21 CSCW 2021 papers to read

CSCW 2021 is coming up fast and these are my paper picks.

No particular order, just papers that stood out to me. Papers are generally related to health, social media, and interactive machine learning, as those are my interests. I picked 21 papers I want to read, plus 6 papers I’ve already read.

(Edit: this list is only based on half of the papers at CSCW, those accepted and published in issue CSCW1 of the Proceedings of the ACM on Human-Computer Interaction. I totally missed that there’s a whole second issue, CSCW2! That’s what I get for not looking directly at the program.)

Papers I want to read

Ke Zhou, Luca Maria Aiello, Sanja Scepanovic, Daniele Quercia, and Sara Konrath. 2021. The Language of Situational Empathy. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 13 (April 2021), 19 pages. DOI:https://doi.org/10.1145/3449087

Computational models for predicting empathy in text. Previous approaches for doing similar have been very unconvincing, so I’m excited to read their attempt.

Cody Buntain, Richard Bonneau, Jonathan Nagler, and Joshua A. Tucker. 2021. YouTube Recommendations and Effects on Sharing Across Online Social Platforms. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 11 (April 2021), 26 pages. DOI:https://doi.org/10.1145/3449085

Cool cross-platform empirical study.

Olivia K. Richards, Adrian Choi, and Gabriela Marcu. 2021. Shared Understanding in Care Coordination for Children’s Behavioral Health. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 21 (April 2021), 25 pages. DOI:https://doi.org/10.1145/3449095

Care coordination challenges in practice between medical professionals and non-professional caregivers. Interesting to contrast with the collaboration practices described by Amsha et al., also in the conference.

Farnaz Jahanbakhsh, Amy X. Zhang, Adam J. Berinsky, Gordon Pennycook, David G. Rand, and David R. Karger. 2021. Exploring Lightweight Interventions at Posting Time to Reduce the Sharing of Misinformation on Social Media. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 18 (April 2021), 42 pages. DOI:https://doi.org/10.1145/3449092

Useful taxonomy of news truthfulness, interesting empirical study.

Jack Bandy. 2021. Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 74 (April 2021), 34 pages. DOI:https://doi.org/10.1145/3449148

Credit to Jack for tackling the wide range of methods referred to as “audits”. Important work.

Elahe Naserianhanzaei and Miriam Koschate-Reis. 2021. Do Group Memberships Online Protect Addicts in Recovery Against Relapse? Testing the Social Identity Model of Recovery in the Online World. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 68 (April 2021), 18 pages. DOI:https://doi.org/10.1145/3449142

Survival analysis modeling of addiction recovery, as affected by online group membership. An ambitious space for quantitative work.

Maria Antoniak, Melanie Walsh, and David Mimno. 2021. Tags, Borders, and Catalogs: Social Re-Working of Genre on LibraryThing. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 29 (April 2021), 29 pages. DOI:https://doi.org/10.1145/3449103

I love classification and boundary work, and this is a fun investigation of genre.

Molly G. Hickman, Viral Pasad, Harsh Kamalesh Sanghavi, Jacob Thebault-Spieker, and Sang Won Lee. 2021. Understanding Wikipedia Practices Through Hindi, Urdu, and English Takes on an Evolving Regional Conflict. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 34 (April 2021), 31 pages. DOI:https://doi.org/10.1145/3449108

Interesting Wikipedia case study.

Danaë Metaxa, Michelle A. Gan, Su Goh, Jeff Hancock, and James A. Landay. 2021. An Image of Society: Gender and Racial Representation and Impact in Image Search Results for Occupations. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 26 (April 2021), 23 pages. DOI:https://doi.org/10.1145/3449100

Lovely replication + extension of a classic social computing paper.

Jack Bandy and Nicholas Diakopoulos. 2021. More Accounts, Fewer Links: How Algorithmic Curation Impacts Media Exposure in Twitter Timelines. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 78 (April 2021), 28 pages. DOI:https://doi.org/10.1145/3449152

Sock-puppet audit of Twitter’s curation/ranking algorithm.

Téo Sanchez, Baptiste Caramiaux, Jules Françoise, Frédéric Bevilacqua, and Wendy E. Mackay. 2021. How do People Train a Machine? Strategies and (Mis)Understandings. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 162 (April 2021), 26 pages. DOI:https://doi.org/10.1145/3449236

A study of algorithm teaching, based on an interactive machine learning system for sketch recognition.

Sindhu Kiranmai Ernala, Kathan H. Kashiparekh, Amir Bolous, Asra Ali, John M. Kane, Michael L. Birnbaum, and Munmun De Choudhury. 2021. A Social Media Study on Mental Health Status Transitions Surrounding Psychiatric Hospitalizations. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 155 (April 2021), 32 pages. DOI:https://doi.org/10.1145/3449229

Mixture models have really made a resurgence in social media research recently. I remain a skeptic, but I’m interested to dig into their validation method (which is the tricky part!). Unique dataset.

Swati Mishra and Jeffrey M. Rzeszotarski. 2021. Crowdsourcing and Evaluating Concept-driven Explanations of Machine Learning Models. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 139 (April 2021), 26 pages. DOI:https://doi.org/10.1145/3449213

Most explanation/interpretability work is questionable, but this looks interesting. I like the conceptual information framing.

Nazanin Andalibi and Patricia Garcia. 2021. Sensemaking and Coping After Pregnancy Loss: The Seeking and Disruption of Emotional Validation Online. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 127 (April 2021), 32 pages. DOI:https://doi.org/10.1145/3449201

“Algorithmic symbolic annihilation” is an interesting concept that dovetails nicely with recent work on the value assumptions of machine learning systems. Honestly, I’m just a huge Naz Andalibi stan.

Robin N. Brewer, Sarita Schoenebeck, Kerry Lee, and Haripriya Suryadevara. 2021. Challenging Passive Social Media Use: Older Adults as Caregivers Online. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 123 (April 2021), 20 pages. DOI:https://doi.org/10.1145/3449197

Older adults as caregivers when they choose not to interact on social media.

Austin P. Wright, Omar Shaikh, Haekyu Park, Will Epperson, Muhammed Ahmed, Stephane Pinel, Duen Horng (Polo) Chau, and Diyi Yang. 2021. RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 181 (April 2021), 26 pages. DOI:https://doi.org/10.1145/3449280

Interesting moderation experiment: by making toxicity predictions visible to users, they train people to adversarially write toxic content that evades automated classifiers.

Zahra Ashktorab, Michael Desmond, Josh Andres, Michael Muller, Narendra Nath Joshi, Michelle Brachman, Aabhas Sharma, Kristina Brimijoin, Qian Pan, Christine T. Wolf, Evelyn Duesterwald, Casey Dugan, Werner Geyer, and Darrell Reimer. 2021. AI-Assisted Human Labeling: Batching for Efficiency without Overreliance. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 89 (April 2021), 27 pages. DOI:https://doi.org/10.1145/3449163

Batch vs single-item labeling. A hot area in ML industry right now, and an important area for additional empirical work.

Jialun Aaron Jiang, Kandrea Wade, Casey Fiesler, and Jed R. Brubaker. 2021. Supporting Serendipity: Opportunities and Challenges for Human-AI Collaboration in Qualitative Analysis. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 94 (April 2021), 23 pages. DOI:https://doi.org/10.1145/3449168

We’re reading this next week in the GroupLens paper meeting. This was one of my original research interests when I started my PhD, so I’m always excited to read papers that push in this direction. Additional context and nuance provided by Feuston and Brubaker.

Kimberley R. Allison, Pandora Patterson, Daniel Guilbert, Melissa Noke, and Olga Husson. 2021. Logging On, Reaching Out, and Getting By: A Review of Self-reported Psychosocial Impacts of Online Peer Support for People Impacted by Cancer. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 95 (April 2021), 35 pages. DOI:https://doi.org/10.1145/3449169

Definitely an important review topic.

Jessica A. Pater, Chanda Phelan, Victor P. Cornet, Ryan Ahmed, Sarah Colletta, Erik Hess, Connie Kerrigan, and Tammy Toscos. 2021. User-Centered Design of a Mobile App to Support Peer Recovery in a Clinical Setting. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 112 (April 2021), 31 pages. DOI:https://doi.org/10.1145/3449186

Systems work for peer coaching.

Aaron Mueller, Zach Wood-Doughty, Silvio Amir, Mark Dredze, and Alicia Lynn Nobles. 2021. Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 107 (April 2021), 28 pages. DOI:https://doi.org/10.1145/3449181

Social media dataset analysis. Interesting-looking methods.

Papers I’ve already read (and recommend)

Papers by my labmates

Haiwei Ma, Sunny Parawala, and Svetlana Yarosh. 2021. Detecting Expressive Writing in Online Health Communities by Modeling Aggregated Empirical Data. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 62 (April 2021), 32 pages. DOI:https://doi.org/10.1145/3449136

Ambitious and novel approach to an important modeling task.

C. Estelle Smith, Avleen Kaur, Katie Z. Gach, Loren Terveen, Mary Jo Kreitzer, and Susan O’Conner-Von. 2021. What is Spiritual Support and How Might It Impact the Design of Online Communities? Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 43 (April 2021), 42 pages. DOI:https://doi.org/10.1145/3449117

Spiritual support is an understudied construct in online communities.

Ruoyan Kong, Haiyi Zhu, and Joseph A. Konstan. 2021. Learning to Ignore: A Case Study of Organization-Wide Bulk Email Effectiveness. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 80 (April 2021), 23 pages. DOI:https://doi.org/10.1145/3449154

Email sucks! A classic multi-stakeholder problem, with bad incentives and bad outcomes.

Papers from other labs

Nathan TeBlunthuis, Benjamin Mako Hill, and Aaron Halfaker. 2021. Effects of Algorithmic Flagging on Fairness: Quasi-experimental Evidence from Wikipedia. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 56 (April 2021), 27 pages. DOI:https://doi.org/10.1145/3449130

Great methods.

Sanchari Das, Tousif Ahmed, Apu Kapadia, and Sameer Patil. 2021. Does This Photo Make Me Look Good? How Social Media Feedback on Photos Impacts Posters, Outsiders, and Friends. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 46 (April 2021), 32 pages. DOI:https://doi.org/10.1145/3449120

I love to see conceptual replications at CSCW.

Zheng Yao, Diyi Yang, John M. Levine, Carissa A. Low, Tenbroeck Smith, Haiyi Zhu, and Robert E. Kraut. 2021. Join, Stay or Go? A Closer Look at Members’ Life Cycles in Online Health Communities. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 171 (April 2021), 22 pages. DOI:https://doi.org/10.1145/3449245

Mixed-methods work is really hard to get right. This paper generated a lot of discussion during the review process, and I’m pleased to see it end up with an Honorable Mention.

Any papers you think I missed? Please let me know.