Machine-arranged Interactions Improve Institutional Belonging and Cohesion

TL;DR

This study tests whether machine-arranged, in-person one-on-one meetings can boost university students' sense of institutional belonging and warmth toward diverse groups. Using the Connect platform at UVA, participants were randomized to receive introductions or serve as wait-lists, with end-of-semester surveys tracking belonging and cohesion over time. The results show that participation is associated with a $4.5 ext{ extperthousand}?$ increase in final belonging and a $3.94 ext{ extperthousand}?$ increase in final cohesion, with exposure to similar backgrounds and differing group perceptions further modulating outcomes. The findings suggest technology-enabled, programmatic introductions can meaningfully improve belonging and cross-group cohesion in diverse university settings, offering a scalable path for organizational inclusion efforts.

Abstract

We investigated how participation in machine-arranged meetings were associated with feelings of institutional belonging and perceptions of demographic groups. We collected data from 535 individuals who participated in a program to meet new friends. Data consisted of surveys measuring demography, belonging, and perceptions of various demographic groups at the start and end of the program. Participants were partitioned into a control group who received zero introductions, and an intervention group who received multiple introductions. For each participant, we computed twelve features describing participation status, demography and the amount of program-facilitated exposure to others who were similar to them and different from them. We used a linear model to study the association of our features with the participants' final belonging and perceptions while controlling for their initial belonging and perceptions. We found that those who participated in the machine-arranged meetings had 4.5% higher belonging, and 3.9% more positive perception of others.

Figures (2)

• Figure 1: Network plot of participants in the program as a function of their final belonging. Plot shows participants who logged a meeting or were on the wait-list (excluding those in the intervention group who never logged a meeting). Node size reflects extent in majority status. Node color reflects final belonging; redder nodes had higher final belonging, bluer nodes had lower final belonging. Edge thickness reflects the absolute value of the cumulative difference of similarity and difference features for the pair of participants. Edge color indicates the polarity of the difference between cumulative similarity and difference; a red edges indicates both participants were more similar than different, and blue indicates that participants were more different than similar.
• Figure 2: Network plot of participants in the program as a function of their final cohesion towards other. Plot shows participants who logged a meeting or were on the wait-list (excluding those in the intervention group who never logged a meeting). Node size reflects extent in majority status. Node color indicates change in perception; Red nodes indicate increased cohesion in their perception of the other group, Blue nodes indicates decreased cohesion in their perception of the other group. Edge color indicates the polarity of the difference between cumulative similarity and difference; a red edges indicates both participants were more similar than different, and blue indicates that participants were more different than similar.