Share This Author
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter
A list of criteria founded in critical race theory is provided, and these are used to annotate a publicly available corpus of more than 16k tweets and present a dictionary based the most indicative words in the data.
Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter
- Zeerak Waseem
- Computer ScienceNLP+CSS@EMNLP
- 1 November 2016
It is found that amateur annotators are more likely than expert annotators to label items as hate speech, and that systems training on expert annotations outperform systems trained on amateur annotations.
Understanding Abuse: A Typology of Abusive Language Detection Subtasks
A typology that captures central similarities and differences between subtasks is proposed and the implications of this for data annotation and feature construction are discussed.
HateCheck: Functional Tests for Hate Speech Detection Models
- Paul Röttger, B. Vidgen, Dong Nguyen, Zeerak Waseem, H. Margetts, J. Pierrehumbert
- Computer ScienceACL
- 31 December 2020
HateCheck, a suite of functional tests for hate speech detection models that specifies 29 model functionalities motivated by a review of previous research and a series of interviews with civil society stakeholders, is introduced.
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection
This work provides a new dataset of 40,000 entries, generated and labelled by trained annotators over four rounds of dynamic data creation, and shows that model performance is substantially improved using this approach.
Detecting East Asian Prejudice on Social Media
A new dataset and the creation of a machine learning classifier that categorizes social media posts from Twitter into four classes: Hostility against East Asia, Criticism of EastAsia, Meta-discussions of East Asian prejudice, and a neutral class are reported.
Dynabench: Rethinking Benchmarking in NLP
It is argued that Dynabench addresses a critical need in the community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios.
Bridging the Gaps: Multi Task Learning for Domain Transfer of Hate Speech Detection
This paper investigates methods for bridging differences in annotation and data collection of abusive language tweets such as different annotation schemes, labels, or geographic and cultural influences from data sampling, and considers three distinct sets of annotations.
Disembodied Machine Learning: On the Illusion of Objectivity in NLP
This opinion paper argues that addressing and mitigating biases is near-impossible, because both data and ML models are objects for which meaning is made in each step of the development pipeline, from data selection over annotation to model training and analysis.
Using TF-IDF n-gram and Word Embedding Cluster Ensembles for Author Profiling
This system employs an ensemble of two probabilistic classifiers: a Logistic regression classifier trained on TF-IDF transformed n-grams and a Gaussian Process classifiertrained on word embedding clusters derived for an additional, external corpus of tweets.