Analysis of Online Conversations to Detect Cyberpredators Using Recurrent Neural Networks

Jinhwa Kim, Yoon Jo Kim, Mitra Behzadi, Ian G. Harris


Abstract
We present an automated approach to analyze the text of an online conversation and determine whether one of the participants is a cyberpredator who is preying on another participant. The task is divided into two stages, 1) the classification of each message, and 2) the classification of the entire conversation. Each stage uses a Recurrent Neural Network (RNN) to perform the classification task.
Anthology ID:
2020.stoc-1.3
Volume:
Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Archna Bhatia, Samira Shaikh
Venue:
STOC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
15–20
Language:
English
URL:
https://aclanthology.org/2020.stoc-1.3
DOI:
Bibkey:
Cite (ACL):
Jinhwa Kim, Yoon Jo Kim, Mitra Behzadi, and Ian G. Harris. 2020. Analysis of Online Conversations to Detect Cyberpredators Using Recurrent Neural Networks. In Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management, pages 15–20, Marseille, France. European Language Resources Association.
Cite (Informal):
Analysis of Online Conversations to Detect Cyberpredators Using Recurrent Neural Networks (Kim et al., STOC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.stoc-1.3.pdf