• DocumentCode
    163441
  • Title

    Sentiment Analysis in Arabic tweets

  • Author

    Duwairi, Rehab M. ; Marji, Raed ; Sha´ban, Narmeen ; Rushaidat, Sally

  • Author_Institution
    Dept. of Comput. Inf. Syst., Jordan Univ. of Sci. & Technol., Irbid, Jordan
  • fYear
    2014
  • fDate
    1-3 April 2014
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    Social media platforms such as blogs, social networking sites, content communities and virtual worlds are tremendously becoming one of the most powerful sources for news, markets, industries, and much more. They are a wide platform full of thoughts, emotions, reviews and feedback, which can be used in many aspects. Despite these great avails, and with the increasingly enormous number of Arabic users on the internet, little research has tied these two together in a high and accurate professional manner [1]. This paper deals with Arabic Sentiment Analysis. We developed a framework that makes it possible to analyze Twitter comments or “Tweets” as having positive, negative or neutral sentiments. This can be applied in a wide range of applications ranging from politics to marketing. This framework has many novel aspects such as handling Arabic dialects, Arabizi and emoticons. Also, crowdsourcing was utilized to collect a large dataset of tweets.
  • Keywords
    data analysis; natural language processing; social networking (online); Arabic dialects; Arabic sentiment analysis; Arabic tweets; Arabizi; Twitter comments analysis; crowdsourcing; emoticons; social media platforms; Accuracy; Dictionaries; Internet; Media; Niobium; Sentiment analysis; Support vector machines; Arabic Sentiment Analysis; Crowdsourcing; Data Analytics; Opinion Mining; Supervised Learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information and Communication Systems (ICICS), 2014 5th International Conference on
  • Conference_Location
    Irbid
  • Print_ISBN
    978-1-4799-3022-7
  • Type

    conf

  • DOI
    10.1109/IACS.2014.6841964
  • Filename
    6841964