A Review of Automated Detection Methods for Cyberbullying

Mahlangu, Thabo; Tu, Chunling; Owolawi, Pius A.

doi:10.1109/iconic.2018.8601278

Cited by 18 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three main reasons underlying the popularity of this algorithm in this field can be retrieved: i. cyberbullying outcomes are commonly operationalized as binary outcomes (e.g., bullied or not bullied) as shown by previous research [66,67,68]; ii. Rosa et al quantitively demonstrated that the SVM is the best performing algorithm by supporting its use in cyberbullying detection [64]; iii. the applicability to linear and non-linear data distributions represents a remarkable advantage of this algorithm.…”

Section: B Main Algorithmsmentioning

confidence: 96%

“…Six of the selected reviews reported the Support Vector Machine (SVM) algorithm to be the most used ML algorithm in cyberbullying detection [55,56,57,58,60,64]. In this model, data points are separated by a hyperplane fitting the model in a way that two distinct classes are identified.…”

Section: B Main Algorithmsmentioning

confidence: 99%

“…In contrast, accuracy, sensitivity, and specificity are metrics commonly used for classification problems (i.e., models containing categorical outcomes), such as the case of cyberbullyingoften operationalized as a categorical variable. Given the classificatory nature of models predicting cyberbullying, evaluation metrics of classification models are the most applied in this field [55,57,64]. In detail, three of the selected reviews consistently reported four frequently used metrics, that are accuracy, precision, recall, and F1 score.…”

Section: Main Metrics Fig 4 Main Algorithms and Evaluation Metricmentioning

confidence: 99%

“…Accordingly, the F1 score is a more comprehensive metric that includes both recall and precision information. Rosa et al stated indeed that, despite the relevance of recall as a key-metric in cyberbullying detection, the F1 score is the most balanced way to evaluate cyberbullying classification algorithms [64].…”

Section: Main Metrics Fig 4 Main Algorithms and Evaluation Metricmentioning

confidence: 99%

“…In this sense, these algorithms may lead to the development of applications, usable by school staff, able to detect suspicious interactions or contents, and immediately warns school leaders and counselors. Rosa et al also stressed the importance of using ML algorithms for prevention purposes, by focusing on the need to integrate digital tools (e.g., applications, games, and websites) in social networks to prevent cyberbullying [64]. These systems should be improved at detecting cyberbullying at its earliest stage, by preventing cyberbullies from reaching their target [64].…”

Section: ML and Links To Preventionmentioning

confidence: 99%

See 4 more Smart Citations

Cyberbullying Detection Through Machine Learning: Can Technology Help to Prevent Internet Bullying?

Angelis*¹,

Perasso²

2020

IJMH

View full text Add to dashboard Cite

Cyberbullying constitutes a threat to adolescents’ psychosocial wellbeing that developed alongside technological progress. Detecting online bullying cases is still an issue because most of victims and bystanders do not timely report cyberbullying episodes to adults. Therefore, automatized technologies may play a critical role in detecting cyberbullying through the use of Machine Learning (ML). ML covers a broad range of techniques that enables systems to quickly access and learn from data, and to make decisions about complex problems. This contribution aims at deepening the role of ML in cyberbullying detection and prevention. Specifically, the following issues are addressed: i. identifying the features most frequently considered to develop ML models predicting cyberbullying; ii. identifying the most used ML algorithms and their evaluation methods; iii. understanding the implication of ML for prevention; iv. highlighting the main theoretical and methodological issues of ML algorithms in predicting cyberbullying. To answer these research questions, a systematic review of literature reviews, from a total of n=186 records from online databanks, has been conducted. Ten literature reviews have been elected to analyze and discuss evidence about ML preventative potential against cyberbullying. Most of the models used content-based features to predict cyberbullying. The majority of these features includes words written in social network posts, whereas Support Vector Machine, Naïve Bayes, and Convolutional Neural Networks are the most used alghorithms. Methodological and technical issues have been critically discussed. ML represents an innovative preventative strategy that may optimize and integrate educational programs for adolescents and be the starting point of the development of technology-based automatized detection strategies. Future research is challenged to develop algorithms capable of detecting cyberbullying from several multimedia sources.

show abstract

Section: B Main Algorithmsmentioning

confidence: 96%