Sentiment Analysis Using Optimal Feature and Ensemble Classifier |
Author(s): |
| Manpreet kaur , Department of Computer Science and Application, Kurukshetra University, Kurukshetra; Monika, Department of Computer Science and Application |
Keywords: |
| Sentiment Analysis, Opinion Mining, Support Vector Machine (SVM), Naive Bayes (NB), Classification, Random Forest, K- Nearest Neighbor (KNN), Sentiments |
Abstract |
|
Sentiment Analysis means opinion mining. The goal is to identify people’s opinions, perceptions, emotions toward entities and their attribute. Opinions are in positive, negative, and neutral in nature. For classifications of these opinions, different classifier can be used. This paper, improve the accuracy of ensemble classifier i.e. random forest and also perform analysis on the large dataset of movie reviews with the help of various classifiers like Support vector machine, k-nearest neighbor, naive bayes on proposed optimal features. The proposed method achieves better accuracy than the previous approaches by using optimal features and TF-IDF for finding the frequency of term occurs in a document and for identifying how the term important is. Here, three metrics are used i.e. F-measure, Precision and recall for evaluating the performance of classifiers. |
Other Details |
|
Paper ID: IJSRDV4I40748 Published in: Volume : 4, Issue : 4 Publication Date: 01/07/2016 Page(s): 964-966 |
Article Preview |
|
|
|
|
