Supervised Classifiers to Identify Hate Speech on English and Spanish Tweets

Almatarneh, Sattam; Gamallo, Pablo; Pena, Francisco José Ribadas; Alexeev, Alexey

doi:10.1007/978-3-030-34058-2_3

Cited by 14 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies have been carried out such as [7], which compared different ML classifiers to identify the hate speech focused on two targets-women and immigrants-in English and Spanish tweets. The paper shows the comparison between different ML strategies in this particular task and concludes with SVM, Complement Naive Bayes and RF clearly outperforming the other classifiers and showing stable performance across all features.…”

Section: Related Workmentioning

confidence: 99%

Comparison between Machine Learning and Deep Learning Approaches for the Detection of Toxic Comments on Social Networks

Bonetti,

Martínez-Sober,

Torres

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The way we communicate has been revolutionised by the widespread use of social networks. Any kind of online message can reach anyone in the world almost instantly. The speed with which information spreads is undoubtedly the strength of social networks, but at the same time, any user of these platforms can see how toxic messages spread in parallel with likes, comments and ratings about any person or entity. In such cases, the victim feels even more helpless and defenceless as a result of the rapid spread. For this reason, we have implemented an automatic detector of toxic messages on social media. This allows us to stop toxicity in its tracks and protect victims. In particular, the aim of the survey is to demonstrate how traditional Machine Learning methods of Natural Language Processing (NLP) work on equal terms with Deep Learning methods represented by a Transformer architecture and characterised by a higher computational cost. In particular, the paper describes the results obtained by testing different supervised Machine Learning classifiers (Logistic Regression, Random Forest and Support Vector Machine) combined with two topic-modelling techniques of NLP, (Latent Semantic Analysis and Latent Dirichlet Allocation). A pre-trained Transformer named BERTweet was also tested. All models performed well in this task, so much so that values close to or above 90% were achieved in terms of the F1 score evaluation metric. The best result achieved by Transformer BERTweet, 91.40%, was therefore not impressive in this context, as the performance gains are too small compared to the computational overhead.

show abstract

Section: Related Workmentioning

confidence: 99%

Comparison between Machine Learning and Deep Learning Approaches for the Detection of Toxic Comments on Social Networks

Bonetti,

Martínez-Sober,

Torres

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Classic supervised machine learning methods have been explored for automated hate speech detection. Among these, Support Vector Machines (SVM) (Burnap & Williams, 2015;Salminen et al, 2020), Logistic Regression (LR) (Davidson et al, 2017;Khan et al, 2021;Waseem & Hovy, 2016), Naive Bayes (NB) (Ibrohim & Budi, 2019;Salminen et al, 2020), Random Forest (RF) (Almatarneh et al, 2019), C4.5 decision tree learning (Watanabe et al, 2018). Although more expensive, ensemble approaches have presented robust results of the different classification task (Burnap & Williams, 2015;Markov et al, 2021;Nugroho et al, 2019;Paschalides et al, 2020;Zimmerman et al, 2018).…”

Section: Automatic Hate Speech Detectionmentioning

confidence: 99%

“…In Plaza-Del-Arco et al ( 2020) used TF weighting to represent unigrams and bigrams as vectors of numerical features to misogyny and xenophobia detected in Spanish tweets. Several works used TF-IDF weighting features for hate speech detection (Almatarneh et al, 2019;Elisabeth et al, 2020;Mossie & Wang, 2020;Salminen et al, 2020). The TF-IDF provided good classification performance for hate speech detection with the same dataset to train and test the models.…”

Section: Term Frequencymentioning

confidence: 99%

Exploring Automatic Hate Speech Detection on Social Media: A Focus on Content-Based Analysis

2023

View full text Add to dashboard Cite

Hate speech is a challenging problem, and its dissemination can cause potential harm to individuals and society by creating a sense of general unwelcoming to the marginalized groups, which usually are targeted. Therefore, it is essential to understand this issue and which techniques are useful for automatic detection. This paper presents a survey on automatic hate speech detection on social media, providing a structured overview of theoretical aspects and practical resources. Thus, we review different definitions of the term “hate speech” from social network platforms and the scientific community. We also present an overview of the methodologies used for hate speech detection, and we describe the main approaches currently explored in this context, including popular features, datasets, and algorithms. Furthermore, we discuss some challenges and opportunities for better solving this issue.

show abstract

“…Classic supervised machine learning methods with different techniques for feature extraction have been frequently used in the literature for hate speech detection (Almatarneh et al, 2019;Santosh & Aravind, 2019). General feature representation methods of text mining have been successfully adapted to the problem of hate speech detection, such as Bag-of-Words (BoW) (Burnap & Williams, 2016;Nobata et al, 2016), n-grams (Corazza et al, 2020;Santosh & Aravind, 2019), dictionaries or lexical resources (Gitari et al, 2015;Mathew et al, 2019), etc.…”

Section: Automatic Hate Speech Detectionmentioning

confidence: 99%

“…For the representations f 4 to f 9 , we selected traditional feature extraction methods used for hate speech detection (Almatarneh et al, 2019;Corazza et al, 2020;Elisabeth et al, 2020;Salminen et al, 2020;Senarath & Purohit, 2020;Santosh & Aravind, 2019). These methods are based on the Bag-of-Words (BoW) technique.…”

Section: Pool Generationmentioning

confidence: 99%

Unintended bias evaluation: An analysis of hate speech detection and gender bias mitigation on social media using ensemble learning

Nascimento¹,

Cavalcanti²,

Abreu³

2022

Expert Systems with Applications

View full text Add to dashboard Cite

Supervised Classifiers to Identify Hate Speech on English and Spanish Tweets

Cited by 14 publications

References 11 publications

Comparison between Machine Learning and Deep Learning Approaches for the Detection of Toxic Comments on Social Networks

Comparison between Machine Learning and Deep Learning Approaches for the Detection of Toxic Comments on Social Networks

Exploring Automatic Hate Speech Detection on Social Media: A Focus on Content-Based Analysis

Unintended bias evaluation: An analysis of hate speech detection and gender bias mitigation on social media using ensemble learning

Contact Info

Product

Resources

About