Combining FastText and Glove Word Embedding for Offensive and Hate speech Text Detection

Badri, Nabil; Kboubi, Férihane; Chaïbi, Anja Habacha

doi:10.1016/j.procs.2022.09.132

Cited by 27 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of these models is much higher than lexicon-based methods and embedding-based approaches. In [24], authors used an ensemble model which integrates a series of features from the abusive text and user behaviours and in [26], an approach that utilized a blend of Glove and FastText word embeddings as input characteristics along with a BiGRU model, aiming to detect hate speech originating from social media platforms is introduced. After the discovery of pre-trained models such as BERT [27], a significant number of hate-speech detection methodologies adopted them as embedding as well as some research used transformer model directly for the classification [28], [29].…”

Section: B Hate Speech Detection Using Text Embedding-based Methodsmentioning

confidence: 99%

Fine-Grained Emotions Influence on Implicit Hate Speech Detection

Jafari,

Li,

Rajapaksha

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Recent years brought an exponential growth of social media which revolutionized freedom of speech but significantly increased the propagation of hate speech and hate-based activities. Therefore, constructive countermeasures are necessary to prevent escalating hateful content on online social media. Many recent works target explicit hate speech, but only a few studies have utilized multiple fused features such as sentiment, targets, and emotions as attributes to enhance the detection of hate speech. In general, sentiment features help to discern feelings such as positivity or negativity, and emotion features provide a deeper level of granularity, focusing on a more comprehensive understanding of sensitivities. The aim of this paper is to investigate the significance of incorporating fine-grained emotions as an essential feature in improving the classification of implicit hate speech. First, we analyzed emotion variations of hateful and non-hateful content and explored their major fine-grained emotion discrepancies targeting implicit hateful content. Next, we introduce a multi-task learning approach that integrates emotions and sentiment features to classify implicit expressions of hatred. To evaluate the effectiveness of our multi-task learning approach, we compared it with baseline models using single-task learning approaches. The experimental results show that our multi-task approach outperformed in classifying implicit hate speech compared to the baseline models and demonstrates that fine-grained emotional knowledge decreases the classification error across multiple implicit hate categories.

show abstract

Section: B Hate Speech Detection Using Text Embedding-based Methodsmentioning

confidence: 99%

Fine-Grained Emotions Influence on Implicit Hate Speech Detection

Jafari,

Li,

Rajapaksha

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Dhamija and Katarya [38] implemented roBERTa-based embedding and classified them by Decision Trees. Badri et al [39] trained a BiGRU classifier with a combination of FastText and Glove word embedding for hate and offensive language detection on the OLID dataset. Khan et al [42] created a system that utilizes the BiLSTM classification method to detect OL in social media comment sections, specifically in the Pashto language.…”

Section: Literature Reviewmentioning

confidence: 99%

Pars-HaO: Hate and Offensive Language Detection on Persian Tweets Using Machine Learning and Deep Learning

Karami Sheykhlan,

Abdoljabbar,

Karimpour

2023

Preprint

View full text Add to dashboard Cite

As social networks continue to gain widespread popularity, an urgent requirement arises to automatically identify and detect offensive language and hate speech. While there is a wealth of research and datasets available for English in this domain, there is currently a scarcity of research and datasets focused on identifying hate speech and offensive language in Persian text. This article introduces a 3-class dataset named Pars-HaO, consisting of 8013 tweets, to fill the gap in existing research. We collected the dataset by combining comments from pages that are more exposed to hate speech and using a keyword-based approach. Three annotators then labeled the tweets. In this study, we employed a combination of the Convolutional Neural Network (CNN) model and four widely recognized machine learning models, namely Support Vector Machine (SVM) and Logistic Regression (LR), Random Forest (RF), and Decision Tree (DT) as a baseline. Then, we compared the base models with Long Short-Term Memory(LSTM), Bidirectional LSTM (BiLSTM), and CNN models, each trained using the output of the last hidden state of Bidirectional Encoder Representations from Transformers (BERT). Experimental results on the Pars HaO dataset demonstrated that the BERT with BiLSTM technique yielded the best outcome, achieving a macro F1-score of 70%.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Pars-HaO: Hate and Offensive Language Detection on Persian Tweets Using Machine Learning and Deep Learning

Karami Sheykhlan,

Abdoljabbar,

Karimpour

2023

Preprint

View full text Add to dashboard Cite

As social networks continue to gain widespread popularity, an urgent requirement arises to automatically identify and detect offensive language and hate speech. While there is a wealth of research and datasets available for English in this domain, there is currently a scarcity of research and datasets focused on identifying hate speech and offensive language in Persian text. This article introduces a 3-class dataset named Pars-HAO, consisting of 8013 tweets, to fill the gap in existing research. We collected the dataset by combining comments from pages that are more exposed to hate speech and using a keyword-based approach. Three annotators then labeled the tweets. In this study, we employed a combination of the Convolutional Neural Network (CNN) model and two widely recognized machine learning models, namely Support Vector Machine (SVM) and Logistic Regression (LR), as a baseline. To improve the classification performance, we employed the Hard Voting ensemble learning technique. Experimental results on the Pars-HAO dataset demonstrated that the Hard voting ensemble learning technique yielded the best outcome, achieving a macro F1-score of 68.76%.

show abstract

Combining FastText and Glove Word Embedding for Offensive and Hate speech Text Detection

Cited by 27 publications

References 17 publications

Fine-Grained Emotions Influence on Implicit Hate Speech Detection

Fine-Grained Emotions Influence on Implicit Hate Speech Detection

Pars-HaO: Hate and Offensive Language Detection on Persian Tweets Using Machine Learning and Deep Learning

Pars-HaO: Hate and Offensive Language Detection on Persian Tweets Using Machine Learning and Deep Learning

Contact Info

Product

Resources

About