Generalizability of Abusive Language Detection Models on Homogeneous German Datasets

被引：4

作者：

Seemann, Nina ^{[1
]}

Lee, Yeong Su ^{[1
]}

Höllig, Julian ^{[1
]}

Geierhos, Michaela ^{[1
]}

机构：

[1] Research Institute CODE, Bundeswehr University Munich, Werner-Heisenberg-Weg 39, Neubiberg,85577, Germany

来源：

关键词：

Compendex;

D O I：

10.1007/s13222-023-00438-1

中图分类号：

学科分类号：

摘要：

Deep learning

引用

页码：15 / 25

页数：10

共 14 条

[1] Beddiar DR(2021)Data expansion using back translation and paraphrasing for hate speech detection Online Soc Netw Media 24 100-153
[2] Jahan MS(2020)The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation Bmc Genomics 58 102524-500
[3] Oussalah M(2021)How well do hate speech, toxicity, abusive and offensive language classification models generalize across datasets? Inf Process Manag 12 491-190
[4] Chicco D(2018)Large scale crowdsourcing and characterization of Twitter abusive behavior ICWSM 4 155-undefined
[5] Jurman G(2018)The SFU opinion and comments corpus: a corpus for the analysis of Online news comments Corpus Pragmat undefined undefined-undefined
[6] Fortuna P(undefined)undefined undefined undefined undefined-undefined
[7] Soler-Company J(undefined)undefined undefined undefined undefined-undefined
[8] Wanner L(undefined)undefined undefined undefined undefined-undefined
[9] Founta A(undefined)undefined undefined undefined undefined-undefined
[10] Djouvas C(undefined)undefined undefined undefined undefined-undefined