Information Extraction for Social Media

M. B. Habib, M. van Keulen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

13 Downloads (Pure)


The rapid growth in IT in the last two decades has led to a growth in the amount of information available online. A new style for sharing information is social media. Social media is a continuously instantly updated source of information. In this position paper, we propose a framework for Information Extraction (IE) from unstructured user generated contents on social media. The framework proposes solutions to overcome the IE challenges in this domain such as the short context, the noisy sparse contents and the uncertain contents. To overcome the challenges facing IE from social media, State-Of-The-Art approaches need to be adapted to suit the nature of social media posts. The key components and aspects of our proposed framework are noisy text filtering, named entity extraction, named entity disambiguation, feedback loops, and uncertainty handling.
Original languageEnglish
Title of host publicationProceedings of the Third Workshop on Semantic Web and Information Extraction (SWAIE 2014), Dublin, Ireland
Place of PublicationDublin
PublisherAssociation for Computational Linguistics
Number of pages8
Publication statusPublished - 1 Aug 2014
Externally publishedYes


  • Information Extraction
  • Social Media
  • Twitter

Cite this