The number of academic papers being published is increasing rapidly, and recommending sufficient citations to assist researchers in writing papers is a non-trivial task. Conventional recommendation approaches may not be optimal, as the recommended papers may already be known to the users or may be solely relevant to the surrounding context but not to other concepts discussed in the manuscript. In this study, we propose a novel embedding algorithm, namely DocCit2Vec, along with the new concept of "structural context", to address the aforementioned issues. The proposed models are compared extensively with network-based, document-based, and combined approaches in experiments of citation recommendation and classification tasks. Three implications are concluded. First, the document-based methods demonstrated overwhelmingly superior performances for citation recommendation than the network-based methods, as the latter lack consideration of the word information. Second, DocCit2Vec exhibited significant improvement for citation recommendation among the document-based methods. Third, the ability to conduct classification tasks could be significantly enhanced by adding attention layer to DocCit2Vec.

Based on an exponentially increasing number of academic articles, discovering and citing comprehensive and appropriate resources has become a non-trivial task. Conventional citation recommender methods suffer from severe information loss. For example, they do not consider the section of the paper that the user is writing and for which they need to find a citation, the relatedness between the words in the local context (the text span that describes a citation), or the importance on each word from the local context. These shortcomings make such methods insufficient for recommending adequate citations to academic manuscripts. In this study, we propose a novel embedding-based neural network called "dual attention model for citation recommendation (DACR)" to recommend citations during manuscript preparation. Our method adapts embedding of three semantic information: words in the local context, structural contexts 1 , and the section on which a user is working. A neural network model is designed to maximize the similarity between the embedding of the three input (local context words, section and structural contexts) and the target citation appearing in the context. The core of the neural network model is composed of self-attention and additive attention, where the former aims to capture the relatedness between the contextual words and structural context, and the latter aims to learn the importance of them. The experiments on real-world datasets demonstrate the effectiveness of the proposed approach.

The number of academic papers being published is increasing exponentially in recent years, and recommending adequate citations to assist researchers in writing papers is a non-trivial task. Conventional approaches may not be optimal, as the recommended papers may already be known to the users, or be solely relevant to the surrounding context but not other ideas discussed in the manuscript. In this work, we propose a novel embedding algorithm DocCit2Vec, along with the new concept of "structural context", to tackle the aforementioned issues. The proposed approach demonstrates superior performances to baseline models in extensive experiments designed to simulate practical usage scenarios.