Inducing a lexicon of abusive words: a feature-based approach
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 p...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
2018
|
| In: |
The 2018 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - proceedings of the conference
Year: 2018, Pages: 1046-1056 |
| DOI: | 10.18653/v1/N18-1095 |
| Online Access: | Verlag, Volltext: https://doi.org/10.18653/v1/N18-1095 Verlag, Volltext: https://www.aclweb.org/anthology/N18-1095 
|
| Author Notes: | Michael Wiegand, Josef Ruppenhofer, Anna Schmidt, Clayton Greenberg |
| Summary: | 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 cross-domain detection of abusive microposts. |
|---|---|
| Item Description: | Gesehen am 04.09.2019 |
| Physical Description: | Online Resource |
| DOI: | 10.18653/v1/N18-1095 |