Anatomy of Online Hate: Developing a Taxonomy and Machine Learning Models for Identifying and Classifying Hate in Online News Media

By Joni O. Salminen, Hind Almerekhi, Milica Milenkovic, Soon-gyo Jung, Jisun An, Haewoon Kwak, Bernard Jim Jansen. 2018

190 citations recorded by the source corpus.

Online social media platforms generally attempt to mitigate hateful expressions, as these comments can be detrimental to the health of the community. However, automatically identifying hateful comments can be challenging. We manually label 5,143 hateful expressions posted to YouTube and Facebook videos among a dataset of 137,098 comments from an online news media. We then create a granular taxonomy of different types and targets of online hate and train machine learning models to automatically detect and classify the hateful comments in the full dataset. Our contribution is twofold: 1) creating a granular taxonomy for hateful online comments that includes both types and targets of hateful comments, and 2) experimenting with machine learning, including Logistic Regression, Decision Tree, Random Forest, Adaboost, and Linear SVM, to generate a multiclass, multilabel classification model that automatically detects and categorizes hateful comments in the context of online news media. We find that the best performing model is Linear SVM, with an average F1 score of 0.79 using TF-IDF features. We validate the model by testing its predictive ability, and, relatedly, provide insights on distinct types of hate speech taking place on social media.

Subfields: Artificial Intelligence, Communication, Information Systems, Natural Language Processing, Safety, Robustness & Interpretability

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 Communication

In Information Systems

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

HateCheck: Functional Tests for Hate Speech Detection Models (2020, neutral): “Other work has further differentiated between different types of hate and non-hate (e.g. Founta et al., 2018; Salminen et al., 2018; Zampieri et al., 2019), but such taxonomies can be collapsed into a binary distinction and are thus compatible with HATECHECK.”
Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech (2023, background): “Hate Speech Explanation Generation To hinder the spread of toxic speech among online social platforms, researchers developed machine learning models in recent years [2, 5, 16].”
Challenges and frontiers in abusive content detection (2019, background): “One consideration is who the system detects abuse for; that is, who actually receives abuse (Salminen et al., 2018).”
Chain of Explanation: New Prompting Method to Generate Quality Natural Language Explanation for Implicit Hate Speech (2022, background): “Natural language processing has shown to be a powerful tool to accurately and efficiently detect hateful speech on online social platforms [23].”
Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases (2021, background): “Prior work has also explored sophisticated feature representations including n-grams, linguistic and syntactic features (Nobata et al., 2016), TFIDF (Salminen et al., 2018), Bag of Words and word embeddings (Djuric et al., 2015), as well as content-specific features such as mentions, proper nouns, n”
Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, background): “Salminen et al. (2018) suggest ﬁne-grained annotation schemes for deeper understanding of abuse; they propose 29 categories that include both types of abuse and their targets (e.g., humiliation, religion).”
Developing an online hate classifier for multiple social media platforms (2020, methodology): “[5] find media and police to be major targets of hate in online news commenting.”
Online Hate Ratings Vary by Extremes: A Statistical Analysis (2019, background): “In previous research, toxicity has been seen conceptually equivalent to online hate [16].”
Predicting Anti-Asian Hateful Users on Twitter during COVID-19 (2021, background): “, 2018), YouTube (Salminen et al., 2018), online games (Kwak et al.”
Detecting weak and strong Islamophobic hate speech on social media (2018, background): “(Salminen et al., 2018, p. 331) Most existing research into multi-class classification has focused on distinguishing between different targets of hate rather than different strengths (Burnap & Williams, 2016; Park & Fung, 2017; Saleem, Dillon, Benesch, & Ruths, 2017; Salminen et al., 2018; Silva,…”
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse (2019, background): “These categories of abuse and the importance of community norms have been noted elsewhere (Liu et al., 2018; Guberman and Hemphill, 2017; Salminen et al., 2018; Blackwell et al., 2017) but have not yet received the same level of attention in NLP.”