SAMAR: A System for Subjectivity and Sentiment Analysis of Arabic Social Media

Abstract

In this work, we present SAMAR, a system for Subjectivity and Sentiment Analysis (SSA) for Arabic social media genres. We investigate: how to best represent lexical information; whether standard features are useful; how to treat Arabic dialects; and, whether genre specific features have a measurable impact on performance. Our results suggest that we need individualized solutions for each domain and task, but that lemmatization is a feature in all the best approaches. 1