Enhancing citation recommendation using citation network embedding

Today, increased attention is drawn towards network representation learning, a technique that maps nodes of a network into vectors of a low-dimensional embedding space. A network embedding constructed this way aims to preserve nodes similarity and other specific network properties. Embedding vectors can later be used for downstream machine learning problems, such as node classification, link prediction and network visualization. Naturally, some networks have text information associated with them. For instance, in a citation network, each node is a scientific paper associated with its abstract or title; in a social network, all users may be viewed as nodes of a network and posts of each user as textual attributes. In this work, we explore how combining existing methods of text and network embeddings can increase accuracy for downstream tasks and propose modifications to popular architectures to better capture textual information in network embedding and fusion frameworks.

Download Full-text

Supplemental Material for The Psychology of Men and Masculinities: Using Citation Network Analysis to Understand Research Domains, Collaborations, and Grant Competitiveness

Psychology of Men & Masculinity ◽

10.1037/men0000139.supp ◽

2017 ◽

Keyword(s):

Network Analysis ◽

Citation Network ◽

Citation Network Analysis ◽

Psychology Of Men ◽

Men And Masculinities ◽

Research Domains

Download Full-text

Exploring key transformism properties of patent citation network: the base of hybrid rice

Advances in Industrial Engineering, Information and Water Resources ◽

10.2495/aie120261 ◽

2012 ◽

Author(s):

Tianhua Song ◽

Guang Yu ◽

Chunsheng Shi ◽

Hui Zhou ◽

Bo Zou

Keyword(s):

Hybrid Rice ◽

Citation Network ◽

Patent Citation ◽

Patent Citation Network

Download Full-text

Who Talks and Who Listens? A Bibliometric Analysis of Economics Journals Co-Citation Network

SSRN Electronic Journal ◽

10.2139/ssrn.2885126 ◽

2016 ◽

Author(s):

Tianhao Wu

Keyword(s):

Bibliometric Analysis ◽

Citation Network ◽

Economics Journals

Download Full-text

A Survey of Network Embedding for Drug Analysis and Prediction

Current Protein and Peptide Science ◽

10.2174/1389203721666200702145701 ◽

2020 ◽

Vol 21 ◽

Author(s):

Zhixian Liu ◽

Qingfeng Chen ◽

Wei Lan ◽

Jiahai Liang ◽

Yiping Pheobe Chen ◽

...

Keyword(s):

Deep Learning ◽

Protein Function ◽

Dimensional Space ◽

Auxiliary Information ◽

Matrix Decomposition ◽

Drug Analysis ◽

Machine Learning Algorithms ◽

Superior Performance ◽

Network Embedding ◽

Similarity Estimation

: Traditional network-based computational methods have shown good results in drug analysis and prediction. However, these methods are time consuming and lack universality, and it is difficult to exploit the auxiliary information of nodes and edges. Network embedding provides a promising way for alleviating the above problems by transforming network into a low-dimensional space while preserving network structure and auxiliary information. This thus facilitates the application of machine learning algorithms for subsequent processing. Network embedding has been introduced into drug analysis and prediction in the last few years, and has shown superior performance over traditional methods. However, there is no systematic review of this issue. This article offers a comprehensive survey of the primary network embedding methods and their applications in drug analysis and prediction. The network embedding technologies applied in homogeneous network and heterogeneous network are investigated and compared, including matrix decomposition, random walk, and deep learning. Especially, the Graph neural network (GNN) methods in deep learning are highlighted. Further, the applications of network embedding in drug similarity estimation, drug-target interaction prediction, adverse drug reactions prediction, protein function and therapeutic peptides prediction are discussed. Several future potential research directions are also discussed.

Download Full-text

A Review of Minimum Quantity Lubrication (MQL) based on Bibliometry

Current Materials Science ◽

10.2174/2666145413999201222104811 ◽

2020 ◽

Vol 13 ◽

Author(s):

Gaurav Gaurav ◽

Abhay Sharma ◽

G S Dangayach ◽

M L Meena

Keyword(s):

Descriptive Analysis ◽

Minimum Quantity Lubrication ◽

Citation Network ◽

Machining Process ◽

Cutting Fluid ◽

Future Research ◽

Research Directions ◽

Minimum Quantity ◽

Research Areas ◽

Future Research Directions

Background: Minimum quantity lubrication (MQL) is one of the most promising machining techniques that can yield a reduction in consumption of cutting fluid more than 90 % while ensuring the surface quality and tool life. The significance of the MQL in machining makes it imperative to consolidate and analyse the current direction and status of research in MQL. Objective: This study aims to assess global research publication trends and hot topics in the field of MQL among machining process. The bibliometric and descriptive analysis are the tools that the investigation aims to use for the data analysis of related literature collected from Scopus databases. Methods: Various performance parameters are extracted, such as document types and languages of publication, annual scientific production, total documents, total citations, and citations per article. The top 20 of the most relevant and productive sources, authors, affiliations, countries, word cloud, and word dynamics are assessed. The graphical visualisation of the bibliometric data is presented in terms of bibliographic coupling, citation, and co-citation network. Results: The investigation reveals that the International Journal of Machine Tools and Manufacture (2611 citations, 31 hindex) is the most productive journal that publishes on MQL. The most productive institution is the University of Michigan (32 publications), the most cited country is Germany (1879 citations), and the most productive country in MQL is China (124 publications). The study shows that ‘Cryogenic Machining’, ‘Sustainable Machining’, ‘Sustainability’, ‘Nanofluid’ and ‘Titanium alloy’ are the most recent keywords and indications of the hot topics and future research directions in the MQL field. Conclusion: The analysis finds that MQL is progressing in publications and the emerging with issues that are strongly associated with the research. This study is expected to help the researchers to find the most current research areas through the author’s keywords and future research directions in MQL and thereby expand their research interests.

Download Full-text