Preventing Scroller Remorse: How to Know What Users Want
A new model can help online media companies understand what gives users long-term satisfaction — not just the instant gratification of continuous scrolling — which can lead to less time spent on the platform, but less users who leave completely.
Most online platforms seek to increase the time users spend there, usually by giving them more content than they have consumed in the past. But this strategy can perpetuate mindless scrolling and potentially cause regrettable users to go cold turkey.
“There’s a discussion in the search community and in tech companies about how people may use online media a lot, but often come away without valuing the time they spent,” said Jon Kleinberg ’93, Professor of Computer Science at Tisch University. at Cornell Ann S. Bowers College of Computing and Information Science. Kleinberg co-authored a new article that provides tools to help mitigate this conflict by giving online media companies new ways to understand what users really want.
“These platforms are designed to watch what you do and then give you more of what you want,” Kleinberg said. “So on the one hand, these platforms are highly optimized. On the other hand, we often feel like we’re not making the right choices when we’re at it. So how do you reconcile these two things? »
This inconsistency may be the result of two known facets of human decision-making, System 1 and System 2. System 1 makes fast, almost automatic decisions, while System 2 is slower, reflexive, and more logical. With food, system 1 wants the whole bag of chips, while system 2 chooses the salad. Both foods can be part of a balanced diet, but fries provide instant satisfaction, while salad provides long-lasting satisfaction. With online media, celebrity posts may trigger System 1, while an educational video may interest System 2.
To understand how these two systems affect online media consumption, Kleinberg worked with former graduate student Manish Raghavan, MS ’18, Ph.D. ’21, now at the Massachusetts Institute of Technology, and Sendhil Mullainathan ’93, a behavioral economist at the University of Chicago. They developed a model that simulates how a user with conflicting desires interacts with a platform and then suggests ways to prioritize the value the user receives.
Their paper, “The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization,” received the Exemplary Applied Modeling Paper Award at the Association for Computing Machinery Economics and Computation 2022 conference. This is the second year in a row that an article co-authored by Kleinberg has received the award.
The model is necessary, the researchers said, because most platforms have heaps of behavioral data — clicks, shares, and session durations — that mostly reflect system choices 1. Collecting information about the choices of the system 2, for example through user satisfaction surveys, is much more difficult.
The new model is a starting point for businesses to understand what drives user decisions. “While some types of content behave like junk food, others can behave like healthy salads, and distinguishing the difference is key to understanding what users want,” Raghavan said. The model can help companies categorize content as chips or salad, and tweak the algorithm to prevent users from binging.
Additionally, the model may suggest design changes. For example, platforms can let System 2 kick in periodically by adding regular breaks, an option that some social media companies already offer. They can also turn off autoplay, which tends to fuel impulsive decisions in System 1.
Now the authors are working with platform designers to discover which interventions successfully improve user happiness. They also aim to incorporate user interactions into the model, to see how peer likes and comments impact the experience.
Ideally, the authors hope this model will shift the conversation away from extending engagement towards increasing the value of the platform for users. “I think a lot of these companies are recognizing that in the long run, making people happier and safer using these platforms actually benefits them,” Raghavan said.
The work was funded by the Center for Research on Computation and Society at Harvard University, the the Vannevar Bush Faculty Fellows Program, the MacArthur and Simons Foundations, and the Center for Applied AI at the University of Chicago.
Patricia Waldron is an editor at Cornell Ann S. Bowers College of Computing and Information Science.