@inproceedings{WiegandRuppenhofer2021, author = {Michael Wiegand and Josef Ruppenhofer}, title = {Exploiting emojis for abusive language detection}, series = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, editor = {Paola Merlo and J{\"o}rg Tiedemann and Reut Tsarfaty}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, Pennsylvania}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104168}, pages = {369 -- 380}, year = {2021}, abstract = {We propose to use abusive emojis, such as the “middle finger” or “face vomiting”, as a proxy for learning a lexicon of abusive words. Since it represents extralinguistic information, a single emoji can co-occur with different forms of explicitly abusive utterances. We show that our approach generates a lexicon that offers the same performance in cross-domain classification of abusive microposts as the most advanced lexicon induction method. Such an approach, in contrast, is dependent on manually annotated seed words and expensive lexical resources for bootstrapping (e.g. WordNet). We demonstrate that the same emojis can also be effectively used in languages other than English. Finally, we also show that emojis can be exploited for classifying mentions of ambiguous words, such as “fuck” and “bitch”, into generally abusive and just profane usages.}, language = {en} }