Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems

TL;DR

This study investigates how social explanations in music recommender systems influence user decisions, revealing limited correlation between initial interest and actual ratings, and proposes a probabilistic model to understand this interplay.

Contribution

It provides empirical evidence on the effects of social explanations and introduces a probabilistic model to explain their influence on user decision-making in music recommendations.

Findings

Explanations influence the likelihood of checking out artists.

Little correlation between initial interest and actual ratings.

Proposes a probabilistic model to explain decision processes.

Abstract

Recommender systems associated with social networks often use social explanations (e.g. "X, Y and 2 friends like this") to support the recommendations. We present a study of the effects of these social explanations in a music recommendation context. We start with an experiment with 237 users, in which we show explanations with varying levels of social information and analyze their effect on users' decisions. We distinguish between two key decisions: the likelihood of checking out the recommended artist, and the actual rating of the artist based on listening to several songs. We find that while the explanations do have some influence on the likelihood, there is little correlation between the likelihood and actual (listening) rating for the same artist. Based on these insights, we present a generative probabilistic model that explains the interplay between explanations and background information on music preferences, and how that leads to a final likelihood rating for an artist. Acknowledging the impact of explanations, we discuss a general recommendation framework that models external informational elements in the recommendation interface, in addition to inherent preferences of users.