Individualized video recommendation modulates functional connectivity between large scale networks

Abstract

With the emergence of AI‐powered recommender systems and their extensive use in the video streaming service, questions and concerns also arise. Why can recommended video content continuously capture users' attention? What is the impact of long‐term exposure to personalized video content on one's behaviors and brain functions? To address these questions, we designed an fMRI experiment presenting participants with personally recommended videos and generally recommended ones. To examine how large‐scale networks were modulated by personalized video content, graph theory analysis was applied to investigate the interaction between seven networks, including the ventral and dorsal attention networks (VAN, DAN), frontal–parietal network (FPN), salience network (SN), and three subnetworks of default mode network (dorsal medial prefrontal (dMPFC), Core, and medial temporal lobe (MTL)). Our results showed that viewing nonpersonalized video content mainly enhanced the connectivity in the DAN‐FPN‐Core pathway, whereas viewing personalized ones increased not only the connectivity in this pathway but also the DAN‐VAN‐dMPFC pathway. In addition, both personalized and nonpersonalized short videos decreased the couplings between SN and VAN as well as between two DMN subsystems, Core and MTL. Collectively, these findings uncovered distinct patterns of network interactions in response to short videos and provided insights into potential neural mechanisms by which human behaviors are biased by personally recommended content.

Aberrant dynamic functional network connectivity in type 2 diabetes mellitus individuals

“…Due to the pivotal role DMN played in cognitive function, we divided it into the dDMN, vDMN and PCUN (Shirer et al 2012 ) to investigate connectivity alteration in each subnetwork. Recent studies suggested these three subnetworks display heterogeneous functional connectivity both in task state (Su et al 2021 ) and resting state (Chen et al 2017 ), while we did not find similar patterns in our dFNC results. However, we noticed that the differences in functional connectivity between T2DM and HC groups in the DMN were mainly reflected by differences in the PCUN.…”

A Systematic Review of Structural and Functional MRI Studies Investigating Social Networking Site Use

“…Interestingly, however, and contrasting with an important role for the NAc in other SNS use behaviours, the NAc was deactivated (although not significantly) when viewing both video types. In an extension of this work, the same group published further analyses of the same dataset using graph theory to investigate the functional connectivity between seven networks [81]. Results revealed that viewing personalised videos increased connectivity in the DAN-VAN-DMN pathway, whereas both video types resulted in reduced coupling between the salience network (i.e., anterior insula and dorsal ACC) and VAN as well as between two subsystems in the DMN.…”

“…The PCC constitutes a central structure of the default mode network (DMN), a neural network that is maximally activated at rest [117,118]. The DMN has been found to show increased activation and altered functional connectivity with various other regions (including regions in the dorsal and ventral attention networks) when viewing personalised TikTok videos and after reading SNS microblogs [68,80,81]. Such findings imply that passively consuming SNS content (particularly personalised content) may activate a neural state similar to that when mind wandering, which may facilitate prolonged use through modulating attention and inducing absent-minded scrolling/browsing of SNS feeds.…”

“…The precuneus, a region which neighbours the PCC, is another core hub of the DMN and is therefore also implicated in studies demonstrating alterations of DMN activity and functional connectivity when viewing SNS content [68,80,81]. The precuneus is also thought to play an important role in a range of complex tasks including visuo-spatial imagery, memory retrieval and self-referential cognition [120].…”

Plasma NFL Disrupt Cognitive Integrity Via Coupling the Interactions of Core Subsystem and Frontoparietal Network in Alzheimer's Disease

“…The FPN comprises the lateral prefrontal cortex, dorsal anterior cingulate cortex, precuneus, anterior inferior parietal lobule, and the inferior temporal cortex, appear to be involved in instantiating and exibly modulating cognitive control [16]. Moreover, the previous study has revealed core subsystem coupling with FPN during cognitive activity [17]. However, it remains unclear how core subsystem and FPN cohesively recon gure in AD-spectrum patients, and whether such recon gurations re ect behavioral performance.…”