Collaborator recommendation in heterogeneous bibliographic networks using random walks

Conceptual model of knowledge management system for scholarly publication cycle in academic institution

Purpose

Study on knowledge-based systems for scientific publications is growing very broadly. However, most of these studies do not explicitly discuss the knowledge management (KM) component as knowledge management system (KMS) implementation. This background causes academic institutions to face challenges in developing KMS to support scholarly publication cycle (SPC). Therefore, this study aims to develop a new KMS conceptual model, Identify critical components and provide research gap opportunities for future KM studies on SPC.

Design/methodology/approach

This study used a systematic literature review (SLR) method with the procedure from Kitchenham et al. Then, the SLR results are compiled into a conceptual model design based on a framework on KM foundations and KM solutions. Finally, the model design was validated through interviews with related field experts.

Findings

The KMS for SPC focuses on the discovery, sharing and application of knowledge. The majority of KMS use recommendation systems technology with content-based filtering and collaborative filtering personalization approaches. The characteristics data used in KMS for SPC are structured and unstructured. Metadata and article abstracts are considered sufficiently representative of the entire article content to be used as a search tool and can provide recommendations. The KMS model for SPC has layers of KM infrastructure, processes, systems, strategies, outputs and outcomes.

Research limitations/implications

This study has limitations in discussing tacit knowledge. In contrast, tacit knowledge for SPC is essential for scientific publication performance. The tacit knowledge includes experience in searching, writing, submitting, publishing and disseminating scientific publications. Tacit knowledge plays a vital role in the development of knowledge sharing system (KSS) and KCS. Therefore, KSS and KCS for SPC are still very challenging to be researched in the future. KMS opportunities that might be developed further are lessons learned databases and interactive forums that capture tacit knowledge about SPC. Future work potential could identify other types of KMS in academia and focus more on SPC.

Originality/value

This study proposes a novel comprehensive KMS model to support scientific publication performance. This model has a critical path as a KMS implementation solution for SPC. This model proposes and recommends appropriate components for SPC requirements (KM processes, technology, methods/techniques and data). This study also proposes novel research gaps as KMS research opportunities for SPC in the future.

Recommendations for item set completion: on the semantics of item co-occurrence with data sparsity, input size, and input modalities

We address the problem of recommending relevant items to a user in order to “complete” a partial set of already-known items. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender’s performance. We also investigate data sparsity by imposing a pruning threshold on minimum item occurrence and the influence of using additional metadata. As models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is usually helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. The simple item co-occurrence model is a strong baseline for citation recommendation but can provide good results also for subject labels. Autoencoders have the capability to exploit additional metadata besides the partial item set as input, and achieve comparable or better performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the results. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate model and carefully decide which metadata to exploit.

Academic Collaborator Recommendation Based on Attributed Network Embedding

Purpose

Based on real-world academic data, this study aims to use network embedding technology to mining academic relationships, and investigate the effectiveness of the proposed embedding model on academic collaborator recommendation tasks.

Design/methodology/approach

We propose an academic collaborator recommendation model based on attributed network embedding (ACR-ANE), which can get enhanced scholar embedding and take full advantage of the topological structure of the network and multi-type scholar attributes. The non-local neighbors for scholars are defined to capture strong relationships among scholars. A deep auto-encoder is adopted to encode the academic collaboration network structure and scholar attributes into a low-dimensional representation space.

Findings

1. The proposed non-local neighbors can better describe the relationships among scholars in the real world than the first-order neighbors. 2. It is important to consider the structure of the academic collaboration network and scholar attributes when recommending collaborators for scholars simultaneously.

Research limitations

The designed method works for static networks, without taking account of the network dynamics.

Practical implications

The designed model is embedded in academic collaboration network structure and scholarly attributes, which can be used to help scholars recommend potential collaborators.

Originality/value

Experiments on two real-world scholarly datasets, Aminer and APS, show that our proposed method performs better than other baselines.