Leveraging Diversity in Online Interactions
Nardine Osman, Bruno Rosell i Gui, Carles Sierra
TL;DR
The paper tackles online support matching by mediating interactions through declarative norms and diversity-aware profile selection. It implements a WeNet framework where norms can be updated at runtime and users can specify diversity requirements across four deep dimensions. The work demonstrates through multi-site pilots that diversity-aware matching can be achieved and that user satisfaction is high, with explainability mechanisms to clarify norms. The findings highlight context-dependent value of diversity and point to future work on automatic norm learning and adaptive norm interpretation to improve scalability and adaptability in real-world communities.
Abstract
This paper addresses the issue of connecting people online to help them find support with their day-to-day problems. We make use of declarative norms for mediating online interactions, and we specifically focus on the issue of leveraging diversity when connecting people. We run pilots at different university sites, and the results show relative success in the diversity of the selected profiles, backed by high user satisfaction.