Filters








6 Hits in 5.1 sec

Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining [article]

Jiaying Liu, Feng Xia, Lei Wang, Bo Xu, Xiangjie Kong, Hanghang Tong, Irwin King
2020 arXiv   pre-print
For this purpose, we propose a novel model based on Network Representation Learning (NRL), namely Shifu2, which takes the collaboration network as input and the identified advisor-advisee relationship  ...  This work aims to discover advisor-advisee relationships hidden behind scientific collaboration networks.  ...  We also compare Shifu2 with existing solutions for identifying advisor-advisee relationships: • Shifu [15] . Shifu is a deep learning model based on the stacked autoencoder.  ... 
arXiv:2008.07097v1 fatcat:42xeh2uz2ja47pzyhdiqtkkuci

Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining

Jiaying Liu, Feng Xia, Lei Wang, Bo Xu, Xiangjie Kong, Hanghang Tong, Irwin King
2019 IEEE Transactions on Knowledge and Data Engineering  
We also compare Shifu2 with existing solutions for identifying advisor-advisee relationships: • Shifu [15] . Shifu is a deep learning model based on the stacked autoencoder.  ...  Through individual training of data in different fields, Shifu2 model has better applicability and scalability. (2) Shifu utilizes supervised learning using a deep learning based model.  ... 
doi:10.1109/tkde.2019.2946825 fatcat:f4kcn724nfdvzg7bk5ekvjqwxq

The Use of Academic Social Networking Sites in Scholarly Communication: Scoping Review

Milkyas Hailu, Jianhua Wu
2020 Data and Information Management  
The study found that there has been an increase in scholarly big data research in recent years. The paper also discusses the key findings and concepts stated in each theme.  ...  Four main themes within the research literature are proposed: motivation and uses, impact assessment, features and services, and scholarly big data.  ...  Similarly, Wang et al. (2019) proposed Shifu: a deep-learning-based advisor-advisee relationship identification method that takes into account both the local properties and the network characteristics  ... 
doi:10.2478/dim-2020-0050 fatcat:ogwzdeopzrhmhpkil3lmbjbk5m

Applying Deep Learning Techniques for Big Data Analytics: A Systematic Literature Review

Memudu Tunde Muhammed, Obidallah Waeal J, Raahemi Bijan
2018 Archives of Information Science and Technology  
No of FS Tittle Name of dataset Description of dataset Size of dataset [FS1] Shifu: Deep Learning Based Advisor-advisee Relationship Mining in Scholarly Big Data. PhDTree DBLP dataset.  ...  A deep-learning-based advisor- advisee relationship identification method which takes into account both the local properties and network characteristics Consist of Inferred 1,111,513 advisor-advisee  ... 
doi:10.36959/863/756 fatcat:hzigrkqofjckfeygxannfwzcye

Metaphor research in the 21st century: A bibliographic analysis

Dongyu Zhang, Minghao Zhang, Ciyuan Peng, Jason Jung, Feng Xia
2020 Computer Science and Information Systems  
Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor re search, and expounds the underlying patterns of its development.  ...  Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships  ...  Wang, W., Liu, J., Xia, F., King, I., Tong, H.: Shifu: Deep learning based advisor-17 advisee relationship mining in scholarly big data.  ... 
doi:10.2298/csis201109059z fatcat:gx4kc6tqfjai7kfbs5zglevski

Data-driven Computational Social Science: A Survey

Jun Zhang, Wei Wang, Feng Xia, Yu-Ru Lin, Hanghang Tong
2020 Big Data Research  
Social science concerns issues on individuals, relationships, and the whole society.  ...  In this paper, to the best of our knowledge, we present a survey on data-driven computational social science for the first time which primarily focuses on reviewing application domains involving human  ...  In addition, Wang et al. [50] proposed Shifu, a deep-learning-based advisor-advisee relationship identification method that takes into account both the local properties and network characteristics.  ... 
doi:10.1016/j.bdr.2020.100145 fatcat:jazh5b3itfgmvh4pn37l4v5m7y