Simplifying Sparse Expert Recommendation by Revisiting Graph Diffusion

TL;DR

This paper introduces a simple graph-diffusion model for expert recommendation in community question answering platforms, effectively capturing users' evolving expertise and outperforming existing deep learning and collaborative approaches.

Contribution

The paper presents a novel graph-diffusion approach that incorporates semantic and temporal information to improve expert recommendation, especially for cold-start users.

Findings

Outperforms state-of-the-art methods on five real-world datasets.

Achieves ~30% performance gain for cold-start users.

Effectively models users' changing interests over time.

Abstract

Community Question Answering (CQA) websites have become valuable knowledge repositories where individuals exchange information by asking and answering questions. With an ever-increasing number of questions and high migration of users in and out of communities, a key challenge is to design effective strategies for recommending experts for new questions. In this paper, we propose a simple graph-diffusion expert recommendation model for CQA, that can outperform state-of-the art deep learning representatives and collaborative models. Our proposed method learns users' expertise in the context of both semantic and temporal information to capture their changing interest and activity levels with time. Experiments on five real-world datasets from the Stack Exchange network demonstrate that our approach outperforms competitive baseline methods. Further, experiments on cold-start users (users with a limited historical record) show our model achieves an average of ~ 30% performance gain compared to the best baseline method.