A Novel Deep Learning Based Sentiment Analysis of Movie using Hybrid CNN_SVM Algorithm
Raviya.K1, Mary Vennila.S2
1Mrs.Raviya.K*, Research Scholar, PG and Research Department of computer science, Presidency College, Chennai. India.
2Dr. Mary Vennila.S, Associate Professor and Research Supervisor , PG and Research department of computer science, Presidency College, Chennai. India.

Manuscript received on November 17., 2019. | Revised Manuscript received on November 24 2019. | Manuscript published on 30 November, 2019. | PP: 12391-12394 | Volume-8 Issue-4, November 2019. | Retrieval Number: D7115118419/2019©BEIESP | DOI: 10.35940/ijrte.D7115.118419

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: Data flow in web is becoming high and vast, extracting useful and meaningful information from the same is especially significant. The extracted information can be utilized for enhanced decision making. The information provided by the end-users is normally in the form of comments with respect to different products and services. Sentiment analysis is effectively carried out in these kinds of compact review to give away the people’s opinion of any products. This analyzed data will be efficient to improve the business strategy. In our work the collected online movie reviews are analyzed by using machine learning sentiment classification models like Random Forest, Naive Bayes, KNN and SVM. The work has been extended with CNN and hybrid CNN-SVM deep learning models to achieve higher performance. Comparing the workings of all the above classification models for sentiment analysis based upon various performance metrics is the main objective of the paper.
Keywords: Machine Learning, Sentiment Analysis, Movie review, Algorithm, Random Forest, Naive Bayes, KNN, SVM, CNN
Scope of the Article: Machine Learning.