Multi-Output Recommender: Items, Groups and Friends, and Their Mutual Contributing Effects

TL;DR

This paper introduces a multi-output recommender system that predicts items, groups, and friends simultaneously to enhance social media user engagement and facilitate effective group recommendations.

Contribution

It proposes a novel multi-output recommendation model that captures mutual effects among items, groups, and friends, improving recommendation accuracy in social media platforms.

Findings

Enhanced recommendation accuracy demonstrated

Effective modeling of mutual effects among outputs

Improved user engagement in social groups

Abstract

Due to the development of social media technology, it becomes easier for users to gather together to form groups. Take the Last.fm for example, users can join groups they may be interested where they can share their loved songs and discuss topics about songs and singers. However, the number of groups grows over time, users need effective groups recommendations in order to meet more like-minded users.