Comparative Study on Classification Algorithms for Sentiment Analysis

  T.Devishree,  K.S. Jeen Marseline

The paper is based on comparative study with the classifiers named Support Vector Machine (SVM) and Recurrent Neural Network Long-Short Term Memory (RNN LSTM). The process has taken place by two classification algorithms to measure the sentiment from customer reviews. Sentiment analysis may also know to be opinion mining, which is the process of determining whether the text reflects positive, negative or neutral sentiment. Using this analysis, business managers can acquire deep perception into customer opinions about their product. Customer opinion can bring any changes to a brand’s success and the decision to monitor it can be the difference between a well-produced product and a missed opportunity. It can also inform marketing and product strategy by revealing chances to reframe the customer experience. By applying few metrics measures to produce the accuracy and finally, concluded by the comparative measures of the reviews from both the classifiers and finally among those classifier RNN LSTM shows the better results.

Keywords- sentiment analysis, SVM, LSTM RNN

Unique Identification Number - IJEDR1803055
Page Number(s) - 314-317
Pubished in - Volume 6 | Issue 3 | August 2018
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  T.Devishree,  K.S. Jeen Marseline,   "Comparative Study on Classification Algorithms for Sentiment Analysis", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.6, Issue 3, pp.314-317, August 2018, Available at :http://www.ijedr.org/papers/IJEDR1803055.pdf