ColdRoute: Effective Routing of Cold Questions in Stack Exchange Sites

TL;DR

ColdRoute introduces a novel approach using Factorization Machines to improve routing of cold questions in Stack Exchange, especially for new askers, significantly outperforming existing semantic matching methods.

Contribution

The paper presents ColdRoute, a new method leveraging Factorization Machines for better routing of cold questions, addressing challenges with new askers and cold-start problems.

Findings

Significant improvements in routing metrics over state-of-the-art methods.

Effective handling of cold questions posted by new and existing askers.

Demonstrated success across eight Stack Exchange sites.

Abstract

Routing questions in Community Question Answer services (CQAs) such as Stack Exchange sites is a well-studied problem. Yet, cold-start -- a phenomena observed when a new question is posted is not well addressed by existing approaches. Additionally, cold questions posted by new askers present significant challenges to state-of-the-art approaches. We propose ColdRoute to address these challenges. ColdRoute is able to handle the task of routing cold questions posted by new or existing askers to matching experts. Specifically, we use Factorization Machines on the one-hot encoding of critical features such as question tags and compare our approach to well-studied techniques such as CQARank and semantic matching (LDA, BoW, and Doc2Vec). Using data from eight stack exchange sites, we are able to improve upon the routing metrics (Precision$@1$, Accuracy, MRR) over the state-of-the-art models such as semantic matching by $159.5\%$,$31.84\%$, and $40.36\%$ for cold questions posted by existing askers, and $123.1\%$, $27.03\%$, and $34.81\%$ for cold questions posted by new askers respectively.