Helping the Ineloquent Farmers: Finding Experts for Questions With Limited Text in Agricultural Q&A Communities

Abstract

Nowadays, hundreds of thousands of farmers in China seek online in agricultural Q&A communities, such as Farm-Doctor, for agricultural advice. As in many other Q&A communities, the key design issue is to find experts to provide timely and suitable answers. State-of-the-art approaches often rely on extracting topics from the question texts, however, the major challenge here is that questions in agricultural Q&A communities often contain limited textual information. To solve this problem, in this article, we conduct an extensive measurement on Farm-Doctor, which consists of over 690 thousand questions and over 3 million answers, and we model Farm-Doctor as a heterogeneous information network that incorporates rich side information. We propose a novel approach based on graph neural network to accurately recommend for each question the users that are highly likely to answer it. With an average income of fewer than 6 dollars a day, our method helps these less eloquent farmers with their cultivation and hopefully provides a way to improve their lives.

Keywords

• Question and answering
• question routing
• network representation learning