Sentiment Analysis for Social Media using SVM Classifier of Machine Learning
Dipti Sharma1, Munish Sabharwal2
1Dipti Sharma, Department of Computer Science & Engineering, Chandigarh University, Mohali, India.
2Munish Sabharwal, Department of Computer Science & Engineering, Chandigarh University, Mohali, India.
Manuscript received on 21 September 2019 | Revised Manuscript received on 30 September 2019 | Manuscript Published on 01 October 2019 | PP: 39-47 | Volume-8 Issue-9S4 July 2019 | Retrieval Number: I11070789S419 /19©BEIESP | DOI: 10.35940/ijitee.I1107.0789S419
Open Access | Editorial and Publishing 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: Sentiment analysis is an area of natural language processing (NLP) and machine learning where the text is to be categorized into predefined classes i.e. positive and negative. As the field of internet and social media, both are increasing day by day, the product of these two nowadays is having many more feedbacks from the customer than before. Text generated through social media, blogs, post, review on any product, etc. has become the bested suited cases for consumer sentiment, providing a best-suited idea for that particular product. Features are an important source for the classification task as more the features are optimized, the more accurate are results. Therefore, this research paper proposes a hybrid feature selection which is a combination of Particle swarm optimization (PSO) and cuckoo search. Due to the subjective nature of social media reviews, hybrid feature selection technique outperforms the traditional technique. The performance factors like f-measure, recall, precision, and accuracy tested on twitter dataset using Support Vector Machine (SVM) classifier and compared with convolution neural network. Experimental results of this paper on the basis of different parameters show that the proposed work outperforms the existing work.
Keywords: Sentiment analysis, Data mining, Feature Optimization, Machine learning.
Scope of the Article: Machine Learning