Live Multi-Streaming and Donation Recommendations via Coupled Donation-Response Tensor Factorization

TL;DR

This paper introduces a novel tensor factorization-based system for real-time multi-streaming and donation recommendations, effectively capturing complex social interactions to improve recommendation accuracy.

Contribution

It proposes a new multi-streaming recommendation framework, DAMRec, and a tensor factorization model, MARS, to better model streamer-viewer interactions and enhance recommendation performance.

Findings

MARS outperforms existing recommenders by at least 38.8% in hit ratio.

Experimental results on Twitch and Douyu validate the effectiveness of the proposed method.

The approach effectively models socio-temporal donation-response interactions.

Abstract

In contrast to traditional online videos, live multi-streaming supports real-time social interactions between multiple streamers and viewers, such as donations. However, donation and multi-streaming channel recommendations are challenging due to complicated streamer and viewer relations, asymmetric communications, and the tradeoff between personal interests and group interactions. In this paper, we introduce Multi-Stream Party (MSP) and formulate a new multi-streaming recommendation problem, called Donation and MSP Recommendation (DAMRec). We propose Multi-stream Party Recommender System (MARS) to extract latent features via socio-temporal coupled donation-response tensor factorization for donation and MSP recommendations. Experimental results on Twitch and Douyu manifest that MARS significantly outperforms existing recommenders by at least 38.8% in terms of hit ratio and mean average precision.