Sliding into My DMs: Detecting Uncomfortable or Unsafe Sexual Risk Experiences within Instagram Direct Messages Grounded in the Perspective of Youth
Sliding into My DMs: Detecting Uncomfortable or Unsafe Sexual Risk Experiences within Instagram Direct Messages Grounded in the Perspective of Youth
复制标题
滑入我的私信：从年轻人的角度检测 Instagram 私信中不舒服或不安全的性风险经历
DOI：
10.1145/3579522
复制
发表时间：
2023
影响因子：
--
通讯作者：
Wisniewski, Pamela J.
中科院分区：
文献类型：
--
作者：
Razi, Afsaneh;Alsoubai, Ashwaq;Kim, Seunghyun;Ali, Shiza;Stringhini, Gianluca;De Choudhury, Munmun;Wisniewski, Pamela J.
我们收集了150名青少年（年龄在13-21岁之间）的Instagram数据，其中包括15，547次私人信息对话，其中326次对话被参与者标记为性风险。基于这些数据，我们利用以人为本的机器学习方法为青少年社交媒体对话创建性风险检测分类器。我们的卷积神经网络（CNN）和随机森林模型在识别对话级别的性风险方面表现出色（AUC=0.88），CNN在消息级别表现出色（AUC=0.85）。我们还训练了分类器来检测严重性风险级别（即，安全，低，中高），CNN优于其他模型（AUC=0.88）。特征分析对性安全与不安全对话中发现的模式有了更深入的了解。我们发现，上下文特征（例如，年龄，性别和关系类型）和语言调查和字数统计（LIWC）在准确检测使年轻人感到不舒服或不安全的性对话方面贡献最大。我们的分析提供了对重要因素和背景特征的深入了解，这些因素和背景特征增强了对青少年私人对话中性风险的自动检测。因此，我们通过以人为本的方法收集和编码青少年的私人社交媒体对话以进行风险分类，为计算风险检测和青少年在线安全文献做出了宝贵的贡献。
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.
登录
查看更多内容
MOSafely：建立开源 HCAI 社区，让互联网成为青少年更安全的地方
DOI：
10.1145/3462204.3481731
发表时间：
2021
期刊：
Workshop at the 2021 ACM Conference on Computer Supported Cooperative Work (CSCW 2021
影响因子：
--
作者：
Caddle, Xavier V;Razi, Afsaneh;Kim, Seunghyun;Ali, Shiza;Popo, Temi;Stringhini, Gianluca;De Choudhury, Munmun;Wisniewski, Pamela J.
通讯作者：
Wisniewski, Pamela J.
寻求帮助中的耻辱：青少年的案例
DOI：
--
发表时间：
2018
期刊：
影响因子：
--
作者：
Z. Shechtman;D. Vogel;Haley A. Strass;Patrick J. Heath
通讯作者：
Patrick J. Heath
影响因子：
0.4
作者：
P. Philipose;M. Kesavan
通讯作者：
M. Kesavan
影响因子：
--
作者：
Ashwaq Alsoubai;Jihye Song;Afsaneh Razi;N. Naher;M. D. Choudhury;P. Wisniewski
通讯作者：
Ashwaq Alsoubai;Jihye Song;Afsaneh Razi;N. Naher;M. D. Choudhury;P. Wisniewski
Instagram 数据捐赠：收集生态有效的社交媒体数据以进行青少年在线风险检测的案例研究
DOI：
10.1145/3491101.3503569
发表时间：
2022
期刊：
2022 ACM Conference on Human Factors in Computing Systems (CHI 2022
影响因子：
--
作者：
Razi, Afsaneh;Alsoubai, Ashwaq;Kim, Seunghyun;Naher, Nurun;Ali, Shiza;Stringhini, Gianluca;De Choudhury, Munmun;Wisniewski, Pamela J.
通讯作者：
Wisniewski, Pamela J.