Robust cyberbullying detection with causal interpretation

Lu Cheng, Ruocheng Guo, Huan Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Cyberbullying poses serious threats to preteens and teenagers, therefore, understanding the incentives behind cyberbullying is critical to prevent its happening and mitigate the impact. Most existing work towards cyberbullying detection has focused on the accuracy, and overlooked causes of the outcome. Discovering the causes of cyberbullying from observational data is challenging due to the existence of confounders, variables that can lead to spurious causal relationships between covariates and the outcome. This work studies the problem of robust cyberbullying detection with causal interpretation and proposes a principled framework to identify and block the influence of the plausible confounders, i.e., p-confounders. The de-confounded model is causally interpretable and is more robust to the changes in data distribution. We test our approach using the state-of-the-art evaluation method, causal transportability. The experimental results corroborate the effectiveness of our proposed algorithm. The purpose of this study is to provide a computational means to understanding cyberbullying behavior from observational data. This improves our ability to predict and to facilitate effective strategies or policies to proactively mitigate the impact of cyberbullying.

Original languageEnglish (US)
Title of host publicationThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages169-175
Number of pages7
ISBN (Electronic)9781450366755
DOIs
StatePublished - May 13 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: May 13 2019May 17 2019

Publication series

NameThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
CountryUnited States
CitySan Francisco
Period5/13/195/17/19

Keywords

  • Causality
  • Cyberbullying detection
  • Social media

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Cheng, L., Guo, R., & Liu, H. (2019). Robust cyberbullying detection with causal interpretation. In The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019 (pp. 169-175). (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308560.3316503

Robust cyberbullying detection with causal interpretation. / Cheng, Lu; Guo, Ruocheng; Liu, Huan.

The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 169-175 (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cheng, L, Guo, R & Liu, H 2019, Robust cyberbullying detection with causal interpretation. in The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019, Association for Computing Machinery, Inc, pp. 169-175, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 5/13/19. https://doi.org/10.1145/3308560.3316503
Cheng L, Guo R, Liu H. Robust cyberbullying detection with causal interpretation. In The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 169-175. (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019). https://doi.org/10.1145/3308560.3316503
Cheng, Lu ; Guo, Ruocheng ; Liu, Huan. / Robust cyberbullying detection with causal interpretation. The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. pp. 169-175 (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019).
@inproceedings{87568d389d8041d5bbaf240d603dfc59,
title = "Robust cyberbullying detection with causal interpretation",
abstract = "Cyberbullying poses serious threats to preteens and teenagers, therefore, understanding the incentives behind cyberbullying is critical to prevent its happening and mitigate the impact. Most existing work towards cyberbullying detection has focused on the accuracy, and overlooked causes of the outcome. Discovering the causes of cyberbullying from observational data is challenging due to the existence of confounders, variables that can lead to spurious causal relationships between covariates and the outcome. This work studies the problem of robust cyberbullying detection with causal interpretation and proposes a principled framework to identify and block the influence of the plausible confounders, i.e., p-confounders. The de-confounded model is causally interpretable and is more robust to the changes in data distribution. We test our approach using the state-of-the-art evaluation method, causal transportability. The experimental results corroborate the effectiveness of our proposed algorithm. The purpose of this study is to provide a computational means to understanding cyberbullying behavior from observational data. This improves our ability to predict and to facilitate effective strategies or policies to proactively mitigate the impact of cyberbullying.",
keywords = "Causality, Cyberbullying detection, Social media",
author = "Lu Cheng and Ruocheng Guo and Huan Liu",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308560.3316503",
language = "English (US)",
series = "The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "169--175",
booktitle = "The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019",

}

TY - GEN

T1 - Robust cyberbullying detection with causal interpretation

AU - Cheng, Lu

AU - Guo, Ruocheng

AU - Liu, Huan

PY - 2019/5/13

Y1 - 2019/5/13

N2 - Cyberbullying poses serious threats to preteens and teenagers, therefore, understanding the incentives behind cyberbullying is critical to prevent its happening and mitigate the impact. Most existing work towards cyberbullying detection has focused on the accuracy, and overlooked causes of the outcome. Discovering the causes of cyberbullying from observational data is challenging due to the existence of confounders, variables that can lead to spurious causal relationships between covariates and the outcome. This work studies the problem of robust cyberbullying detection with causal interpretation and proposes a principled framework to identify and block the influence of the plausible confounders, i.e., p-confounders. The de-confounded model is causally interpretable and is more robust to the changes in data distribution. We test our approach using the state-of-the-art evaluation method, causal transportability. The experimental results corroborate the effectiveness of our proposed algorithm. The purpose of this study is to provide a computational means to understanding cyberbullying behavior from observational data. This improves our ability to predict and to facilitate effective strategies or policies to proactively mitigate the impact of cyberbullying.

AB - Cyberbullying poses serious threats to preteens and teenagers, therefore, understanding the incentives behind cyberbullying is critical to prevent its happening and mitigate the impact. Most existing work towards cyberbullying detection has focused on the accuracy, and overlooked causes of the outcome. Discovering the causes of cyberbullying from observational data is challenging due to the existence of confounders, variables that can lead to spurious causal relationships between covariates and the outcome. This work studies the problem of robust cyberbullying detection with causal interpretation and proposes a principled framework to identify and block the influence of the plausible confounders, i.e., p-confounders. The de-confounded model is causally interpretable and is more robust to the changes in data distribution. We test our approach using the state-of-the-art evaluation method, causal transportability. The experimental results corroborate the effectiveness of our proposed algorithm. The purpose of this study is to provide a computational means to understanding cyberbullying behavior from observational data. This improves our ability to predict and to facilitate effective strategies or policies to proactively mitigate the impact of cyberbullying.

KW - Causality

KW - Cyberbullying detection

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85066891425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066891425&partnerID=8YFLogxK

U2 - 10.1145/3308560.3316503

DO - 10.1145/3308560.3316503

M3 - Conference contribution

AN - SCOPUS:85066891425

T3 - The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

SP - 169

EP - 175

BT - The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

PB - Association for Computing Machinery, Inc

ER -