Show simple item record

dc.contributor.advisorAbdinnour, Sue
dc.contributor.authorGuntaka, Venkata Sai Pramod Reddy
dc.contributor.authorGupta, Aman Kumar
dc.contributor.authorSomisetty, Sravya
dc.date.accessioned2020-05-10T00:31:08Z
dc.date.available2020-05-10T00:31:08Z
dc.date.issued2020-05-01
dc.identifier.citationGuntaka, V. S. P. R., Gupta, A. K., Somisetty, S. 2020. Twitter sentiment analysis and visualization -- In Proceedings: 16th Annual Symposium on Graduate Research and Scholarly Projects. Wichita, KS: Wichita State University, p.31
dc.identifier.urihttps://soar.wichita.edu/handle/10057/17592
dc.descriptionPresented to the 16th Annual Symposium on Graduate Research and Scholarly Projects (GRASP) held online, Wichita State University, May 1, 2020.
dc.descriptionResearch completed in the Department of Electrical Engineering and Computer Science, College of Engineering; Department of Finance, Real Estate, and Decision Sciences, W. Frank Barton School of Business
dc.description.abstractTwitter is a social networking site where users interact by posting messages called "tweets". The tweets cover a wide range of topics including personal, business, and government tweets from all over the world in multiple languages. Twitter presents a crucial data source for various types of analysis. Our research focuses on sentiment analysis of tweets. To achieve this objective, we first collect tweets using a Python library based on a keyword search query (like COVID-19) or a twitter handle for a person i.e. all the tweets made by this person's handle (like @realdonaldtrump). This data collection process is performed on a day basis (last 24 hours) and added to a master data file, which is cumulative. The data collected allows us to analyze them over certain periods of time such as the past day, week, month, and years (when available). The sentiment analysis is then performed by analyzing the text of the tweets and generating positive and negative sentiments for each tweet. We also analyze other metrics, such as the count of tweets, popular positive and negative words used in tweets, etc. We then visualize the sentiment analysis on a dashboard with various types of charts, including maps to understand the geographic origin of tweets, a density chart with positive, negative and neutral tweets along a timeline, bar charts visualizing the most popular hashtags, a Word Cloud representing the most important words across the tweets, and many more. Work in progress will be shared.
dc.description.sponsorshipGraduate School, Academic Affairs, University Libraries
dc.language.isoen_US
dc.publisherWichita State University
dc.relation.ispartofseriesGRASP
dc.relation.ispartofseriesv. 16
dc.titleTwitter sentiment analysis and visualization
dc.typeAbstract
dc.rights.holderWichita State University


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record