2019
DOI: 10.1007/978-3-030-34058-2_3
|View full text |Cite
|
Sign up to set email alerts
|

Supervised Classifiers to Identify Hate Speech on English and Spanish Tweets

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(7 citation statements)
references
References 11 publications
0
7
0
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%
“…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%
“…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%
“…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%