Ralf Krestel

• About Me
• Publications
  • Book Chapters
  • Journal Articles
    • DMKD 21
    • WPI 21
    • JLCL 20
    • ARTI 20
    • DBS 19
    • DTA 19
    • NAR 17
    • DBS 17
    • TCDL 16
    • SMR 16
    • NN 15
    • NLE 14
    • IR 12
    • NEURO 12
    • IR 10
    • IS 10
  • Conference Papers
  • Workshop Papers
  • Posters & Demos
  • Proceedings
  • Others
• Travels

JLCL 20

Explaining Offensive Language Detection

Abstract

Machine learning approaches have proven to be on or even above human-level accuracy for the task of offensive language detection. In contrast to human experts, however, they often lack the capability of giving explanations for their decisions. This article compares four different approaches to make offensive language detection explainable: an interpretable machine learning model (naive Bayes), a model-agnostic explainability method (LIME), a model-based explainability method (LRP), and a self-explanatory model (LSTM with an attention mechanism). Three different classification methods: SVM, naive Bayes, and LSTM are paired with appropriate explanation methods. To this end, we investigate the trade-off between classification performance and explainability of the respective classifiers. We conclude that, with the appropriate explanation methods, the superior classification performance of more complex models is worth the initial lack of explainability.

Full Paper

JLCL20.pdf

BibTex Entry

@article{krestel-jlcl20, author = {Risch, Julian and Ruff, Robin and Krestel, Ralf}, journal = {Journal for Language Technology and Computational Linguistics}, title = {Explaining Offensive Language Detection}, year = {2020}, volume={tbd}, number={tbd}, issn={2190-6858}, note={GSCL} }