An official website of the United States government
We collected Instagram data from 150 adolescents (ages 13-21) that included 15,547 private message conversations of which 326 conversations were flagged as sexually risky by participants. Based on this data, we leveraged a human-centered machine learning approach to create sexual risk detection classifiers for youth social media conversations. Our Convolutional Neural Network (CNN) and Random Forest models outperformed in identifying sexual risks at the conversation-level (AUC=0.88), and CNN outperformed at the message-level (AUC=0.85). We also trained classifiers to detect the severity risk level (i.e., safe, low, medium-high) of a given message with CNN outperforming other models (AUC=0.88). A feature analysis yielded deeper insights into patterns found within sexually safe versus unsafe conversations. We found that contextual features (e.g., age, gender, and relationship type) and Linguistic Inquiry and Word Count (LIWC) contributed the most for accurately detecting sexual conversations that made youth feel uncomfortable or unsafe. Our analysis provides insights into the important factors and contextual features that enhance automated detection of sexual risks within youths' private conversations. As such, we make valuable contributions to the computational risk detection and adolescent online safety literature through our human-centered approach of collecting and ground truth coding private social media conversations of youth for the purpose of risk classification.
more »
« less
Profiling the Offline and Online Risk Experiences of Youth to Develop Targeted Interventions for Online Safety
We conducted a study with 173 adolescents (ages 13-21), who self-reported their offline and online risk experiences and uploaded their Instagram data to our study website to flag private conversations as unsafe. Risk profiles were first created based on the survey data and then compared with the risk-flagged social media data. Five risk profiles emerged: Low Risks (51% of the participants), Medium Risks (29%), Increased Sexting (8%), Increased Self-Harm (8%), and High Risk Perpetration (4%). Overall, the profiles correlated well with the social media data with the highest level of risk occurring in the three smallest profiles. Youth who experienced increased sexting and self-harm frequently reported engaging in unsafe sexual conversations. Meanwhile, high risk perpetration was characterized by increased violence, threats, and sales/promotion of illegal activities. A key insight from our study was that offline risk behavior sometimes manifested differently in online contexts (i.e., offline self-harm as risky online sexual interactions). Our findings highlight the need for targeted risk prevention strategies for youth online safety.
more »
« less
- PAR ID:
- 10564915
- Publisher / Repository:
- Proceedings of ACM on Human-Computer Interaction
- Date Published:
- Journal Name:
- Proceedings of the ACM on Human-Computer Interaction
- Volume:
- 8
- Issue:
- CSCW1
- ISSN:
- 2573-0142
- Page Range / eLocation ID:
- 1 to 37
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Online sexual risks pose a serious and frequent threat to adolescents’ online safety. While significant work is done within the HCI community to understand teens’ sexual experiences through public posts, we extend their research by qualitatively analyzing 156 private Instagram conversations flagged by 58 adolescents to understand the characteristics of sexual risks faced with strangers, acquaintances, and friends. We found that youth are often victimized by strangers through sexual solicitation/harassment as well as sexual spamming via text and visual media, which is often ignored by them. In contrast, adolescents’ played mixed roles with acquaintances, as they were often victims of sexual harassment, but sometimes engaged in sexting, or interacted by rejecting sexual requests from acquaintances. Lastly, adolescents were never recipients of sexual risks with their friends, as they mostly mutually participated in sexting or sexual spamming. Based on these results, we provide our insights and recommendations for future researchers. Trigger Warning: This paper contains explicit language and anonymized private sexual messages. Reader discretion advised.more » « less
-
Ensuring the online safety of youth has motivated research towards the development of machine learning (ML) methods capable of accurately detecting social media risks after-the-fact. However, for these detection models to be effective, they must proactively identify high-risk scenarios (e.g., sexual solicitations, cyberbullying) to mitigate harm. This `real-time' responsiveness is a recognized challenge within the risk detection literature. Therefore, this paper presents a novel two-level framework that first uses reinforcement learning to identify conversation stop points to prioritize messages for evaluation. Then, we optimize state-of-the-art deep learning models to accurately categorize risk priority (low, high). We apply this framework to a time-based simulation using a rich dataset of 23K private conversations with over 7 million messages donated by 194 youth (ages 13-21). We conducted an experiment comparing our new approach to a traditional conversation-level baseline. We found that the timeliness of conversations significantly improved from over 2 hours to approximately 16 minutes with only a slight reduction in accuracy (0.88 to 0.84). This study advances real-time detection approaches for social media data and provides a benchmark for future training reinforcement learning that prioritizes the timeliness of classifying high-risk conversations.more » « less
-
We collected Instagram Direct Messages (DMs) from 100 adolescents and young adults (ages 13-21) who then flagged their own conversations as safe or unsafe. We performed a mixed-method analysis of the media files shared privately in these conversations to gain human-centered insights into the risky interactions experienced by youth. Unsafe conversations ranged from unwanted sexual solicitations to mental health related concerns, and images shared in unsafe conversations tended to be of people and convey negative emotions, while those shared in regular conversations more often conveyed positive emotions and contained objects. Further, unsafe conversations were significantly shorter, suggesting that youth disengaged when they felt unsafe. Our work uncovers salient characteristics of safe and unsafe media shared in private conversations and provides the foundation to develop automated systems for online risk detection and mitigation.more » « less
-
Let's Talk about Sext: How Adolescents Seek Support and Advice about Their Online Sexual ExperiencesWe conducted a thematic content analysis of 4,180 posts by adolescents (ages 12-17) on an online peer support mental health forum to understand what and how adolescents talk about their online sexual interactions. Youth used the platform to seek support (83%), connect with others (15%), and give advice (5%) about sexting, their sexual orientation, sexual abuse, and explicit content. Females often received unwanted nudes from strangers and struggled with how to turn down sexting requests from people they knew. Meanwhile, others who sought support complained that they received unwanted sexual solicitations while doing so—to the point that adolescents gave advice to one another on which users to stay away from. Our research provides insight into the online sexual experiences of adolescents and how they seek support around these issues. We discuss how to design peer-based social media platforms to support the well-being and safety of youth.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3637391
