Semantic Sentiment Analysis in Arabic Social Media

Social media is a huge source of information. And is increasingly being used by governments, companies, and marketers to understand how the crowd thinks. Sentiment analysis aims to determine the attitudes of a group of people that are using one or more social media platforms with respect to a certain topic. In this paper, we propose a semantic approach to discover user attitudes and business insights from social media in Arabic, both standard and dialects. We also introduce the first version of our Arabic Sentiment Ontology (ASO) that contains different words that express feelings and how strongly these words express these feelings. We then show the usability of our approach in classifying different Twitter feeds on different topics.