Paper: A Large Scale Arabic Sentiment Lexicon for Arabic Opinion Mining

ACL ID W14-3623
Title A Large Scale Arabic Sentiment Lexicon for Arabic Opinion Mining
Venue Workshop on Arabic Natural Language Processing
Session
Year 2014
Authors

Most opinion mining methods in English rely successfully on sentiment lexicons, such as English SentiWordnet (ESWN). While there have been efforts towards building Arabic sentiment lexicons, they suffer from many deficiencies: limited size, unclear usability plan given Ara- bic?s rich morphology, or non- availability publicly. In this paper, we address all of these issues and produce the first publicly available large scale Standard Arabic sentiment lexicon (Ar- SenL) using a combination of existing re- sources: ESWN, Arabic WordNet, and the Standard Arabic Morphological Ana- lyzer (SAMA). We compare and com- bine two methods of constructing this lexicon with an eye on insights for Ara- bic dialects and other low resource lan- guages. We also present an extrinsic evaluation in ...