Content-driven detection of cyberbullying on the instagram social network

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We study detection of cyberbullying in photosharing networks, with an eye on developing earlywarning mechanisms for the prediction of posted images vulnerable to attacks. Given the overwhelming increase in media accompanying text in online social networks, we investigate use of posted images and captions for improved detection of bullying in response to shared content. We validate our approaches on a dataset of over 3000 images along with peer-generated comments posted on the Instagram photo-sharing network, running comprehensive experiments using a variety of classifiers and feature sets. In addition to standard image and text features, we leverage several novel features including topics determined from image captions and a pretrained convolutional neural network on image pixels. We identify the importance of these advanced features in assisting detection of cyberbullying in posted comments. We also provide results on classification of images and captions themselves as potential targets for cyberbullies.

Original languageEnglish (US)
Pages (from-to)3952-3958
Number of pages7
JournalIJCAI International Joint Conference on Artificial Intelligence
Volume2016-January
StatePublished - 2016

Fingerprint

Classifiers
Pixels
Neural networks
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

@article{3a74f8f5d5dc4667a074dc26009facbd,
title = "Content-driven detection of cyberbullying on the instagram social network",
abstract = "We study detection of cyberbullying in photosharing networks, with an eye on developing earlywarning mechanisms for the prediction of posted images vulnerable to attacks. Given the overwhelming increase in media accompanying text in online social networks, we investigate use of posted images and captions for improved detection of bullying in response to shared content. We validate our approaches on a dataset of over 3000 images along with peer-generated comments posted on the Instagram photo-sharing network, running comprehensive experiments using a variety of classifiers and feature sets. In addition to standard image and text features, we leverage several novel features including topics determined from image captions and a pretrained convolutional neural network on image pixels. We identify the importance of these advanced features in assisting detection of cyberbullying in posted comments. We also provide results on classification of images and captions themselves as potential targets for cyberbullies.",
author = "Haoti Zhong and Hao Li and Anna Squicciarini and Sarah Rajtmajer and Christopher Griffin and Miller, {David Jonathan} and Cornelia Caragea",
year = "2016",
language = "English (US)",
volume = "2016-January",
pages = "3952--3958",
journal = "IJCAI International Joint Conference on Artificial Intelligence",
issn = "1045-0823",

}

TY - JOUR

T1 - Content-driven detection of cyberbullying on the instagram social network

AU - Zhong, Haoti

AU - Li, Hao

AU - Squicciarini, Anna

AU - Rajtmajer, Sarah

AU - Griffin, Christopher

AU - Miller, David Jonathan

AU - Caragea, Cornelia

PY - 2016

Y1 - 2016

N2 - We study detection of cyberbullying in photosharing networks, with an eye on developing earlywarning mechanisms for the prediction of posted images vulnerable to attacks. Given the overwhelming increase in media accompanying text in online social networks, we investigate use of posted images and captions for improved detection of bullying in response to shared content. We validate our approaches on a dataset of over 3000 images along with peer-generated comments posted on the Instagram photo-sharing network, running comprehensive experiments using a variety of classifiers and feature sets. In addition to standard image and text features, we leverage several novel features including topics determined from image captions and a pretrained convolutional neural network on image pixels. We identify the importance of these advanced features in assisting detection of cyberbullying in posted comments. We also provide results on classification of images and captions themselves as potential targets for cyberbullies.

AB - We study detection of cyberbullying in photosharing networks, with an eye on developing earlywarning mechanisms for the prediction of posted images vulnerable to attacks. Given the overwhelming increase in media accompanying text in online social networks, we investigate use of posted images and captions for improved detection of bullying in response to shared content. We validate our approaches on a dataset of over 3000 images along with peer-generated comments posted on the Instagram photo-sharing network, running comprehensive experiments using a variety of classifiers and feature sets. In addition to standard image and text features, we leverage several novel features including topics determined from image captions and a pretrained convolutional neural network on image pixels. We identify the importance of these advanced features in assisting detection of cyberbullying in posted comments. We also provide results on classification of images and captions themselves as potential targets for cyberbullies.

UR - http://www.scopus.com/inward/record.url?scp=85006115794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006115794&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85006115794

VL - 2016-January

SP - 3952

EP - 3958

JO - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

SN - 1045-0823

ER -