Opinion Analysis on Twitter Data and Detecting Spam Tweets
Sai Charan Reddy Duvvuru1, Kommana N S V Srinesh Chowdary2, Tunga Sri Ashrith Reddy3
1Sai Charan Reddy Duvvuru, Department of Computer Science & Engineering, VIT University, Vellore, India.
2Kommana N S V Srinesh Chowdary, Department of Computer Science and Engineering,VIT University, Vellore, India.
3Tunga Sri Ashrith Reddy, Department of Computer Science &Engineering, VIT University, Vellore, India.
Manuscript received on November 15, 2019. | Revised Manuscript received on 24 November, 2019. | Manuscript published on December 10, 2019. | PP: 711-714 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6818129219/2019©BEIESP | DOI: 10.35940/ijitee.B6818.129219
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: Social network sites are getting to be noticeably awesome through a great many clients. The data that is accumulated from the clients has square with favorable circumstances to their companions and spammers. Twitter is a standout amongst the most well-known informal organizations that, clients can send short printed messages in particular tweet. Opinion analysis is utilized as a part of different fields to reach to a last reaction. For the most part different internet business sites utilize this analysis to enhance their organizations. In this project we used an improvised opinion analysis which includes spam recognition. Looks into have demonstrated that this specific system is additionally subjected to spammer’s attack more than other informal communities and more than six percent of tweets are spam. So, analyze of the spam tweets is imperative. In this research we firstly decide different components that are in charge of spam tweets and after that we distinguish them. Previous works in this field of spam tweets were completed by classification algorithms. Results appear, when this specific algorithm is set reasonably to the measure of exactness and accuracy of spam tweets location will enhance and false positive rate will decrease to the base of an incentive in correlation with the previous works.
Keywords: Data Stream, Opinion Analysis, Spam Detection, Twitter.
Scope of the Article: Data Analytics