Nozza@LT-EDI-ACL2022: Ensemble Modeling for Homophobia and Transphobia Detection

Nozza, Debora

doi:10.18653/v1/2022.ltedi-1.37

Cited by 5 publications

(2 citation statements)

References 26 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In one study, the ensemble transformer-based model was implemented to classify homophobia and transphobia on social media comments in Tamil and Tamil-English datasets [1]. Similarly, to classify the comments as homophobia and transphobia in English, different transformer-based models (BERT, RoBERTa and HateBERT) were implemented [2].…”

Section: Related Workmentioning

confidence: 99%

Detection of Homophobia & Transphobia in Malayalam and Tamil: Exploring Deep Learning Methods

Sharma

Gupta

Singh

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

The increase in abusive content on online social media platforms is impacting the social life of online users. Use of offensive and hate speech has been making social media toxic. Homophobia and transphobia constitute offensive comments against LGBT+ community. It becomes imperative to detect and handle these comments, to timely flag or issue a warning to users indulging in such behaviour. However, automated detection of such content is a challenging task, more so in Dravidian languages which are identified as low resource languages. Motivated by this, the paper attempts to explore applicability of different deep learning models for classification of the social media comments in Malayalam and Tamil languages as homophobic, transphobic and non-anti-LGBT+content. The popularly used deep learning models-Convolutional Neural Network (CNN), Long Short Term Memory (LSTM) using GloVe embedding and transformer-based learning models (Multilingual BERT and Indic-BERT) are applied to the classification problem. Results obtained show that In-dicBERT outperforms the other implemented models, with obtained weighted average F1-score of 0.86 and 0.77 for Malayalam and Tamil, respectively. Therefore, the present work confirms higher performance of IndicBERT on the given task in selected Dravidian languages.

show abstract

Section: Related Workmentioning

confidence: 99%

Detection of Homophobia & Transphobia in Malayalam and Tamil: Exploring Deep Learning Methods

Sharma

Gupta

Singh

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…[12] employed a RoBERTa-based approach to explore on the task [10] data. Given the substantial minority class, the authors of [13] authors proposed a method using data augmentation and ensembles modelling. They fine-tuned big linguistic models utilised the balanced democratic majority on their predictions.…”

Section: Literature Surveymentioning

confidence: 99%

Detecting homophobic and transphobic texts from youtube comments using machine learning models

Subramanian,

Sathishkumar,

Shanmugavadivel

et al. 2023

ACE

View full text Add to dashboard Cite

Today's world has witnessed an exponential rise in disseminating degrading and offensive content via social media. A global increase in violence against minorities, such as gun violence, murders, and forced displacement, has been connected to using harsh and derogatory language online. The policies enacted to prevent abusive or derogatory language risk stifling free speech and are applied differently. These languages can affect the mental state of social media users. Homophobic and transphobic expressions are a insulting people's sexuality or character among harsh and disrespectful remarks. To study social media information and discriminate between homophobic and transphobic comments, it is necessary to construct language-based automatic categorization methods. This dataset consists of Tamil YouTube comments collected as part of the Shared Task on Sentiment Analysis and Homophobia detection of YouTube comments in Code-Mixed Dravidian Languages. This study detects and categorises abusive comments using machine learning models such as SVM, Naive Bayes, Logistic regression, and KNN. In comparison to other classifiers, the accuracy of logistic regression is the highest, at 55%.

show abstract

Detection of homophobia and transphobia in YouTube comments

Chakravarthi

2023

Int J Data Sci Anal

View full text Add to dashboard Cite

Users of online platforms have negative effects on their mental health as a direct result of the spread of abusive content across social media networks. Homophobia are terms that refer to the fear, hatred, discomfort, or suspicion of or toward those who identify as homosexual or bisexual. Transphobia is fear, hatred, discomfort toward those who are transgenders. Homophobia/transphobia speechs are a sort of offensive language that can be summed up as hate speech directed toward LGBTQ+ persons, and it has become an increasing concern in recent years. The homophobia and transphobia found online are a serious societal issue that can make online platforms toxic and unwelcoming to LGBTQ+ individuals and hinder the eradication of equality, diversity, and inclusion. We present a new dataset for online homophobia and transphobia detection that has been annotated by experts, which will enable homophobic and transphobic content to be automatically recognized. The dataset includes 15,141 annotated comments written in English, Tamil, and both Tamil and English. Additionally, we provide the outcomes of our benchmark system in a variety of machine learning models. For the purpose of developing benchmark systems, we conducted a number of experiments utilizing a variety of cutting-edge machine and deep learning models. Furthermore, we discuss our shared task conducted at LTEDI-ACL 2022 workshop to improve the research in homophobia and transphobia detection. It garnered 10 systems for the Tamil language, 13 systems for the English language, and 11 systems for the combination of Tamil and English languages. The best systems for Tamil, English, and Tamil–English each received an average macro F1 score of 0.570, 0.870, and 0.610, respectively.

show abstract

Nozza@LT-EDI-ACL2022: Ensemble Modeling for Homophobia and Transphobia Detection

Cited by 5 publications

References 26 publications

Detection of Homophobia & Transphobia in Malayalam and Tamil: Exploring Deep Learning Methods

Detection of Homophobia & Transphobia in Malayalam and Tamil: Exploring Deep Learning Methods

Detecting homophobic and transphobic texts from youtube comments using machine learning models

Detection of homophobia and transphobia in YouTube comments

Contact Info

Product

Resources

About