Dynamic network embedding enhanced advisor-advisee relationship identification based on internet of scholars

Abstract Advisor–advisee relationship is a special social relationship and interpersonal relationship. In the era of scholarly big data, mining and analyzing this kind of academic relationships is of great significance. Though many studies explore the advisor–advisee relationships based on real-world dataset, the scale of their dataset is relatively small. Based on the assumption that advisor–advisee relationships are hidden in collaboration networks, this paper proposes a novel method by performing dynamic network embedding on internet of scholars. Specifically, we consider various scholar attributes and dynamic network embedding-based scholar vector as the input of supervised machine learning methods for advisor–advisee relationship identification. Experimental results on the real-world dataset show that our proposed method can achieve the best performance compared with several state-of-the-art methods.

[1]  Feng Xia,et al.  Understanding the advisor–advisee relationship via scholarly data analysis , 2018, Scientometrics.

[2]  C. Lee Giles.  Scholarly big data: information extraction and data mining , 2013, CIKM.

[3]  Jie Tang,et al.  Inferring social ties across heterogenous networks , 2012, WSDM '12.

[4]  Ying Ding,et al.  Scientific collaboration and endorsement: Network analysis of coauthorship and citation networks , 2011, J. Informetrics.

[5]  Charles J. Gelso,et al.  Measuring the working alliance in advisor-advisee relationships in graduate school. , 2001 .

[6]  Jie Tang,et al.  ArnetMiner: extraction and mining of academic social networks , 2008, KDD.

[7]  Marie V. Plaisime,et al.  Mentorship: The necessity of intentionality. , 2019, The American journal of orthopsychiatry.

[8]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[9]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[10]  Jinzhong Wang,et al.  Trust-Enhanced Collaborative Filtering for Personalized Point of Interests Recommendation , 2020, IEEE Transactions on Industrial Informatics.

[11]  Xing Xie,et al.  Context-aware Academic Collaborator Recommendation , 2018, KDD.

[12]  Feng Xia,et al.  Shifu: Deep Learning Based Advisor-advisee Relationship Mining in Scholarly Big Data , 2017, WWW.

[13]  Taiji Suzuki,et al.  Cross-domain Recommendation via Deep Domain Adaptation , 2018, ECIR.

[14]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[15]  Jinzhong Wang,et al.  Geography-Aware Inductive Matrix Completion for Personalized Point-of-Interest Recommendation in Smart Cities , 2020, IEEE Internet of Things Journal.

[16]  Jaegul Choo,et al.  Short-Text Topic Modeling via Non-negative Matrix Factorization Enriched with Local Word-Context Correlations , 2018, WWW.

[17]  Yilong Yin,et al.  Identifying advisor-advisee relationships from co-author networks via a novel deep model , 2018, Inf. Sci..

[18]  Mohammad Al Hasan,et al.  Name Disambiguation in Anonymized Graphs using Network Embedding , 2017, CIKM.

[19]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[20]  Gérard Biau,et al.  Analysis of a Random Forests Model , 2010, J. Mach. Learn. Res..

[21]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[22]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[23]  Thomas L. Griffiths,et al.  The Author-Topic Model for Authors and Documents , 2004, UAI.

[24]  Jiawei Han,et al.  Mining advisor-advisee relationships from research publication networks , 2010, KDD.

[25]  L. Amaral,et al.  The role of mentorship in protégé performance , 2010, Nature.

[26]  Jie Chen,et al.  EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs , 2020, AAAI.