TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Wiegand, Michael
A1  - Ruppenhofer, Josef
ED  - Merlo, Paola
ED  - Tiedemann, Jörg
ED  - Tsarfaty, Reut
T1  - Exploiting emojis for abusive language detection
T2  - Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
N2  - 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.
KW  - Smiley
KW  - Beleidigung
KW  - Beschimpfung
KW  - Lexikon
KW  - Kontrastive Linguistik
KW  - Ambiguität
KW  - fuck
KW  - Social Media
KW  - Computerunterstützte Kommunikation
KW  - Graphisches Symbol
KW  - abusive language
KW  - abusive emojis
KW  - abusive words
KW  - ambiguous words
Y1  - 2021
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104168
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104168
UR  - https://www.aclweb.org/anthology/2021.eacl-main.28
SP  - 369
EP  - 380
PB  - Association for Computational Linguistics
CY  - Stroudsburg, Pennsylvania
ER  -