While social media algorithms have become excellent at matching a user’s viewing habits with targeted, personalized content, psychologists at The University of Texas at Dallas have determined that these algorithms may have a negative influence on a user’s mental health.

Dr. Alva Tang, assistant professor of psychology in the School of Behavioral and Brain Sciences, is corresponding author of a proof-of-concept study published online June 25 in Computers in Human Behavior that explores the links between algorithm-recommended content, how that content is processed by the brain and symptoms of depression.

In the study, 60 young adults with an average age of 20 were assessed via validated anxiety and depression scales. They then watched two sets of videos: one of personally recommended videos from their own Instagram or TikTok accounts, which were further categorized for content types; the other of generalized trending videos. Brain activity was recorded using EEG to measure frontal alpha asymmetry — a well-established measure of emotional processing and motivation.

“In frontal alpha asymmetry, dominance on the left represents more positive” emotional processing, Tang explained. Right-sided dominance typically relates to negative processing and withdrawal behaviors.

“Instead of after-the-fact reflections, we looked at real-time emotion processing” and documented reactions to personalized recommendations, Tang noted. This approach differs from prior research relying on surveys and self-reports.

First author Carole Leung, a doctoral student in cognition and neuroscience, explained that total screen time alone may weakly predict mental health outcomes. “What the algorithm recommends to you matters, too. The emotional content in your personalized feed is linked to your brain’s real-time emotional responses and to depressive symptoms.”

Dr. Stacie Warren, associate professor of psychology and study co-author, emphasized the measurement approach: “EEG is a real-time processing measure of brain activity within milliseconds.” Combining neuroimaging with self-reported depressive symptoms provides objective evaluation of algorithmically selected social media engagement.

The study results confirmed that participants with more depressive symptoms receive recommendations leaning toward depressive content. Their brain activity shows patterns characteristic of depression—distinct from activity while viewing trending videos generally.

“What we’re finding is that if you’re already feeling depressed, then the algorithms reflect that. Continued engagement reinforces this negative feedback loop,” Warren stated. Participants brought their own phones; researchers did not select videos for them.

The most common recommended video category concerns social relationships—romantic or friendships. Researchers found that participant emotions could influence app recommendations. “If you’re more depressed, you’re more likely to be exposed to a video showing an argument or conflict,” Tang said. Positive videos typically show friends supporting each other, while neutral videos lack emotional connotation.

Viewing fewer positive social relationship videos correlated with relative right frontal alpha asymmetry, indicating more negative feelings.

“Depressed individuals have a tendency to focus on negative things, dismissing the positive things they encounter,” Warren explained. Continued scrolling while depressed exposes users to fewer positive videos.

Researchers hope to develop healthy social media engagement behaviors preventing negative mood amplification. Current interventions focus on educating critical, effective social media use.

“We are teaching teenagers who frequently use TikTok and Instagram how to curate positive content while limiting the negative,” Tang said. Resetting accounts to defaults provides new recommendations, allowing users to retrain algorithms.

Parents should understand algorithm influence on mood, but limiting teen screen time alone won’t teach adaptive responses. “Two years ago, the guidance from the American Academy of Pediatrics was to reduce screen time,” Tang noted. Telling teenagers to avoid phones proves ineffective in today’s context.

Researchers are collecting data on teenagers ages 13 to 16 for potential long-term study examining emotional effects of algorithm suggestions over time.

Other UT Dallas contributors include Lucie H. Nguyen BS’25, an incoming medical student at Dell Medical School at UT Austin; Christina Vlahakos, now a Northwestern University graduate student; and Dr. Carlos Busso, now at Carnegie Mellon University.

This research was supported by a 2025 Social Sciences Seed Grant from UT Dallas and a Behavioral Health Research Award from the University of North Texas’ Center for Psychosocial Health Disparities Research.

---

Journal: Computers in Human Behavior
DOI: 10.1016/j.chb.2026.109098
Publication Date: 25-Jun-2026

Source: University of Texas at Dallas