Prediction of Cyberbullying Incidents on the Instagram Social Network
This addresses cyberbullying, a growing issue affecting over half of American teens, by applying existing methods to new data on Instagram.
This paper tackled the problem of automatically detecting and predicting cyberbullying incidents on Instagram by collecting a dataset of images and comments, labeling it via crowdsourcing, and analyzing features like cyberaggression and image content. The result involved designing and evaluating classifiers for detection, though no concrete performance numbers are provided in the abstract.
Cyberbullying is a growing problem affecting more than half of all American teens. The main goal of this paper is to investigate fundamentally new approaches to understand and automatically detect and predict incidents of cyberbullying in Instagram, a media-based mobile social network. In this work, we have collected a sample data set consisting of Instagram images and their associated comments. We then designed a labeling study and employed human contributors at the crowd-sourced CrowdFlower website to label these media sessions for cyberbullying. A detailed analysis of the labeled data is then presented, including a study of relationships between cyberbullying and a host of features such as cyberaggression, profanity, social graph features, temporal commenting behavior, linguistic content, and image content. Using the labeled data, we further design and evaluate the performance of classifiers to automatically detect and pre- dict incidents of cyberbullying and cyberaggression.