• A.GEETHA
• M.ANJALI

Sentiment analysis is an freely automated mining of opinion, emotions and attitudes from the given text, database and speech through an NLP methods. It classifies our opinion into negative and positive categories else it makes neutral options. In our subjective analysis from mining the appraisal extraction of customer’s text meets the opinion to check. It may differ from their domains for example departmental stores, stock market, organization etc., for products, opinions likewise to make the decisions; it leads to powerful functionality to business earners using this analysis. The classification of sentiment is made as sentiment level, document level, feature level and aspect level, we have the classes called positive, negative and neutral. All those analysis give their results as best algorithm to find out sentiment analysis from the dataset, from that our thesis discuss about three main algorithms with an real time dataset taken from Amazon, it is review data’s about electronic products. We made our results using R tool to compare all those algorithm namely Support Vector Machine, Naïve bayes algorithm,, Logistic Regression,, Decision tree and neural network.

Sentiment Analysis, Naïve Naive Bayes Classifier, Support Vector Machine, Neural Network , Decision Tree and Logistic Regression

"SENTIMENT ANALYSIS OF ONLINE PRODUCTS BASED ON ITS REVIEW USING DATAMINING TECHINIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.92-97, June 2019, Available :http://www.jetir.org/papers/JETIR1906R51.pdf

"SENTIMENT ANALYSIS OF ONLINE PRODUCTS BASED ON ITS REVIEW USING DATAMINING TECHINIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp92-97, June 2019, Available at : http://www.jetir.org/papers/JETIR1906R51.pdf