• Login
    View Item 
    •   Shocker Open Access Repository Home
    • Graduate Student Research
    • GRASP: Graduate Research and Scholarly Projects
    • Proceedings 2020: 16th Annual Symposium on Graduate Research and Scholarly Projects
    • View Item
    •   Shocker Open Access Repository Home
    • Graduate Student Research
    • GRASP: Graduate Research and Scholarly Projects
    • Proceedings 2020: 16th Annual Symposium on Graduate Research and Scholarly Projects
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Twitter sentiment analysis and visualization

    View/Open
    abstract (85.63Kb)
    Date
    2020-05-01
    Author
    Guntaka, Venkata Sai Pramod Reddy
    Gupta, Aman Kumar
    Somisetty, Sravya
    Advisor
    Abdinnour, Sue
    Metadata
    Show full item record
    Citation
    Guntaka, 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
    Abstract
    Twitter 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.
    Description
    Presented to the 16th Annual Symposium on Graduate Research and Scholarly Projects (GRASP) held online, Wichita State University, May 1, 2020.

    Research 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
    URI
    https://soar.wichita.edu/handle/10057/17592
    Collections
    • EECS Graduate Student Conference Papers
    • FREDS Research Publications
    • Proceedings 2020: 16th Annual Symposium on Graduate Research and Scholarly Projects

    Browse

    All of Shocker Open Access RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsBy TypeThis CollectionBy Issue DateAuthorsTitlesSubjectsBy Type

    My Account

    LoginRegister

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    DSpace software copyright © 2002-2023  DuraSpace
    DSpace Express is a service operated by 
    Atmire NV