Recommendations with Benefits: Exploring Explanations in Information Sharing Recommender Systems for Temporary Teams

Abstract

Increased use of collaborative technologies and agile teamwork models has led to a greater need for temporary teams. Unfortunately, they lack the normal team formation processes that traditional teams use. Information sharing recommender systems can be used to share information about team members amongst the team; however, these systems rely on the team members themselves to disclose valuable information. While prior research has shown that an effective way to encourage user disclosure is through explanations to the user about what benefits they will gain from disclosure, the timing of such explanations has yet to be consideblack. In a between-subjects study with 150 participants, we assessed the content and timing of explanations on levels of disclosure in temporary teams. Our results indicate that providing benefit-related explanations during the time of disclosure can increase user disclosure, and providing benefit-related explanations during the recommendation process can increase user trust in the system. These results provide important design implications for teams and the HCI community.

Keywords:

• Recommender systems
• information sharing
• mental models
• explanations

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Geoff Musick

Geoff Musick is a UI/UX Designer for a company that works in the fields of missile defense, space, and cyber systems. He received his Ph.D. in Human-Centered Computing from Clemson University in the fall of 2022. His research focused on artificial intelligence, teamwork, and recommender systems.

Allyson I. Hauptman

Allyson I. Hauptman is a doctoral candidate in Human Centered Computing at Clemson University and conducts research as part of the Team Research Analytics in Computational Environments (TRACE) Research Group. Her primary research interests involve the design and evaluation of adaptive autonomous teammates.

Christopher Flathmann

Christopher Flathmann is a Research Assistant Professor in the Human-Centered Computing Department at Clemson University. He received a Ph.D. in Human-Centered Computing from Clemson University in 2023.

Nathan J. McNeese

Nathan J. McNeese is the CECAS Dean’s Professor and Assistant Professor of Human-Centered Computing and Director of the Team Research Analytics in Computational Environments (TRACE) Research Group. His current research interests span across human-AI teaming, human-centered AI, and the development/design of human-centered collaborative tools and systems.

Bart P. Knijnenburg

Bart P. Knijnenburg is an Associate Professor in Human-Centered Computing and an expert in privacy decision-making and the user-centric evaluation of adaptive decision-support systems. His NSF CAREER award winning research includes a conceptual framework and practical guidelines for user-centric evaluation that has become the de-facto standard in the field.