# Trust and Trustworthiness in Social Recommender Systems

## TL;DR

This paper explores how trustworthiness dimensions in social recommender systems can help combat misinformation and political polarization by promoting diversity, transparency, and explainability in news recommendations.

## Contribution

It introduces a user-centric trustworthiness framework to challenge naive assumptions in social recommendation algorithms, aiming to reduce dogmatization and improve transparency.

## Key findings

- Trustworthiness dimensions can discourage ideological dogmatization.
- Promoting diversity and transparency enhances user decision-awareness.
- Framework offers new opportunities for transparent news recommender systems.

## Abstract

The prevalence of misinformation on online social media has tangible empirical connections to increasing political polarization and partisan antipathy in the United States. Ranking algorithms for social recommendation often encode broad assumptions about network structure (like homophily) and group cognition (like, social action is largely imitative). Assumptions like these can be na\"ive and exclusionary in the era of fake news and ideological uniformity towards the political poles. We examine these assumptions with aid from the user-centric framework of trustworthiness in social recommendation. The constituent dimensions of trustworthiness (diversity, transparency, explainability, disruption) highlight new opportunities for discouraging dogmatization and building decision-aware, transparent news recommender systems.