A review of citation recommendation: from textual content to enriched context

Citation recommendation systems play an important role to alleviate the dilemma that scholar users spend a lot of time and experiences for literature survey. With the burgeoning computational models and open data movement, scientific repository can provide more evidence in support of recommendation. On the one hand, recommenders are applying better algorithms to understand the text of user queries and candidate citations. On the other hand, more types of data such as citation network and co-author relationship are aggregated to enrich the citation contextual information. The available data used for recommendation has been extended from textual content to enriched context. This review is conducted to identify the information and methods used for recommendations recently. We begin by introducing definitions of the task, recommending factors along with the corresponding problems and some application platforms. Then, we classify existing recommenders according to user query types and review representative methods for each type. We also elaborate on different strategies applied in three main stages of citation recommendation. Finally, a few open issues for future investigations are proposed.