Who is the “human” in human-centered machine learning: The case of predicting mental health from social media

被引：72
作者：
Chancellor S. [1 ]
Baumer E.P.S. [2 ]
De Choudhury M. [1 ]
机构：
[1] Georgia Tech, Atlanta, GA
[2] Lehigh University, Bethlehem, PA
来源：
Proceedings of the ACM on Human-Computer Interaction | 2019年 / 3卷 / CSCW期
基金：
美国国家卫生研究院; 美国国家科学基金会;
关键词：
Human-centered machine learning; Machine learning; Mental health; Research ethics; Social media;
D O I：
10.1145/3359249
中图分类号：
学科分类号：
摘要：
“Human-centered machine learning” (HCML) combines human insights and domain expertise with data-driven predictions to answer societal questions. This area’s inherent interdisciplinarity causes tensions in the obligations researchers have to the humans whose data they use. This paper studies how scientific papers represent human research subjects in HCML. Using mental health status prediction on social media as a case study, we conduct thematic discourse analysis on 55 papers to examine these representations. We identify five discourses that weave a complex narrative of who the human subject is in this research: Disorder/Patient, Social Media, Scientific, Data/Machine Learning, and Person. We show how these five discourses create paradoxical subject and object representations of the human, which may inadvertently risk dehumanization. We also discuss the tensions and impacts of interdisciplinary research; the risks of this work to scientific rigor, online communities, and mental health; and guidelines for stronger HCML research in this nascent area. © 2019 Association for Computing Machinery.
引用
收藏
相关论文
共 187 条
[1]  
Alkhatib A., Anthropological/Artificial Intelligence & the HAI, (2019)
[2]  
Amershi S., Weld D., Vorvoreanu M., Fourney A., Nushi B., Collisson P., Suh J., Iqbal S., Bennett P.N., Inkpen K., Teevan J., Kikin-Gil R., Microsoft E.H., Allen P.G., Four-Ney A., Guidelines for human-AI interaction, CHI Conference on Human Factors in Computing Systems Proceedings (CHI 2019), (2019)
[3]  
Aragon C., Hutto C., Echenique A., Fiore-Gartland B., Huang Y., Kim J., Neff G., Xing W., Bayer J., Developing a research agenda for human-centered data science, Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion, pp. 529-535, (2016)
[4]  
Arboleda-Florez J., Stuart H., From sin to science: Fighting the stigmatization of mental illnesses, Canadian Journal of Psychiatry, 57, 8, pp. 457-463, (2012)
[5]  
Diagnostic and Statistical Manual of Mental Disorders (DSM-5®), (2013)
[6]  
Ayers J.W., Caputi T.L., Nebeker C., Dredze M., Don’t quote me: Reverse identification of research participants in social media studies, Npj Digital Medicine, 1, 1, (2018)
[7]  
Bannon L., From human factors to human actors: The role of psychology and human-computer interaction studies in system design, Design at Work: Cooperative Design of Computer Systems, pp. 25-44, (1991)
[8]  
Bannon L., Reimagining HCI: Toward a more human-centered perspective, Interactions, 18, 4, pp. 50-57, (2011)
[9]  
Barry A., Born G., Weszkalnys G., Logics of interdisciplinarity, Economy and Society, 37, 1, pp. 20-49, (2008)
[10]  
Bauer H.H., Barriers against interdisciplinarity: Implications for studies of science, technology, and society (STS, Science, Technology, & Human Values, 15, 1, pp. 105-119, (1990)
12345678910