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
A Human-Centered Approach to Improving Adolescent Real-Time Online Risk Detection Algorithms
Computational approaches to detect the online risks that the youth encounter have presented promising potentials to protect them online. However, a major identified trend among these approaches is the lack of human-centered machine learning (HCML) aspect. It is necessary to move beyond the computational lens of the detection task to address the societal needs of such a vulnerable population. Therefore, I direct my attention in this dissertation to better understand youths’ risk experiences prior to enhancing the development of risk detection algorithms by 1) Examining youths’ (ages 13–17) public disclosures about sexual experiences and contextualizing these experiences based on the levels of consent (i.e., consensual, non-consensual, sexual abuse) and relationship types (i.e., stranger, dating/friend, family), 2) Moving beyond the sexual experiences to examine a broader array of risks within the private conversations of youth (N = 173) between 13 and 21 and contextualizing the dynamics of youth online and offline risks and the self-reports of risk experiences to the digital trace data, and 3) Building real-time machine learning models for risk detection by creating a contextualized framework. This dissertation provides a human-centered approach for improving automated real-time risk predictions that are derived from a contextualized understanding of the nuances relative to youths’ risk experiences.
more »
« less
- Award ID(s):
- 2329976
- PAR ID:
- 10564912
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9781450394222
- Page Range / eLocation ID:
- 1 to 5
- Format(s):
- Medium: X
- Location:
- Hamburg Germany
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Sexual exploration is a natural part of adolescent development; yet, unmediated internet access has enabled teens to engage in a wider variety of potentially riskier sexual interactions than previous generations, from normatively appropriate sexual interactions to sexually abusive situations. Teens have turned to online peer support platforms to disclose and seek support about these experiences. Therefore, we analyzed posts (N=45,955) made by adolescents (ages 13--17) on an online peer support platform to deeply examine their online sexual risk experiences. By applying a mixed methods approach, we 1) accurately (average of AUC = 0.90) identified posts that contained teen disclosures about online sexual risk experiences and classified the posts based on level of consent (i.e., consensual, non-consensual, sexual abuse) and relationship type (i.e., stranger, dating/friend, family) between the teen and the person in which they shared the sexual experience, 2) detected statistically significant differences in the proportions of posts based on these dimensions, and 3) further unpacked the nuance in how these online sexual risk experiences were typically characterized in the posts. Teens were significantly more likely to engage in consensual sexting with friends/dating partners; unwanted solicitations were more likely from strangers and sexual abuse was more likely when a family member was involved. We contribute to the HCI and CSCW literature around youth online sexual risk experiences by moving beyond the false dichotomy of "safe" versus "risky". Our work provides a deeper understanding of technology-mediated adolescent sexual behaviors from the perspectives of sexual well-being, risk detection, and the prevention of online sexual violence toward youth.more » « less
-
Current youth online safety and risk detection solutions are mostly geared toward parental control. As HCI researchers, we acknowledge the importance of leveraging a youth-centered approach when building Artificial Intelligence (AI) tools for adolescents online safety. Therefore, we built the MOSafely, Is that ‘Sus’ (youth slang for suspicious)? a web-based risk detection assessment dashboard for youth (ages 13-21) to assess the AI risks identified within their online interactions (Instagram and Twitter Private conversations). This demonstration will showcase our novel system that embedded risk detection algorithms for youth evaluations and adopted the human–in–the loop approach for using youth evaluations to enhance the quality of machine learning models.more » « less
-
With the growing ubiquity of the Internet and access to media-based social media platforms, the risks associated with media content sharing on social media and the need for safety measures against such risks have grown paramount. At the same time, risk is highly contextualized, especially when it comes to media content youth share privately on social media. In this work, we conducted qualitative content analyses on risky media content flagged by youth participants and research assistants of similar ages to explore contextual dimensions of youth online risks. The contextual risk dimensions were then used to inform semi- and self-supervised state-of-the-art vision transformers to automate the process of identifying risky images shared by youth. We found that vision transformers are capable of learning complex image features for use in automated risk detection and classification. The results of our study serve as a foundation for designing contextualized and youth-centered machine-learning methods for automated online risk detection.more » « less
-
As adolescents' engagement increases online, it becomes more essential to provide a safe environment for them. Although some apps and systems are available for keeping teens safer online, these approaches and apps do not consider the needs of parents and teens. We would like to improve adolescent online sexual risk detection algorithms. In order to do so, I'll conduct three research studies for my dissertation: 1) Qualitative analysis on teens posts on an online peer support platform about online sexual risks in order to gain deep understanding of online sexual risks 2) Train a machine learning approach to detect sexual risks based on teens conversations with sex offenders 3) develop a machine learning algorithm for detecting online sexual risks specialized for adolescents.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3544549.3577045
