur.
4V. Rishi Chowdary, Scholar UG, Dept Of Compter Science & Engineering, K L University, Vaddeswaram, Guntur.
Manuscript received on 20 August 2019. | Revised Manuscript received on 03 September 2019. | Manuscript published on 30 September 2019. | PP: 4105-4109 | Volume-8 Issue-11, September 2019. | Retrieval Number: K18370981119/2019©BEIESP | DOI: 10.35940/ijitee.K1837.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Analysis of sentiment’s or opinion mining is one of the major challenge of NLP (natural language processing) .Business Analytics plays a major role in the present scenario with a view to improve their business. These human beings especially relies upon on reviews about their product to resist in the marketplace and information analytics which can give us an excellent insight on what to expect in the future. Opinions can be referred to, with which futures opinions can be expected. Few words or terms can determine outcomes or results. As maximum of these business people try to improve their business to get maximum profit by selling quality products .So, in this regard sentiment analysis has gain a whole lot attention in current years.SA is an area of study within NLP which is used in identifying the view or opinion of a particular feature inside a content i.e., text. This paper is based on the different techniques used to classify a specified text according to the views expressed in it, i.e. whether a person’s overall mentality is negative or positive or neutral. We also examine the two-advance methods (feature classification followed by polarity classification) followed along with the experimental results. Finally in this paper we compared 3 ML classification techniques 1) SVM, 2) Naïve Bayes (NB) 3) Logistic Regression with Hybrid Algorithm in which hybrid algorithm gives more accuracy when compared with the other 3 ML algorithms.
Keywords: Sentiment analysis, Sentiment polarity categorization, Natural language Processing, Opinion mining, Feature based sentiment analysis.
Scope of the Article: Software Engineering Techniques and Production Perspectives