This study explores how recommendation algorithms on Douyin respond to users’ growing disengagement from news by shaping the visibility of news content. Adopting an agent-based testing (ABT) approach, we conducted a 2 (intentional news avoidance: 0% vs. 100%) × 2 (unintentional news avoidance: 50% vs. 100%) between-subject experiment to simulate distinct user behaviors and capture large-scale data from news-related videos. Findings indicated that two avoidance behavioral patterns result in contrasting algorithmic outcomes which reinforce or weaken certain news values such as prominence, uniqueness, timeliness, and influence. A significant interaction effect further reveals that the influence of intentional news avoidance on the news values of influence diminishes as users’ preference for non-news content increases, whereas its influence on uniqueness becomes stronger. These findings show that recommender systems adapt to user disengagement by reprioritizing content, highlighting algorithmic curation as a socio-technical process that shapes attention amid selective news exposure.
No takes yet. Share an insight, caveat, or question.
Li et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: