A Detailed Survey On Cyberbullying in Social Networks

Krithika, V.; Priya, V.

doi:10.1109/ic-etite47903.2020.031

Cited by 5 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When new inputs are mapped into the space, they are assigned to the corresponding class by determining the space. In real-life problems, a hyperplane cannot be always a linear seperator [27]. Kernels are implemented in SVM to turn the function space, incase the dataset is seperable by non-linear boundaries.…”

Section: E[p R(error)] ≤ E[numberof Supportvectors] Numberof Training...mentioning

confidence: 99%

“…SVM is used in predicting cyberbullying and is shown to be efficient and effective [5]. SVM has proven to be efficient in terms of binary classification [27]. However, with the increase in the size of the dataset, SVM may not be idle, as it has to deal with vagueness in the language associated with cyberbullying.…”

Section: E[p R(error)] ≤ E[numberof Supportvectors] Numberof Training...mentioning

confidence: 99%

“…The usage of social media platforms such as Facebook, Whatsapp, Twitter, and Instagram had increased over the past years [27]. A huge amount of data is transferred through these platforms among users which also includes obfuscated content and hateful words.…”

Section: Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Cyberbullying Detection using Ensemble Method

Puthenveedu¹

View full text Add to dashboard Cite

show abstract

Section: E[p R(error)] ≤ E[numberof Supportvectors] Numberof Training...mentioning

confidence: 99%

Section: E[p R(error)] ≤ E[numberof Supportvectors] Numberof Training...mentioning

confidence: 99%

See 1 more Smart Citation

Cyberbullying Detection using Ensemble Method

Puthenveedu¹

View full text Add to dashboard Cite

show abstract

“…ey analysed 27 research studies regarding datasets and platform, feature engineering, and the classifiers used for detecting both abuse and cyberbullying. Krithika and Priya [16] discussed different datasets used for cyberbullying detection from different platforms.…”

Section: Introductionmentioning

confidence: 99%

“…They analysed 27 research studies regarding datasets and platform, feature engineering, and the classifiers used for detecting both abuse and cyberbullying. Krithika and Priya [ 16 ] discussed different datasets used for cyberbullying detection from different platforms. They also compared the different classifiers and feature extractions techniques used with the platform for both text and images.…”

Section: Introductionmentioning

confidence: 99%

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