Automatic Detection of Cyberbullying in Social Media Text

Cynthia Van Hee, Gilles Jacobs, Chris Emmery, Bart Desmet, Els Lefever, Ben Verhoeven, Guy De Pauw, W.M.P. Daelemans, Veronique Hoste

Research output: Working paperOther research output

Abstract

While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a training corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for this particular task. Experiments on a holdout test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1-score of 64% and 61% for English and Dutch respectively, and considerably outperforms baseline systems based on keywords and word unigrams.
Original languageEnglish
Number of pages21
Publication statusE-pub ahead of print - 17 Jan 2018

Fingerprint

Intelligent systems
Support vector machines
Classifiers
Experiments
Communication

Cite this

Van Hee, C., Jacobs, G., Emmery, C., Desmet, B., Lefever, E., Verhoeven, B., ... Hoste, V. (2018). Automatic Detection of Cyberbullying in Social Media Text.
Van Hee, Cynthia ; Jacobs, Gilles ; Emmery, Chris ; Desmet, Bart ; Lefever, Els ; Verhoeven, Ben ; De Pauw, Guy ; Daelemans, W.M.P. ; Hoste, Veronique. / Automatic Detection of Cyberbullying in Social Media Text. 2018.
@techreport{1d306c54e4cd4669a65aa3eb4af7a56a,
title = "Automatic Detection of Cyberbullying in Social Media Text",
abstract = "While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a training corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for this particular task. Experiments on a holdout test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1-score of 64{\%} and 61{\%} for English and Dutch respectively, and considerably outperforms baseline systems based on keywords and word unigrams.",
author = "{Van Hee}, Cynthia and Gilles Jacobs and Chris Emmery and Bart Desmet and Els Lefever and Ben Verhoeven and {De Pauw}, Guy and W.M.P. Daelemans and Veronique Hoste",
year = "2018",
month = "1",
day = "17",
language = "English",
type = "WorkingPaper",

}

Van Hee, C, Jacobs, G, Emmery, C, Desmet, B, Lefever, E, Verhoeven, B, De Pauw, G, Daelemans, WMP & Hoste, V 2018 'Automatic Detection of Cyberbullying in Social Media Text'.

Automatic Detection of Cyberbullying in Social Media Text. / Van Hee, Cynthia; Jacobs, Gilles; Emmery, Chris; Desmet, Bart; Lefever, Els; Verhoeven, Ben; De Pauw, Guy; Daelemans, W.M.P.; Hoste, Veronique.

2018.

Research output: Working paperOther research output

TY - UNPB

T1 - Automatic Detection of Cyberbullying in Social Media Text

AU - Van Hee, Cynthia

AU - Jacobs, Gilles

AU - Emmery, Chris

AU - Desmet, Bart

AU - Lefever, Els

AU - Verhoeven, Ben

AU - De Pauw, Guy

AU - Daelemans, W.M.P.

AU - Hoste, Veronique

PY - 2018/1/17

Y1 - 2018/1/17

N2 - While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a training corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for this particular task. Experiments on a holdout test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1-score of 64% and 61% for English and Dutch respectively, and considerably outperforms baseline systems based on keywords and word unigrams.

AB - While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a training corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for this particular task. Experiments on a holdout test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1-score of 64% and 61% for English and Dutch respectively, and considerably outperforms baseline systems based on keywords and word unigrams.

M3 - Working paper

BT - Automatic Detection of Cyberbullying in Social Media Text

ER -

Van Hee C, Jacobs G, Emmery C, Desmet B, Lefever E, Verhoeven B et al. Automatic Detection of Cyberbullying in Social Media Text. 2018 Jan 17.