ALBERT-based fine-tuning model for cyberbullying analysis

Tripathy, Jatin Karthik; Chakkaravarthy, S. Sibi; Satapathy, Suresh Chandra; Sahoo, Madhulika; Vaidehi, V.

doi:10.1007/s00530-020-00690-5

Cited by 14 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other studies utilized CNN's to enhance the cyberbullying detection [42], [43], [44], [45], [46]. Tripathy et al [47] proposed a fine-tuning approach for detecting CB based on ALBER. Agarwal et al [7] utilized RNN based on Under-Sampling and Class Weighting.…”

Section: Related Workmentioning

confidence: 99%

DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

et al. 2022

View full text Add to dashboard Cite

Cyberbullying (CB) has become increasingly prevalent in social media platforms. With the popularity and widespread use of social media by individuals of all ages, it is vital to make social media platforms safer from cyberbullying. This paper presents a hybrid deep learning model, called DEA-RNN, to detect CB on Twitter social media network. The proposed DEA-RNN model combines Elman type Recurrent Neural Networks (RNN) with an optimized Dolphin Echolocation Algorithm (DEA) for finetuning the Elman RNN's parameters and reducing training time. We evaluated DEA-RNN thoroughly utilizing a dataset of 10000 tweets and compared its performance to those of state-of-the-art algorithms such as Bi-directional long short term memory (Bi-LSTM), RNN, SVM, Multinomial Naive Bayes (MNB), Random Forests (RF). The experimental results show that DEA-RNN was found to be superior in all the scenarios. It outperformed the considered existing approaches in detecting CB on Twitter platform. DEA-RNN was more efficient in scenario 3, where it has achieved an average of 90.45% accuracy, 89.52% precision, 88.98% recall, 89.25% F1-score, and 90.94% specificity.

show abstract

Section: Related Workmentioning

confidence: 99%

DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A slight retermed categorization is used in Davidson et al [53] and a follow-up research by Tripathy et al [37], where the provided tweets to be annotated are labelled as one of the three categories: hate speech, o ensive, or neither. Samghabadi et al [54] used three datasets, and one of them was released by Wulczyn et al [55] and labelled using the CrowdFlower website.…”

Section: Dataset Labelling and Evaluation Approachesmentioning

confidence: 99%

“…However, the BERT model comes with huge computational cost as it consists of a huge number of parameters. Tripathy et al [ 37 ] used fine-tuned ALBERT model for cyberbullying detection by using ALBERT-large, a larger pretraining corpus over the BERT-Base that Mozafari et al [ 34 ] implemented. Elsafoury et al [ 13 ] conducted experiments using BERT for cyberbullying detection in comparison to the DL models used in the literature.…”

Section: Cyberbullying Detection Approachesmentioning

confidence: 99%

“…Hosseinmardi et al [ 51 ] used five contributors (i.e., the labellers) and provided them with the images/videos to be annotated and their associated comments as well as the written definitions of cyberbullying and cyberaggression. A slight retermed categorization is used in Davidson et al [ 53 ] and a follow-up research by Tripathy et al [ 37 ], where the provided tweets to be annotated are labelled as one of the three categories: hate speech, offensive, or neither. Samghabadi et al [ 54 ] used three datasets, and one of them was released by Wulczyn et al [ 55 ] and labelled using the CrowdFlower website.…”

Section: Cyberbullying Detection Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Building towards Automated Cyberbullying Detection: A Comparative Analysis

Al-Harigy

Al-Nuaim

Moradpoor

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The increased use of social media among digitally anonymous users, sharing their thoughts and opinions, can facilitate participation and collaboration. However, this anonymity feature which gives users freedom of speech and allows them to conduct activities without being judged by others can also encourage cyberbullying and hate speech. Predators can hide their identity and reach a wide range of audience anytime and anywhere. According to the detrimental effect of cyberbullying, there is a growing need for cyberbullying detection approaches. In this survey paper, a comparative analysis of the automated cyberbullying techniques from different perspectives is discussed including data annotation, data preprocessing, and feature engineering. In addition, the importance of emojis in expressing emotions as well as their influence on sentiment classification and text comprehension leads us to discuss the role of incorporating emojis in the process of cyberbullying detection and their influence on the detection performance. Furthermore, the different domains for using self-supervised learning (SSL) as an annotation technique for cyberbullying detection are explored.

show abstract

“…Cyberbullying datasets from Twitter and Formspring.me social networking sites comprised the corpus. Tripati K et al [17] proposed an ALBERT-based fine-tuning model for cyberbullying detection; the model achieved better performance than GRU and BERT. Sayanta Paul and Sriparna Saha [18] presented an innovative method of BERT for cyberbullying identification.…”

Section: [2] Related Workmentioning

confidence: 99%

Cyberbullying detection on multi-modal data using pre-trained deep learning architectures

Pericherla

Ilavarasan

2021

ing. Solidar

View full text Add to dashboard Cite

Cyberbullying is a big challenging task in the social media era. The forms of bullying are increasing with the increase of digital technologies. In the past, most of the bullying happened through text messages. Now bullies take advantage of technology, they try bullying others in different forms such as images, videos, and emojis. In this paper, we proposed an approach to identify cyberbullying on both text and image data combinations. We used RoBERTa and Xception deep learning architectures to generate word embeddings from the text data and the image respectively. LightGBM classifier is used to classify bullying and non-bullying tweets. The experiments conducted on 2100 samples of combined data of text and image. The proposed approach efficiently classifies bullying data with F1-score of 80% and outperforms as compared to existing approaches.

show abstract

ALBERT-based fine-tuning model for cyberbullying analysis

Cited by 14 publications

References 16 publications

DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

Building towards Automated Cyberbullying Detection: A Comparative Analysis

Cyberbullying detection on multi-modal data using pre-trained deep learning architectures

Contact Info

Product

Resources

About