Opinion Mining and Trend Analysis on Twitter Data
Anuj Kumar1, Hoshiyar S Kanyal2, Shivani Sharma3, Kaushal Singh4, Ayushi Dwivedi5

1Anuj Kumar, Assistant professor, Department of CSE, Hi-Tech Institute of Engg & Technology, Ghaziabad, India.
2Dr. Hoshiyar Singh Kanyal*, Associate Professor & HOD, Department of CSE, Hi-Tech Institute of Engg & Technology, Ghaziabad, India.
3Shivani Sharma B.Tech. (CSE), MAIT, Ghaziabad, India.
4Kaushal Singh, B.Tech. CSE), MAIT, Ghaziabad, India.
5Ayushi Dwivedi, B.Tech. CSE), MAIT, Ghaziabad, India.

Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 1650-1653 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1547059120/2020©BEIESP | DOI: 10.35940/ijrte.A1547.059120
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: With rise in Internet use across the global, there has been a trending increase in the online data. Every person from different profession gives their view from politics to entertainment, sports or economics. The web’s current evolution is a major pacesetter as it generates an effectual methodology to embed “smart data” into web pages and hence result in easy content implementation for authors. The web 2.0 has changed the way of communication on the web. Using Social Networks (SNs) they have become active participants by connecting, producing and sharing information, experiences and opinions with each other [1]. Public opinions extracted in the form of trends are interesting for researchers, sociologists, news reporters, marketing professionals and opinion tracking companies. The aim of this project is opinion mining and the analysis of the trends of the public statements gathered from different social media sources (specifically twitter). Here Binary sentiment analysis is performed on currently fetched data from twitter over various emotional quotients. W have also performed (i) Comparison between two users based on public reaction in the form of likes, shares and number of re-tweets; (ii) Visualization of comparison results by plotting graphs over popularity of social media (likes/re-tweets/shares). 
Keywords: Smart Data, Social Networks (SNs), Web 2.0, Opinion Mining, Binary Sentimental Analysis, Emotional Quotients.
Scope of the Article: Opinion Mining