In this paper we present a new corpus of Arabic tweets that mention some form of violent event, developed to support the automatic identification of Human Rights Abuse. The dataset was manually labelled for seven classes of violence using crowdsourcing.
@InProceedings{ALHELBAWY16.553,
author = {Ayman Alhelbawy and Poesio Massimo and Udo Kruschwitz}, title = {Towards a Corpus of Violence Acts in Arabic Social Media}, booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, year = {2016}, month = {may}, date = {23-28}, location = {Portorož, Slovenia}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Sara Goggi and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {978-2-9517408-9-1}, language = {english} }
Summary of the paper