Machine Learning Suites for Online Toxicity Detection

By David A. Noever. 2018

35 citations recorded by the source corpus.

To identify and classify toxic online commentary, the modern tools of data science transform raw text into key features from which either thresholding or learning algorithms can make predictions for monitoring offensive conversations. We systematically evaluate 62 classifiers representing 19 major algorithmic families against features extracted from the Jigsaw dataset of Wikipedia comments. We compare the classifiers based on statistically significant differences in accuracy and relative execution time. Among these classifiers for identifying toxic comments, tree-based algorithms provide the most transparently explainable rules and rank-order the predictive contribution of each feature. Among 28 features of syntax, sentiment, emotion and outlier word dictionaries, a simple bad word list proves most predictive of offensive commentary.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack (2019, methodology): “Many approaches have been taken to solve these tasks – from linear regression and SVMs to deep learning (Noever, 2018).”
Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection (2019, background): “Current research involves investigating common challenges in toxic comment classiﬁcation (van Aken et al. 2018), identifying subtle forms of toxicity (Noever 2018), detecting early signs of toxicity (Zhang et al. 2018), and analysing sarcasm within conversations (Ghosh, Fabbri, and Muresan 2018).”
COLD: A Benchmark for Chinese Offensive Language Detection (2022, background): “tial role in maintaining social platforms and promoting civilized communication (Davidson et al., 2017; Noever, 2018; Dinan et al., 2019; Jahan and Oussalah, 2021).”
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse (2019, background): “sage are offensive (Carton et al., 2018; Noever, 2018), and work on paraphrase and style transfer for suggesting an appropriate inoffensive alternative (Santos et al.”