@inproceedings{20baaae35f96486fabcb4c9aacd9242a,
title = "LABR: A large scale arabic book reviews dataset",
abstract = "We introduce LABR, the largest sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars. We investigate the properties of the the dataset, and present its statistics. We explore using the dataset for two tasks: sentiment polarity classification and rating classification. We provide standard splits of the dataset into training and testing, for both polarity and rating classification, in both balanced and unbalanced settings. We run baseline experiments on the dataset to establish a benchmark.",
author = "Mohamed Aly and Amir Atiya",
year = "2013",
language = "English (US)",
isbn = "9781937284510",
series = "ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "494--498",
booktitle = "Short Papers",
address = "United States",
note = "51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 ; Conference date: 04-08-2013 Through 09-08-2013",
}