@inproceedings{6a9ba3e6c71640708f1446a2c407da0a,
title = "EveTAR: A new test collection for event detection in Arabic tweets",
abstract = "Research on event detection in Twitter is often obstructed by the lack of publicly-available evaluation mechanisms such as test collections; this problem is more severe when considering the scarcity of them in languages other than English. In this paper, we present EveTAR, the first publicly-available test collection for event detection in Arabic tweets. The collection includes a crawl of 590M Arabic tweets posted in a month period and covers 66 significant events (in 8 different categories) for which more than 134k relevance judgments were gathered using crowdsourcing with high average inter-annotator agreement (Kappa value of 0.6). We demonstrate the usability of the collection by evaluating 3 state-of-the-art event detection algorithms. The collection is also designed to support other retrieval tasks, as we show in our experiments with ad-hoc search systems.",
keywords = "Ad-hoc search, Crowdsourcing, Evaluation, Twitter",
author = "Hind Almerekhi and Maram Hasanain and Tamer Elsayed",
note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016 ; Conference date: 17-07-2016 Through 21-07-2016",
year = "2016",
month = jul,
day = "7",
doi = "10.1145/2911451.2914681",
language = "English",
series = "SIGIR 2016 - Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval",
publisher = "Association for Computing Machinery, Inc",
pages = "689--692",
booktitle = "SIGIR 2016 - Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval",
}