Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2021, 4(3); doi: 10.25236/AJCIS.2021.040311.

Doctor recommendation via community detection


Li Guo, Chenning Du

Corresponding Author:
Li Guo

Dalian Polytechnic University, Dalian, China


With the development of socioeconomic and computer science and technology, people have paid more and more attention to physical health and living convenience, network precision medicine enters people's lives. Because that teamwork is needed in the medical process, how to recommend a doctor to form a team becomes important. Instead of using recommendation algorithm, the paper recommends doctors based on community detection. Firstly, 37144 pairs of doctors with labels based on thesis cooperation relationship were obtained through web crawler, secondly, find the connected subgraph with the union check set, thirdly, create the graph with the doctors as nodes, the cooperation relationship between doctors as the edges, and cut the graph with the algorithm of spectral clustering until the connected graphs have approximately five layers of relations. Then take the number of cooperative papers as the weight of edges. Recommend a doctor with the doctors who are in at least the third layer and with a higher weight score in the same community. At the same time, the paper suggests the doctors of the same community make the team. From the perspective of community detection, this paper solves the problems of doctor recommendation and team building, which results in more ideal results. And the community visualization paves the way for the recommendation system to be completed in the future.


Community detection, Doctor recommendation, Spectral clustering

Cite This Paper

Li Guo, Chenning Du. Doctor recommendation via community detection. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 3: 68-76. https://doi.org/10.25236/AJCIS.2021.040311.


[1] Coscia M, Giannotti F, Pedreschi D. A classification for community discovery methods in complex networks [J]. Statistical Analysis and Data Mining: The ASA Data Science Journal, 2011, 4(5): 512-546.

[2] Youcef Abdelsadek, Kamel Chelghoum, Francine Herrmann, Imed Kacem, Benoît Otjacques. Community extraction and visualization in social networks applied to Twitter [J]. Information Sciences, 2017.

[3] V. Blondel, J. Guillaume, R. Lambiotte, E. Mech. Fast unfolding of communities in large networks J. Stat. Mech (2008), p. P10008

[4] N. Schlitter, T. Falkowski, J. Lssig. Dengraph-ho: density-based hierarchical community detection for explorative visual network analysis Springer (Ed.), Research and Development in Intelligent Systems XXVIII Incorporating Applications and Innovations in Intelligent Systems XIX Proceedings of AI-2011, the Thirty-first SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, Springer, London (2011), pp. 283-296

[5] Y. Hu, J. Wu, Z. Di. Enhance the efficiency of heuristic algorithms for maximizing the modularity Q [J]. EPL (Europhysics Letters), 2009, 85(1).

[6] Cai Xiao-yan, Dai Guan-zhong, Yang Li-bin. Survey on sprctral clustering algorithms [J]. Computer science, 2008, 35(7):14-48.

[7] Zhu Z, Wang L. Initialization approach for fuzzy C-means algorithm for color image segmentation [J]. Application Research of Computers, 2015, 32(4):1257-1260.

[8] Liu Da-you, Jin Di, He Dong-xiao, Huang Jing, Yang Jian-ning, Yang Bo. Community mining in complex networks [J]. Journal of computer research and development, 2013, 50(10):2140-2154.

[9] Pan H F, Dong L, Chen J N, et al. Simulation of Shape Clustering Based on Spectral Graph Theory [J]. Journal of System Simulation, 2011, 23(7): 1409-1413. 

[10] Stephen Alstrup, Mikkel Thorup, Inge Li Gørtz, Theis Rauhe, Uri Zwick. Disjoint Set Union with Constant Time Deletions [J]. ACM Transactions on Algorithms (TALG), 2014, 1(6):1-28.

[11] M.Girvan, M.E.J.Newman. Communitys structure in social and biological networks [J]. PNAS, 2002, (99):7821-7826.

[12] Girvan M, Newman M. Community structure in social and biological networks [J].Proc Natl Acad Sci USA, 2002, 99:7821-7826.

[13] Newman M, Girvan M. Finding and evaluating community structure in networks [J]. Phycical Review E, 2004, 69: 026113.

[14] Newman MEJ. Fast algorithm for detecting community structure in networks[J]. Phycical Review E, 2004, 69(6): 066133.

[15] Grady L. Random walks for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(11): 1768-1783.

[16] Newman M E J. Fast algorithm for detecting community structure in networks [J]. Physical review E. 2004, 69 (6): 066133.

[17] Lancichinetti A, Fortunato S. Community detection algorithms: a comparative analysis [J]. Physical review E, 2009, 80(5): 056117.

[18] De Meo P, Ferrara E, Fiumara G, et al. Generalized louvain method for community detection in large networks[C]//Intelligent Systems Design and Applications (ISDA), 2011 11th International Conference on. IEEE, 2011: 88-93.

[19] Liu X, Murata T. Community detection in large-scale bipartite networks [J]. Information and Media Technologies, 2010, 5(1): 184-192.

[20] Papadopoulos S, Kompatsiaris Y, Vakali A, et al. Community detection in social media[J]. Data Mining and Knowledge Discovery, 2012, 24(3): 515-554.

[21] Plantié M, Crampes M. Survey on social community detection [M]//Social media retrieval. Springer, London, 2013: 65-85.

[22] Gargi U, Lu W, Mirrokni V S, et al. Large-Scale Community Detection on YouTube for Topic Discovery and Exploration[C]//ICWSM. 2011.

[23] Fortunato S. Community detection in graphs[J]. Physics reports, 2010, 486(3-5): 75-174.

[24] Newman M E J. Community detection and graph partitioning[J]. EPL (Europhysics Letters), 2013, 103(2): 28003.

[25] Newman M E J. Spectral methods for community detection and graph partitioning[J]. Physical Review E, 2013, 88(4): 042822.

[26] Chang Su,Yue Yu,Xianzhong Xie,Yukun Wang. Data Sensitive Recommendation Based On Community Detection [J]. Foundations of Computing and Decision Sciences,2015,40(2).

[27] Lian Duan,Yanchi Liu,W. Nick Street,Haibing Lu. Utilizing advances in correlation analysis for community structure detection [J]. Expert Systems With Applications, 2017,84.

[28] Lina Zhao, Hui Li.Evaluation index analysis of non- overlapping community detection algorithms[C].2014 Eighteenth Annual Conference on new technology and application for network of the network application branch of ACU,Kunming,Yunnan,ACU,Beijing,China,p.378-381.

[29] Yang Z, Algesheimer R, Tessone C J. A comparative analysis of community detection algorithms on artificial networks [J]. Scientific Reports, 2016, 6: 30750.

[30] Malliaros F D, Vazirgiannis M. Clustering and community detection in directed networks: A survey [J]. Physics Reports, 2013, 533(4): 95-142.

[31] Shang R, Bai J, Jiao L, et al. Community detection based on modularity and an improved genetic algorithm [J]. Physica A: Statistical Mechanics and its Applications, 2013, 392(5): 1215-1231.

[32] Chen M, Kuzmin K, Szymanski B K. Community detection via maximization of modularity and its variants[J]. IEEE Transactions on Computational Social Systems, 2014, 1(1): 46-65.

[33] Malliaros F D, Vazirgiannis M. Clustering and community detection in directed networks: A survey [J]. Physics Reports, 2013, 533(4): 95-142.

[34] Hanhua Chen,Hai Jin.The detection and evaluation of the community structure in the semantic peer-to-peer overlay network[J].Chinese Science: Information Science,2012,42(05):537-549.

[35] Wenwei Zhan,Jingke Xi,Zhixiao Wang.Hierarchical aggregation community detection algorithm based on similarity modularity[J].Journal of system simulation,2017,29(05):1028-1032+1040.

[36] Orman G K, Labatut V, Cherifi H. Comparative evaluation of community detection algorithms: a topological approach [J]. Journal of Statistical Mechanics: Theory and Experiment, 2012, 2012(08): P08001.