Mining Tweets for Education Reforms

Omar, Mwana S., Njeru, Alexander M., Paracha, Samiullah, Wannous, Muhammad and Yi, Sun, "Mining Tweets for Education Reforms" 2017 IEEE International Conference on Applied System Innovation, Sapporo, 2017/05/13-17.

Document type:
Conference Publication

Metadata
Links
Versions
Statistics
  • Sub-type Conference paper
    Author Omar, Mwana S.
    Njeru, Alexander M.
    Paracha, Samiullah
    Wannous, Muhammad
    Yi, Sun
    Title Mining Tweets for Education Reforms
    Event Series IEEE International Conference on Applied System Innovation
    Publication Date 2017-05-17
    Place of Publication Taipei
    Publisher Taiwanese Institute of Knowledge Innovation (TIKI)
    Pages 416-419
    Title of Event 2017 IEEE International Conference on Applied System Innovation
    Date of Event 2017/05/13-17
    Place of Event Sapporo
    Language eng
    Abstract Microblogging and social networking sites have become a popular means of communication channels among internet users. They provide tools for people to voice their opinions. These sites contain vast amounts of opinionated data, leading to an increased growth in research on sentiment analysis and opinion mining. The study aims at using Twitter, a major and popular platform for microblogging and social communication, to conduct sentiment analysis. Real time data was automatically streamed using the Twitter API to collect the public's sentiments regarding education. A survey was also used to capture the public's opinions. The study will help overcome frustrations during implementation of education policies and reforms by taking into account the public's views and opinions.
    UNBIS Thesaurus SOCIAL MEDIA
    Keyword Machine learning
    Sentiment analysis
    Education reforms
    Copyright Holder The Editors
    Copyright Year 2017
    Copyright type All rights reserved
    ISBN 9781509048977
    DOI 10.1109/ICASI.2017.7988441
  • Versions
    Version Filter Type
  • Citation counts
    Scopus Citation Count Cited 0 times in Scopus Article
    Google Scholar Search Google Scholar
    Access Statistics: 470 Abstract Views  -  Detailed Statistics
    Created: Thu, 10 Aug 2017, 13:37:42 JST by Marcovecchio, Ignacio on behalf of UNU CS