Locate the Hate: Detecting Tweets against Blacks

  title={Locate the Hate: Detecting Tweets against Blacks},
  author={Irene Kwok and Yuzhou Wang},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  • Irene Kwok, Yuzhou Wang
  • Published 29 June 2013
  • Computer Science
  • Proceedings of the AAAI Conference on Artificial Intelligence
Although the social medium Twitter grants users freedom of speech, its instantaneous nature and retweeting features also amplify hate speech. [] Key Result We apply a supervised machine learning approach, employing inexpensively acquired labeled data from diverse Twitter accounts to learn a binary classifier for the labels "racist" and "nonracist" The classifier has a 76% average accuracy on individual tweets, suggesting that with further improvements, our work can contribute data on the sources of anti…
Demographic Word Embeddings for Racism Detection on Twitter
This study presents a supervised learning strategy to detect racist language on Twitter based on word embedding that incorporate demographic information that incorporate age, gender, and location information.
Detecting hate speech on Twitter A comparative study on the naive Bayes classifier
The study shows that character level n-grams outperform word level ngrams, and the optimal size n- gram for character level is using combinations between 1-3.
Monitoring Users' Behavior: Anti-Immigration Speech Detection on Twitter
It is demonstrated that using word n-grams results in higher precision, recall, and f-score as compared to character n- grams, and the implications for future work on hate-speech detection and social media data analysis in general are discussed.
A comparison of classification algorithms for hate speech detection
The results show that the Multinomial Naive Bayes algorithm produces the best model with the highest recall value, which has an accuracy value of 71.2% for the classification of hate speech, which is recommended as the model to detect hate speech on social media.
Requiem for online harassers: Identifying racism from political tweets
This work collects tweets produced by the ego networks of the two former 2016 US Presidential Candidates: Hillary Clinton and Donald Trump, grouped in four datasets and finds the most negative and racist user and the most positive and non-racist user from all datasets.
Learning to Classify Hate and Extremism Promoting Tweets
The problem of hate and extremism promoting tweet identification as a one-class classification problem is formulated and several linguistic features are proposed that are effective and demonstrate that the proposed approach is effective.
Supervised Classifiers to Identify Hate Speech on English and Spanish Tweets
An empirical study that analyzes the influence of two types of linguistic features when they are used to feed different supervised machine learning classifiers in the process of identifying hate speech on Twitter shows that CNB, SVM, and RF are better than the rest classifier in English and Spanish languages by taking into account all features.
Modeling Hate Speech Detection in Social Media Interactions Using Bert
This paper demonstrates how fine tuning a pre-trained Google Bidirectional Encoder Representation from Transformers (BERT) model has been used to achieve an improvement in accuracy of classification of tweets as either hate speech or not.
Hate Speech in the Political Discourse on Social Media: Disparities Across Parties, Gender, and Ethnicity
It is found that tweets are particularly likely to receive hate speech in replies if they are authored by persons of color from the Democratic party, white Republicans, and women, and that negative sentiment attracts more hate speech for Democrats (vs. Republicans).
Racial Bias in Hate Speech and Abusive Language Detection Datasets
Evidence of systematic racial bias in five different sets of Twitter data annotated for hate speech and abusive language is examined, as classifiers trained on them tend to predict that tweets written in African-American English are abusive at substantially higher rates.


Detecting Hate Speech on the World Wide Web
The definition of hate speech, the collection and annotation of the hate speech corpus, and a mechanism for detecting some commonly used methods of evading common "dirty word" filters are described.
Offensive Language Detection Using Multi-level Classification
An automatic flame detection method is described which extracts features at different conceptual levels and applies multi-level classification for flame detection and there is an auxiliary weighted pattern repository which improves accuracy by matching the text to its graded entries.
Thumbs up? Sentiment Classification using Machine Learning Techniques
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
Comparing naive Bayes, decision trees, and SVM with AUC and accuracy
It is proved that AUC is, in general, a better measure (defined precisely) than accuracy for evaluating performance of learning algorithms.
In Proc
  • of the 2012 Workshop on LSM, 19-26.
  • 2012