Targets and Aspects in Social Media Hate Speech

Shvets, A.V.; Fortuna, Paula; Soler, Juan Cerezo; Wanner, Leo

doi:10.18653/v1/2021.woah-1.19

Cited by 6 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The remark "I'm not sexist but female comedians just are not funny!" (Shvets et al, 2021) may seem relatively harmless when coming from a tweeter with few followers, but when coming from an influential critic or the president of a comedians' union, it can actively harm women's careers. Attacks on a group's morals can also have an impact beyond merely insulting.…”

Section: Discussionmentioning

confidence: 99%

Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions

Urja¹,

Vermeulen²,

Nalisnick³

et al. 2022

Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

View full text Add to dashboard Cite

Offensive Content Warning: This paper contains offensive language only for providing examples that clarify this research and do not reflect the authors' opinions. Please be aware that these examples are offensive and may cause you distress.The subjectivity of recognizing hate speech makes it a complex task. This is also reflected by different and incomplete definitions in NLP. We present hate speech criteria, developed with perspectives from law and social science, with the aim of helping researchers create more precise definitions and annotation guidelines on five aspects: (1) target groups, (2) dominance, (3) perpetrator characteristics, (4) type of negative group reference, and the (5) type of potential consequences/effects. Definitions can be structured so that they cover a more broad or more narrow phenomenon. As such, conscious choices can be made on specifying criteria or leaving them open. We argue that the goal and exact task developers have in mind should determine how the scope of hate speech is defined. We provide an overview of the properties of English datasets from hatespeechdata.com that may help select the most suitable dataset for a specific scenario.

show abstract

Section: Discussionmentioning

confidence: 99%

Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions

Urja¹,

Vermeulen²,

Nalisnick³

et al. 2022

Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

View full text Add to dashboard Cite

show abstract

“…Thus, based on the observation process and the review of literature, characteristics and limitations of social media have been extracted. Previous related studies such as the ones by Siddiqui and Singh (2016), Kapoor et al (2018), Jadhav (2020), Shvets et al (2021) and Mallick et al (2022) have been reviewed to confirm the results of the observation and construct the model on which the questionnaire was constructed.…”

Section: Observationmentioning

confidence: 99%

Does social media impact the development of general English vocabulary? perceptions of Egyptian university students

Wannas

Hassan

2023

In. Lang. Cul. & Com.

View full text Add to dashboard Cite

The importance of vocabulary in language learning cannot be overstated because meaningful communication requires a vast repertoire of words to convey ideas. Yet, social media places English language learners in multicultural communities where they can acquire new vocabulary knowledge and use it communicatively. The aim of the study is to investigate the impact of social media on learning English vocabulary at university level. A case study approach was adopted. To this end, a hypothesized model on aspects of learning English from social media was constructed. That was supported by participant observation and a thorough review of the literature. Based on the model, a questionnaire was constructed and disseminated to a total number of 135 Egyptian undergraduate university students. Findings of the study are: 1) learning vocabulary occurs through receiving, producing and constructing vocabulary knowledge, 2) the indirect impact of social media enhances self-confidence, self-esteem, critical thinking, creativity and collaboration among Egyptian university students, 3) social media is characterized by factors that enhance vocabulary learning, and 4) social media has a few limitations that, to some extent, hinder vocabulary learning. It is recommended that further research is conducted on the effect of different social media applications on learning English language vocabulary, grammar and other aspects.

show abstract

“…Based on research by the Pew Research Center in 2014, as many as 73% of adult internet users know someone is being harassed in cyberspace, and 40% have directly victims [3]. These results have sparked many studies to define post typologies that contain hate speech on social media, especially Twitter.…”

Section: Introductionmentioning

confidence: 99%

Comparison of SVM and Naïve Bayes Algorithms with InNER enriched to Predict Hate Speech

HADİ AL GHOZALİ,

PİRMAN,

INDRA

2023

ECJSE

View full text Add to dashboard Cite

Hate speech is one of the negative sides of social media abuse. Hate speech can be classified into insults, defamation, unpleasant acts, provoking, inciting, and spreading fake news (hoax). The purpose of this study is to compare the SVM and Naïve Bayes methods with feature extraction in the form of Indonesian NER (InNER) for detecting hate speech. To obtain the best model, this study applies five steps: a) data collection; b) data preprocessing; c) feature engineering; d) model development; and e) evaluating and comparing models. In this study, we have collected 7100 tweets as an initial dataset. After manual annotation, this study produced 1681 tweets: 548 insult tweets, 288 blasphemy tweets, 272 provocative tweets, and 573 neutral tweets. This study use two Python libraries that accommodate NER in Indonesian, namely the NLTK library and the Polyglot library. Based on the results of the evaluation of the proposed model, model 5, which develops the SVM algorithm with the NLTK library, is the best model proposed. This model shows an accuracy score of 92.88% with a precision of 0.93, a recall of 0.93, and an F-1 score of 0.92.

show abstract

Targets and Aspects in Social Media Hate Speech

Cited by 6 publications

References 35 publications

Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions

Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions

Does social media impact the development of general English vocabulary? perceptions of Egyptian university students

Comparison of SVM and Naïve Bayes Algorithms with InNER enriched to Predict Hate Speech

Contact Info

Product

Resources

About