Feature-Based Opinion Mining and Managed Machine Learning with Sentiment Classification Models
Jagdish Chandra Patni1, Shubham Billus2, Shubhita Garg3, Shivam Billus, Romika4
1Dr. Jagdish Chandra Patni, Department of Virtualization, University of Petroleum & Energy Studies, Dehradun (Uttarakhand) India.
2Shubhita Garg, School of Computer Science, University of Petroleum & Energy Studies, Dehradun (Uttarakhand) India.
Romika, School of Computer Science, University of Petroleum & Energy Studies, Dehradun (Uttarakhand) India. E-mail: email@example.com
3Shubham Billus, School of Computer Science, University of Petroleum & Energy Studies, Dehradun (Uttarakhand) India.
4Shivam Billus, School of Computer Science, University of Petroleum & Energy Studies, Dehradun (Uttarakhand) India.
Manuscript received on November 21, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 3999-4004 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B4555129219/2019©BEIESP | DOI: 10.35940/ijeat.B4555.129219
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Sentiment Analysis is individuals’ opinions and feedbacks study towards a substance, which can be items, services, movies, people or events. The opinions are mostly expressed as remarks or reviews. With the social network, gatherings and websites, these reviews rose as a significant factor for the client’s decision to buy anything or not. These days, a vast scalable computing environment provides us with very sophisticated way of carrying out various data-intensive natural language processing (NLP) and machine-learning tasks to examine these reviews. One such example is text classification, a compelling method for predicting the clients’ sentiment. In this paper, we attempt to center our work of sentiment analysis on movie review database. We look at the sentiment expression to order the extremity of the movie reviews on a size of 0(highly disliked) to 4(highly preferred) and perform feature extraction and ranking and utilize these features to prepare our multilabel classifier to group the movie review into its right rating. This paper incorporates sentiment analysis utilizing feature-based opinion mining and managed machine learning. The principle center is to decide the extremity of reviews utilizing nouns, verbs, and adjectives as opinion words. In addition, a comparative study on different classification approaches has been performed to determine the most appropriate classifier to suit our concern problem space. In our study, we utilized six distinctive machine learning algorithms – Naïve Bayes, Logistic Regression, SVM (Support Vector Machine), RF (Random Forest) KNN (K nearest neighbors) and SoftMax Regression.
Keywords: Sentiment Analysis, Opinion Mining, Movie Review, Machine learning, Classification Algorithms.