Coauthorship network-based literature recommendation with topic model

Abstract

Purpose The information needs of the users of literature database systems often come from the task at hand, which is short term and can be represented as a small number of articles. Previous works on recommending articles to satisfy users’ short-term interests have utilized article content, usage logs, and more recently, coauthorship networks. The usefulness of coauthorship has been demonstrated by some research works, which, however, tend to adopt a simple coauthorship network that records only the strength of coauthorships. The purpose of this paper is to enhance the effectiveness of coauthorship-based recommendation by incorporating scholars’ collaboration topics into the coauthorship network. Design/methodology/approach The authors propose a latent Dirichlet allocation (LDA)-coauthorship-network-based method that integrates topic information into the links of the coauthorship networks using LDA, and a task-focused technique is developed for recommending literature articles. Findings The experimental results using information systems journal articles show that the proposed method is more effective than the previous coauthorship network-based method over all scenarios examined. The authors further develop a hybrid method that combines the results of content-based and LDA-coauthorship-network-based recommendations. The resulting hybrid method achieves greater or comparable recommendation effectiveness under all scenarios when compared to the content-based method. Originality/value This paper makes two contributions. The authors first show that topic model is indeed useful and can be incorporated into the construction of coaurthoship-network to improve literature recommendation. The authors subsequently demonstrate that coauthorship-network-based and content-based recommendations are complementary in their hit article rank distributions, and then devise a hybrid recommendation method to further improve the effectiveness of literature recommendation.

Discovering research topics from library electronic references using latent Dirichlet allocation

“…LDA has been applied in many fields, including pattern detection in images (Agarwal and Triggs, 2008; Coelho et al 2010) and video (Niebles et al , 2008; Wang et al , 2009), automatic essay grading (Kakkonen et al , 2008), and fraud detection (Xing and Girolami, 2007). For different research needs, scholars have performed some expansions to the LDA model, such as the author-topic model (Hwang et al , 2017), dynamic topic models (Blei and Lafferty, 2006), correlated topic models (Blei and Lafferty, 2007), non-Markov continuous-time model (Wang and Mccallum, 2006), and sentence LDA (Bao and Datta, 2014; Jo and Oh, 2011).…”

Can I have more of these please?

“…However, links between co-authors do not carry any topical information. This issue has been addressed in a study (Hwang et al ., 2017) where latent dirichlet allocation (LDA) topic models (Blei et al ., 2003) are integrated with the co-authorship networks. In the recommendation model, scientific papers are conceptualized as author vectors in which elements represent both topic and co-authorship similarity between an author and a paper.…”

Semantic Academic Profiler (SAP): a framework for researcher assessment based on semantic topic modeling

“…In this context, some efforts exploit the concept of topic modeling for detecting and strengthening co-Authorship Networks (Hwang et al., 2017 ; Krasnov et al., 2019 ; Hu et al., 2020 ). In Jeong et al.…”

“…It indicates that determining researchers’ secondary lines of research is even more challenging when there is little information about them. All these analyses need to be taken into account by recent efforts that exploit the concept of topic modeling for detecting and strengthening co-Authorship Networks (Hwang et al.M 2017 ; Krasnov et al., 2019 ; Hu et al., 2020 ). We observe similar results regarding the institution’s profiles, in which institutions with the highest number of researchers had their profiles better evaluated.…”