Cyberbullying detection using probabilistic socio-textual information fusion

Singh, Vivek K.; Huang, Qianjia; Atrey, Pradeep K.

doi:10.1109/asonam.2016.7752342

Cited by 40 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main challenges in automated cyberbullying detection is the availability of cyberbullying-related data. From the datasets in TABLE 5, we can see that seven datasets contain 10% or less of cyberbullying-related (positive) samples [12], [20], [21], [78], [79], [83], [90], while only one dataset is almost balanced, with 42% positive samples and 58% negative samples [87]. Nine datasets have a percentage of positive samples between 11.7% and 29% [13], [15], [17], [53], [67], [78], [84]- [86], while the rest of the datasets contain between 30% and 39% of positive samples [8], [9], [14], [47].…”

Section: ) Data Annotationmentioning

confidence: 99%

“…The imbalance of the datasets resulted in many researchers processing the datasets in order to ensure that the trained machine learning models learn to differentiate between cyberbullying cases and non-cyberbullying-related cases. Some works over-sampled the positive samples either by duplicating the positive samples multiple times in order to balance the dataset [20], [21], while other studies did the opposite by down-sampling negative samples in the dataset [53], [55], [83]. Some studies used search keywords on the streaming APIs to filter the incoming data and make sure to get more data with offensive content [12], [13], [67].…”

Section: ) Data Samplingmentioning

confidence: 99%

“…Furthermore, the users' location has also been used as a feature [8], [16]. User features also include information related to the user's social media network, like the users' number of followers, the number of likes and views they receive, or the number of people they follow [7], [16], [83], [90].…”

Section: ) User Informationmentioning

confidence: 99%

“…Singh et al [83] proposed a method for combining text features, user features, and social media network features in a way that enhances the model's performance, by first determining the agreement score between different types of features and then determining the confidence score of certain 16 https://nlp.stanford.edu/projects/glove/ feature types by calculating their accuracy in predicting the data label (as cyberbullying or not) from previous predictions. This way the model can determine which features are more important for each data instance and consequently make better predictions of the final data label.…”

Section: ) Feature Selectionmentioning

confidence: 99%

See 3 more Smart Citations

When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection

et al. 2021

View full text Add to dashboard Cite

Web 2.0 helped user-generated platforms to spread widely. Unfortunately, it also allowed for cyberbullying to spread. Cyberbullying has negative effects that could lead to cases of depression and low self-esteem. It has become crucial to develop tools for automated cyberbullying detection. The research on developing these tools has been growing over the last decade, especially with the recent advances in machine learning and natural language processing. Given the large body of work on this topic, it is vital to critically review the literature on cyberbullying within the context of these latest advances. In this paper, we conduct a survey on the automated detection of cyberbullying. Our survey sheds light on some challenges and limitations for the field. The challenges range from defining cyberbullying, data collection and feature representation to model selection, training and evaluation. We also provide some suggestions for improving the task of cyberbullying detection. In addition to the survey, we propose to improve the task of cyberbullying detection by addressing some of the raised limitations: 1) Using recent contextual language models like BERT for the detection of cyberbullying; 2) Using slang-based word embeddings to generate better representations of the cyberbullying-related datasets. Our results show that BERT outperforms state-of-the-art cyberbullying detection models and deep learning models. The results also show that deep learning models initialised with slang-based word embeddings outperform deep learning models initialised with traditional word embeddings.

show abstract

Section: ) Data Annotationmentioning

confidence: 99%

Section: ) Data Samplingmentioning

confidence: 99%

Section: ) User Informationmentioning

confidence: 99%

Section: ) Feature Selectionmentioning

confidence: 99%

See 2 more Smart Citations

When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Authors showed that the accuracy of cyberbullying detection could be significantly improved using a Linear Support Vector Machine (SVM) classifier and by integrating multi-modal features from the picture, text, and metadata in the media session. Singh et al 31 proposed a framework to create better cyberbullying predicators by utilizing confidence score and interdependencies linked to different textual and social features. In contrast to an another approach in literature that used a similar features and dataset, the performance of the proposed approach contributed to major improvements in cyberbullying detection.…”

Section: Related Workmentioning

confidence: 99%

Cuckoo inspired stacking ensemble framework for content‐based cybercrime detection in online social networks

Singh

Kaur

2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In recent times, the topic of content-based cybercrime has gained significant attention. It is the requirement of today's era for social media companies to meet the challenges faced in differentiating the oppressive content in both a precise and proficient manner, thereby securing their clients. This article proposes a novel cuckoo inspired stacking ensemble framework that is the integration of Cuckoo Search and several machine learning models. The proposed framework automatically seeks for near-optimal combinations of classification techniques along with their tuning parameters for efficiently solving the problem of content-based cybercrime detection. Four datasets obtained from Formspring, ASKfm, and Twitter are used for testing purposes. The experimental results showcased significant improvement in the performance of classification on all the datasets in comparison to state-of-art classification models. The success rate of the proposed model with the excellent recall is 0.984 via 10-fold cross-validation demonstrates its high efficiency and effectiveness. INTRODUCTIONSocial media has evolved into a prestigious platform where people can share their emotions and has the advantage of being able to hide and perpetrate acts of violence against peers such as dating abuse, gang-related crimes, stacking, and bullying. Social media has also been used as a self-harming agent, especially cyber-suicide. 1 Young people of the 21st century cannot live without social media and the Internet-for example, Twitter, Facebook, and so on. Over 90% of young people use the Internet every day, and about 70% have active accounts on one of the social networking sites. 2,3 Verbal and face-to-face abuses are still more common than virtual abuse. Research indicates that most adolescents and children show little to no participation in abuses across social media networks (65-91%). 4,5 However, violence in the virtual world is a growing problem that requires additional research and prevention. Patchin and Hinduja 6 research shows that violence in social media and cyberbullying is becoming more and more common. The study included a random sample of 4441 teenagers aged 10-18 years from 37 schools. It was found that nearly 20% of teenagers in 2010 claimed to have been victims of cyberbullying, and 20% said that at one point in their lives they experienced bullying in cyberspace. The number of cybercrimes that have been developed and implemented on social media platforms such as Facebook is increasing. Communication on social networking sites is characterized by a higher degree of anonymity, which gives honest opportunities to increase hostility in interpersonal interactions. 7 The account of menacing, demoralization, teen pornography, University Grants Commission [No. F.159(JUNE 2014)/2014(NET)].

show abstract

Identifying Cyberbullying Post on Social Networking Platform Using Machine Learning Technique

Roy

Singh

Tripathy

et al. 2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Cyberbullying detection using probabilistic socio-textual information fusion

Cited by 40 publications

References 13 publications

When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection

When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection

Cuckoo inspired stacking ensemble framework for content‐based cybercrime detection in online social networks

Identifying Cyberbullying Post on Social Networking Platform Using Machine Learning Technique

Contact Info

Product

Resources

About