Reducing Sexual Predation and Victimization Through Warnings and Awareness among High-Risk Users

TL;DR

The study tackles online sexual grooming by delivering warnings and awareness messages to high-risk users, guided by Routine Activity Theory. It implements a large-scale randomized controlled trial on the avatar-based platform Pigg Party, enrolling about $12{,}842$ intervention and $12{,}844$ control participants (n ≈ $25{,}686$) over 138 days, and uses a Graph Attention Network ensemble to identify risk with $AUC=0.87$. The intervention significantly reduced violations and being violated among women for up to 12 weeks, while effects on men were limited, suggesting gender-specific dynamics in online predation and victimization. The findings support guardian-based interventions as a scalable complement to platform moderation, with implications for crime psychology and online safety policy, while highlighting the need for male-focused strategies and cross-platform validation.

Abstract

Online sexual predators target children by building trust, creating dependency, and arranging meetings for sexual purposes. This poses a significant challenge for online communication platforms that strive to monitor and remove such content and terminate predators' accounts. However, these platforms can only take such actions if sexual predators explicitly violate the terms of service, not during the initial stages of relationship-building. This study designed and evaluated a strategy to prevent sexual predation and victimization by delivering warnings and raising awareness among high-risk individuals based on the routine activity theory in criminal psychology. We identified high-risk users as those with a high probability of committing or being subjected to violations, using a machine learning model that analyzed social networks and monitoring data from the platform. We conducted a randomized controlled trial on a Japanese avatar-based communication application, Pigg Party. High-risk players in the intervention group received warnings and awareness-building messages, while those in the control group did not receive the messages, regardless of their risk level. The trial involved 12,842 high-risk players in the intervention group and 12,844 in the control group for 138 days. The intervention successfully reduced violations and being violated among women for 12 weeks, although the impact on men was limited. These findings contribute to efforts to combat online sexual abuse and advance understanding of criminal psychology.

Figures (6)

• Figure 1: Schematic diagram of the experiment
• Figure 2: Players chat via their avatars in Pigg Party. Translation of this figure: "Mind if I join in?,’’ 2: "Hey,’’ 3: "Which anime are you watching? Tell me what you're hooked on!,’’ 4: "There are so many good ones this season, aren't there?,’’ and 5: "I want to know!.’’
• Figure 3: The relationships between violation risk score and violation (left), the relationships between the risk score of being violated and being violated in DM (middle), and the relationships between the risk score of being violated and being violated in AC (right).
• Figure 4: Violation frequencies of high-risk players and their time course from intervention days in the intervention and control groups. The vertical axes are log-scale.
• Figure 5: The frequencies of instances of being violated among high-risk players and their time course from intervention days are shown for both the intervention and control groups (top: DM; bottom: AC). The vertical axes are log-scale.