Sentimental Analysis and Detection of Rumours for Social Media Data using Logistic Regression
Asha R1, Rahul Jain2, Gourav Das3, Pranjnay Bharadwaj4

1Ms. Asha R, Assistant Professor in Computer science Department in SRM Institute of Science and Technology, Chennai.
Rahul Jain, Currently Pursuing B.tech Degree in Computer Science and Engineering at SRM Institute of Science and Technology.
Gourav Das, Currently Pursuing B.tech Degree in Computer Science and Engineering at SRM Institute of Science and Technology.
Pranjnay Bharadwaj, Currently Pursuing B.tech Degree in Computer Science and Engineering at SRM Institute of Science and Technology.

Manuscript received on October 14, 2019. | Revised Manuscript received on 22 October, 2019. | Manuscript published on November 10, 2019. | PP: 2123-2126 | Volume-9 Issue-1, November 2019. | Retrieval Number: A4670119119/2019©BEIESP | DOI: 10.35940/ijitee.A4670.119119
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: Over the last decade ,the Internet has become an ubiquitous and enormous suffuse medium of the user generated content and self-opinionated knowledge. Users currently have the facility to specify their views, opinions and ideas publically. Victimizing social media platform is a place where people can express their mindsets and feelings in a well associated manner and hence is productive and economical . These ever-growing subjective knowledge are doubtless, an especially made for supply of data of any reasonably method process. The Sentiment Analysis aims at distinctive self-opinionated knowledge during an Internet and classifying them in line with their polarity whether or not they contain positive ,negative or neutralizing references. Sentiment Analysis could be a drawback of text based mostly analysis however there are difficulties which are needed to be pondered upon that would create a tough parameter as compared to ancient text based analysis. It depicts the state where it has a desire of trial to figure out these issues and it’s spread out many chances for further analysis for handling negative sentences, hidden emotions , slangs and sentence sarcasm. The project also proposes additional features compared to other previous model projects by enabling the detection of rumor , identifying and analyzing whether message given via user belongs to rumor category or not using Logistic Regression process in Machine Learning domain.
Keywords: Machine Learning , Sentiment Analysis , Rumor Detection, Slang , Social Media Data
Scope of the Article: Machine Learning