TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Wiegand, Michael
A1  - Ruppenhofer, Josef
A1  - Schmidt, Anna
A1  - Greenberg, Clayton
T1  - Inducing a Lexicon of Abusive Words – a Feature-Based Approach
T2  - Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, June 1-June 6, 2018, New Orleans, Louisiana, Volume 1 (Long Papers)
N2  - We address the detection of abusive words. The task is to identify such words among a set of negative polar expressions. We propose novel features employing information from both corpora and lexical resources. These features are calibrated on a small manually annotated base lexicon which we use to produce a large lexicon. We show that the word-level information we learn cannot be equally derived from a large dataset of annotated microposts. We demonstrate the effectiveness of our (domain-independent) lexicon in the crossdomain detection of abusive microposts.
KW  - Computerlinguistik
KW  - Text Mining
KW  - Beleidigung
KW  - Natürliche Sprache
Y1  - 2018
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-84719
UR  - https://aclanthology.info/papers/N18-1095/n18-1095
SN  - 978-1-948087-27-8
SB  - 978-1-948087-27-8
U6  - https://doi.org/10.18653/v1/N18-1095
DO  - https://doi.org/10.18653/v1/N18-1095
SP  - 1046
EP  - 1056
PB  - Association for Computational Linguistics
CY  - Stroudsburg, PA
ER  -