Experts and machines united against cyberbullying

Dadvar, Maral

doi:10.3990/1.9789036537391

Cited by 10 publications

(10 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown by scholars such as Cowie (2013) and Price and Dalgleish (2010), the negative effects of cyberbullying include a lower self-esteem, worse academic achievement, feelings like sadness, anger, fear, depression, and-in extreme cases-cyberbullying could lead to self-harm and suicidal thoughts. As a response to these threats, automated cyberbullying detection has received increased interest resulting in several detection systems (Dinakar et al 2012;Dadvar 2014;Van Hee et al 2015b;Chen, Mckeever, and Delany 2017) and sociological studies investigating the desirability of online monitoring tools (Tucker 2010;Van Royen, Poels, and Vandebosch 2016). In fact, social media users, and specifically teenagers, highly value their privacy and autonomy on social media platforms and underline that priorities must be set related to the detection of harmful content (Van Royen et al 2016).…”

Section: Related Researchmentioning

confidence: 99%

“…Although some studies have investigated rule-based approaches (Reynolds, Kontostathis, and Edwards 2011), the dominant approach to cyberbullying detection involves machine learning, mostly based on supervised (Dinakar, Reichart, and Lieberman 2011;Dadvar 2014) or semisupervised learning (Nahar et al 2014). The former constructs a classifier using labeled training data, whereas semi-supervised approaches rely on classifiers that are built from a small set of labeled and a large set of unlabeled instances.…”

Section: Automated Detection and Analysis Of Cyberbullyingmentioning

confidence: 99%

“…Similar features were also exploited for the detection of fine-grained cyberbullying categories (Van Hee et al 2015b). Studies have also demonstrated the benefits of combining such content-based features with user-based information including previous posts, the user's age, gender, location, number of friends and followers, and so on (Dadvar 2014;Nahar et al 2014;Al-Garadi, Varathan, and Ravana 2016;Chatzakou et al 2017). Recently, deep neural network (DNN) models have also been applied to cyberbullying (Zhang et al 2016;Zhao and Mao 2017;Agrawal and Awekar 2018); in case of comparison with traditional machine learning methods in benchmarking tasks, they currently seem to slightly outperform or perform on par with classifiers like support vector machine (SVM) and even random forest and logistic regression (LR) (Zhang et al 2016;Kumar et al 2018;Emmery et al 2019;Basile et al 2019).…”

Section: Automated Detection and Analysis Of Cyberbullyingmentioning

confidence: 99%

See 2 more Smart Citations

Automatic classification of participant roles in cyberbullying: Can we detect victims, bullies, and bystanders in social media text?

2020

View full text Add to dashboard Cite

Successful prevention of cyberbullying depends on the adequate detection of harmful messages. Given the impossibility of human moderation on the Social Web, intelligent systems are required to identify clues of cyberbullying automatically. Much work on cyberbullying detection focuses on detecting abusive language without analyzing the severity of the event nor the participants involved. Automatic analysis of participant roles in cyberbullying traces enables targeted bullying prevention strategies. In this paper, we aim to automatically detect different participant roles involved in textual cyberbullying traces, including bullies, victims, and bystanders. We describe the construction of two cyberbullying corpora (a Dutch and English corpus) that were both manually annotated with bullying types and participant roles and we perform a series of multiclass classification experiments to determine the feasibility of text-based cyberbullying participant role detection. The representative datasets present a data imbalance problem for which we investigate feature filtering and data resampling as skew mitigation techniques. We investigate the performance of feature-engineered single and ensemble classifier setups as well as transformer-based pretrained language models (PLMs). Cross-validation experiments revealed promising results for the detection of cyberbullying roles using PLM fine-tuning techniques, with the best classifier for English (RoBERTa) yielding a macro-averaged ${F_1}$ -score of 55.84%, and the best one for Dutch (RobBERT) yielding an ${F_1}$ -score of 56.73%. Experiment replication data and source code are available at https://osf.io/nb2r3.

show abstract

Section: Related Researchmentioning

confidence: 99%

Section: Automated Detection and Analysis Of Cyberbullyingmentioning

confidence: 99%

Section: Automated Detection and Analysis Of Cyberbullyingmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of participant roles in cyberbullying: Can we detect victims, bullies, and bystanders in social media text?

2020

View full text Add to dashboard Cite

show abstract

“…x YouTube 449 4177 [16] .640 [9] [] BRT TWI v Twitter 220 5162 [9] .726 [9] [] BRT TW2 v Twitter 194 2599 [9] .719 [24] [] AMI ASK v Ask.fm 3787 86419 [24] .465 [27] [12]…”

Section: Binary Classificationmentioning

confidence: 99%

Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity

Emmery,

Verhoeven,

De Pauw

et al. 2019

Preprint

View full text Add to dashboard Cite

The detection of online cyberbullying has seen an increase in societal importance, popularity in research, and available open data. Nevertheless, while computational power and affordability of resources continue to increase, the access restrictions on high-quality data limit the applicability of state-of-the-art techniques. Consequently, much of the recent research uses small, heterogeneous datasets, without a thorough evaluation of applicability. In this paper, we further illustrate these issues, as we (i) evaluate many publicly available resources for this task and demonstrate difficulties with data collection. These predominantly yield small datasets that fail to capture the required complex social dynamics and impede direct comparison of progress. We (ii) conduct an extensive set of experiments that indicate a general lack of cross-domain generalization of classifiers trained on these sources, and openly provide this framework to replicate and extend our evaluation criteria. Finally, we (iii) present an effective crowdsourcing method: simulating real-life bullying scenarios in a lab setting generates plausible data that can be effectively used to enrich real data. This largely circumvents the restrictions on data that can be collected, and increases classifier performance. We believe these contributions can aid in improving the empirical practices of future research in the field.

show abstract

“…We expand our work by re-implementing the models on a new dataset. For this purpose, we have used a YouTube dataset which has been extensively used in cyberbullying studies [6], [15], [16]. The ultimate aim was to investigate the interoperability and the performance of the reproduced models on new datasets, to see how adaptable they are to different social media platforms and to what extent models trained on a dataset (i.e., social network) can be transferred to another one.…”

Section: Introductionmentioning

confidence: 99%

Cyberbullying Detection in Social Networks Using Deep Learning Based Models

Dadvar

Eckert

2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Cyberbullying is a disturbing online misbehaviour with troubling consequences. It appears in different forms, and in most of the social networks, it is in textual format. Automatic detection of such incidents requires intelligent systems. Most of the existing studies have approached this problem with conventional machine learning models and the majority of the developed models in these studies are adaptable to a single social network at a time. In recent studies, deep learning based models have found their way in the detection of cyberbullying incidents, claiming that they can overcome the limitations of the conventional models, and improve the detection performance. In this paper, we investigate the findings of a recent literature in this regard. We successfully reproduced the findings of this literature and validated their findings using the same datasets, namely Wikipedia, Twitter, and Formspring, used by the authors. Then we expanded our work by applying the developed methods on a new YouTube dataset (~54k posts by ~4k users) and investigated the performance of the models in new social media platforms. We also transferred and evaluated the performance of the models trained on one platform to another platform. Our findings show that the deep learning based models outperform the machine learning models previously applied to the same YouTube dataset. We believe that the deep learning based models can also benefit from integrating other sources of information and looking into the impact of profile information of the users in social networks.

show abstract

Experts and machines united against cyberbullying

Cited by 10 publications

References 105 publications

Automatic classification of participant roles in cyberbullying: Can we detect victims, bullies, and bystanders in social media text?

Automatic classification of participant roles in cyberbullying: Can we detect victims, bullies, and bystanders in social media text?

Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity

Cyberbullying Detection in Social Networks Using Deep Learning Based Models

Contact Info

Product

Resources

About