A proposed sentiment analysis tool for modern Arabic using human-based computing

  • Authors:
  • Afnan A. Al-Subaihin;Hend S. Al-Khalifa;AbdulMalik S. Al-Salman

  • Affiliations:
  • King Saud University, Riyadh, Saudi Arabia;King Saud University, Riyadh, Saudi Arabia;King Saud University, Riyadh, Saudi Arabia

  • Venue:
  • Proceedings of the 13th International Conference on Information Integration and Web-based Applications and Services
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sentiment analysis is the process of identifying the polarity of sentiments held in opinions found in pieces of text and classifying them as positive, negative or neutral. In this paper, we propose the implementation of a sentiment analysis tool that is conducted over text found in Arabic new media including web forums, comments on newspaper articles and other websites with evaluative content. The expected input of the tool, which is informal Colloquial Arabic, is characterized to be of highly non-structured nature and subject to trends used to express sentiments. Our solution is a novel technique that merges the area of human computation with the task of natural language processing.