Offensive language detection in Tamil YouTube comments by adapters and cross-domain knowledge transfer

Malliga, S.; Ponnusamy, Rahul; Benhur, Sean; Shanmugavadivel, Kogilvani; Ganesan, Adhithiya; Ravi, D.; Shanmugasundaram, Gowtham Krishnan; Priyadharshini, Ruba; Chakravarthi, Bharathi Raja

doi:10.1016/j.csl.2022.101404

Cited by 31 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These papers examine the use of machine learning models to predict the sentiment of new comments based on previously trained data [28]. Another literature [29] explores using NLP transformer-based models to detect offensive language in YouTube comments. It empirically establishes that these transformer-based models are more effective in detecting offensive language when compared to machine learning algorithms.…”

Section: Youtubementioning

confidence: 99%

“…For instance, one study [28] found that machine learning models trained on annotated sentiment classes accurately predicted sentiment in YouTube comments. Another study [29] empirically established that NLP transformerbased models outperformed traditional machinelearning algorithms in detecting offensive language in YouTube comments. Furthermore, research by Smith et al [30,31] demonstrated the effectiveness of deep learning models in predicting job offer chances based on video resumes uploaded to YouTube.…”

Section: Youtubementioning

confidence: 99%

See 1 more Smart Citation

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Tetteh,

Thushara

2023

Preprint

View full text Add to dashboard Cite

The advent of the internet has presented a novel paradigm for conducting consumer research and focus group investigations. Social media platforms enable organizations and entities to efficiently obtain and analyze public opinions regarding their products and services. This eliminates the need for extensive resource allocation towards traditional survey methods and information-gathering strategies. The present study investigates the potential of utilizing the YouTube platform as a valuable data source for product review analysis—our research centers on Apple Inc. and its most profitable product, the Apple iPhone. Using user feedback from review videos, we employ a lexicon-based subjectivity analysis methodology to identify statements articulating subjective viewpoints about the iPhone product. Traditional sentiment analysis methods categorize opinionated views into two broad categories: positive or negative. To assess the general market perception of the product, we employ SpaCy’s aspect extraction functionality to identify significant parts of the product that are subject to viewer critique. A BERTopic model processes the user’s text by using topic modeling techniques to extract latent themes that provide insights into the various detected characteristics. The BERTopic model has high efficiency and yields a coherence score of 69%.

show abstract

Section: Youtubementioning

confidence: 99%

Section: Youtubementioning

confidence: 99%

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Tetteh,

Thushara

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Some of the newest approaches have combined several models for improving final results [14], [15] or leveraged knowledge from other tasks using multi-task learning [16] or meta-learning [17], while other approaches have focused on a multilingual setting [18], [19]. Besides, there are continuous efforts for creating new data in new languages [14], [20].…”

Section: A Offensive Language Detectionmentioning

confidence: 99%

Offensive Language Detection in Spanish Social Media: Testing From Bag-of-Words to Transformers Models

Molero,

Pérez-Martín,

Rodrigo

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Social networks allow us to communicate with people around the world. However, some users usually take advantage of anonymity for writing offensive comments to others, which might affect those who receive offensive messages or discourage the use of these networks. However, it is impossible to manually check every message. This has promoted several proposals for automatic detection systems. Current state-of-the-art systems are based on the transformers' architecture and most of the work has been focused on the English language. However, these systems do not pay too much attention to the unbalanced nature of data, since there are fewer offensive comments than non-offensive in a real environment. Besides, these previous works have not studied the impact on the final results of pre-processing or the corpora used for pre-training the models. In this work, we propose and evaluate a series of automatic methods aimed at detecting offensive language in Spanish texts addressing the unbalanced nature of data. We test different learning models, from those based on classical Machine Learning algorithms using Bag-of-Words as data representation to those based in large language models and neural networks such as transformers, paying more attention to minor classes and the corpora used for pre-training the transformer-based models. We show how transformer-based models continue obtaining the best results, but we improved previous results by a 6,2% by adding new steps of pre-processing and using models pre-trained with Spanish social-media data, setting new state-of-the-art results.

show abstract

“…Therefore, the detection of offensive language has become an active research task in natural language processing (NLP). Offensive language can be defined as text that uses abusive slurs or derogatory terms [3]. Different forms of offensive language include hate speech, aggressive content, cyberbullying, and toxic comments.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Arabic offensive language detection with BERT-BiGRU model

Bensoltane,

Zaki

2024

Bulletin EEI

View full text Add to dashboard Cite

With the advent of Web 2.0, various platforms and tools have been developed to allow internet users to express their opinions and thoughts on diverse topics and occurrences. Nevertheless, certain users misuse these platforms by sharing hateful and offensive speeches, which has a negative impact on the mental health of internet society. Thus, the detection of offensive language has become an active area of research in the field of natural language processing. Rapidly detecting offensive language on the internet and preventing it from spreading is of great practical significance in reducing cyberbullying and self-harm behaviors. Despite the crucial importance of this task, limited work has been done in this field for nonEnglish languages such as Arabic. Therefore, in this paper, we aim to improve the results of Arabic offensive language detection without the need for laborious preprocessing or feature engineering work. To achieve this, we combine the bidirectional encoder representations from transformers (BERT) model model with a bidirectional gated recurrent unit (BiGRU) layer to further enhance the extracted context and semantic features. The experiments were conducted on the Arabic dataset provided by the SemEval 2020 Task 12. The evaluation results show the effectiveness of our model compared to the baseline and related work models by achieving a macro F1- score of 93.16%.

show abstract

Offensive language detection in Tamil YouTube comments by adapters and cross-domain knowledge transfer

Cited by 31 publications

References 12 publications

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Offensive Language Detection in Spanish Social Media: Testing From Bag-of-Words to Transformers Models

Enhancing Arabic offensive language detection with BERT-BiGRU model

Contact Info

Product

Resources

About