Research Article
BibTex RIS Cite

Identification of Influencer with Machine Learning Using Centrality Measures in Social Networks

Year 2024, , 166 - 172, 30.04.2024
https://doi.org/10.53433/yyufbed.1348472

Abstract

Detection of influencers in social networks is an essential problem for many areas in practice, such as public opinion shaping, viral marketing, and preventing the spread of rumors. For this, it is necessary to estimate how much influence each individual has according to their position on the network. For this purpose, network centrality measures, which provide information about the position of individuals on the network, are frequently used in the literature. Most existing studies try to rank individuals on social networks according to their influence and thus identify the most influential people. On the other hand, a tiny percentage of individuals on a social network are influencers. In this regard, instead of trying to rank all individuals according to their influence, it is sufficient for many applications to divide potential influencers and other individuals into two classes. In this study, we considered the detection problem of influencers as a binary classification problem. We determined the centrality measures of individuals as features and classified the individuals as the influencers and the others with the Decision Tree classifier. Experimental studies have shown that the Decision Tree classifier gives more successful results than the basic centrality measures.

References

  • Azaouzi, M., Mnasri, W., & Romdhane, B. L. (2021). New trends in influence maximization models. Computer Science Review, 40, 100393. doi:10.1016/j.cosrev.2021.100393
  • Borgatti, S. P. (2006). Identifying sets of key players in a social network. Computational and Mathematical Organization Theory, 12(1), 21-34. doi:10.1007/s10588-006-7084-x
  • Guo, J., & Wu, W. (2021). Adaptive influence maximization. ACM Transactions on Knowledge Discovery from Data, 15(5), 1-23. doi:10.1145/3447396
  • Kempe, D., Kleinberg, J., & Tardos, É. (2003, August). Maximizing the spread of influence through a social network. International Conference on Knowledge Discovery and Data mining, New York, USA.
  • Keng, Y. Y., Kwa, K. H., & McClain, C. (2020). Convex combinations of centrality measures. Journal of Mathematical Sociology, 45(4), 195-222. doi:10.1080/0022250X.2020.1765776
  • Li, D., Wang, C., Zhang, S., Zhou, G., Chu, D., & Wu, C. (2017). Positive influence maximization in signed social networks based on simulated annealing. Neurocomputing, 260, 69-78. doi:10.1016/j.neucom.2017.03.003
  • McAuley, J., & Leskovec, J. (2012). Learning to discover social circles in ego networks. NIPS’12 Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, USA.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., …, & Duchesnay, E. (2011). Scikit-learn: Machine Learning in {P}ython. Journal of Machine Learning Research, 12, 2825–2830.
  • Rezaei, A. A., Munoz, J., Jalili, M., & Khayyam, H. (2023). A machine learning-based approach for vital node identification in complex networks. Expert Systems with Applications, 214, 119086. doi:10.1016/j.eswa.2022.119086
  • Sabah, L., & Şimşek, M. (2023). A new fast entropy‐based method to generate composite centrality measures in complex networks. Concurrency and Computation: Practice and Experience, 35(10). doi:10.1002/cpe.7657
  • Salavati, C., Abdollahpouri, A., & Manbari, Z. (2019). Ranking nodes in complex networks based on local structure and improving closeness centrality. Neurocomputing, 336, 36-45. doi:10.1016/j.neucom.2018.04.086
  • Saxena, A., & Iyengar, S. (2020). Centrality measures in complex networks: A survey. doi:10.48550/arXiv.2011.07190
  • Sheng, J., Dai, J., Wang, B., Duan, G., Long, J., Zhang, J., …, & Guan, W. (2020). Identifying influential nodes in complex networks based on global and local structure. Physica A: Statistical Mechanics and its Applications, 541, 123262. doi:10.1016/j.physa.2019.123262
  • Şimşek, M., & Meyerhenke, H. (2020). Combined centrality measures for an improved characterization of influence spread in social networks. Journal of Complex Networks, 8(1), cnz048. doi:10.1093/comnet/cnz048
  • Şimşek, A. (2021). Lexical sorting centrality to distinguish spreading abilities of nodes in complex networks under the Susceptible-Infectious-Recovered (SIR) model. Journal of King Saud University - Computer and Information Sciences, 34(8), 4810-4820. doi:10.1016/j.jksuci.2021.06.010
  • Wang, S., Liu, J., & Jin, Y. (2019). Finding influential nodes in multiplex networks using a memetic algorithm. IEEE Transactions on Cybernetics, 51(2), 1-13. doi:10.1109/TCYB.2019.2917059
  • Wen, T., Pelusi, D., & Deng, Y. (2020). Vital spreaders identification in complex networks with multi-local dimension. Knowledge-Based Systems, 195, 105717. doi:10.1016/j.knosys.2020.105717
  • Yang, Y., Wang, X., Chen, Y., Hu, M., & Ruan, C. (2020). A novel centrality of influential nodes identification in complex networks. IEEE Access, 8, 58742-58751. doi:10.1109/ACCESS.2020.2983053
  • Zengin Alp, Z., & Gündüz Öğüdücü, Ş. (2018). Identifying topical influencers on twitter based on user behavior and network topology. Knowledge-Based Systems, 141, 211–221. doi:10.1016/j.knosys.2017.11.021
  • Zhang, Z., Li, X., & Gan, C. (2021). Identifying influential nodes in social networks via community structure and influence distribution difference. Digital Communications and Networks, 7(1), 131-139. doi:10.1016/j.dcan.2020.04.011
  • Zhao, J., Wang, Y., & Deng, Y. (2020a). Identifying influential nodes in complex networks from global perspective. Chaos, Solitons and Fractals, 133, 109637. doi:10.1016/j.chaos.2020.109637
  • Zhao, G., Jia, P., Huang, C., Zhou, A., & Fang, Y. (2020b). A machine learning based framework for identifying influential nodes in complex networks. IEEE Access, 8, 65462-65471. doi:10.1109/ACCESS.2020.2984286
  • Zhuang, Y.-B., Li, Z.-H., & Zhuang, Y.-J. (2021). Identification of influencers in online social networks: measuring influence considering multidimensional factors exploration. Heliyon, 7(4), e06472. doi:10.1016/j.heliyon.2021.e06472

Sosyal Ağlarda Merkezilik Ölçütleri Kullanılarak Makine Öğrenmesi İle Etkili Bireylerin Tespiti

Year 2024, , 166 - 172, 30.04.2024
https://doi.org/10.53433/yyufbed.1348472

Abstract

Sosyal ağlardaki etkili bireylerin tespiti, kamuoyu şekillendirme, viral pazarlama, dedikodu yayılımını önleme gibi pratikte birçok alan için önemli bir problemdir. Bunun için her bir bireyin ne kadar etkiye sahip olduğunun, bireyin ağ üzerindeki konumuna göre tahmin edilmesi gerekmektedir. Bu amaçla, bireylerin ağ üzerindeki konumları ile ilgili bilgi veren ağ merkezilik ölçütleri literatürde sıklıkla kullanılmaktadır. Mevcut çalışmaların büyük bir kısmı, sosyal ağlardaki bireyleri etkilerine göre sıralamaya ve bu şekilde en etkili kişileri tespit etmeye çalışırlar. Öte yandan, bir sosyal ağ üzerindeki bireylerin çok küçük bir kısmı gerçekten etkili bireydir. Bu bakımdan, bütün bireyleri etkilerine göre bir sıraya koymaya çalışmak yerine, etkili olabilecek bireyleri ve diğer bireyleri iki sınıfa ayırmak birçok uygulama için yeterlidir. Biz bu çalışmada, etkili birey tespiti problemini ikili sınıflandırma problemi olarak ele aldık. Bireylerin merkeziyet ölçütlerini birer öznitelik olarak belirleyip, Karar Ağacı sınıflandırıcı ile bireyleri etkili ve değil şeklinde sınıflandırdık. Deneysel çalışmalar; Karar Ağacı sınıflandırıcının, temel merkezilik ölçütlerine göre daha başarılı sonuçlar verdiğini göstermiştir.

References

  • Azaouzi, M., Mnasri, W., & Romdhane, B. L. (2021). New trends in influence maximization models. Computer Science Review, 40, 100393. doi:10.1016/j.cosrev.2021.100393
  • Borgatti, S. P. (2006). Identifying sets of key players in a social network. Computational and Mathematical Organization Theory, 12(1), 21-34. doi:10.1007/s10588-006-7084-x
  • Guo, J., & Wu, W. (2021). Adaptive influence maximization. ACM Transactions on Knowledge Discovery from Data, 15(5), 1-23. doi:10.1145/3447396
  • Kempe, D., Kleinberg, J., & Tardos, É. (2003, August). Maximizing the spread of influence through a social network. International Conference on Knowledge Discovery and Data mining, New York, USA.
  • Keng, Y. Y., Kwa, K. H., & McClain, C. (2020). Convex combinations of centrality measures. Journal of Mathematical Sociology, 45(4), 195-222. doi:10.1080/0022250X.2020.1765776
  • Li, D., Wang, C., Zhang, S., Zhou, G., Chu, D., & Wu, C. (2017). Positive influence maximization in signed social networks based on simulated annealing. Neurocomputing, 260, 69-78. doi:10.1016/j.neucom.2017.03.003
  • McAuley, J., & Leskovec, J. (2012). Learning to discover social circles in ego networks. NIPS’12 Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, USA.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., …, & Duchesnay, E. (2011). Scikit-learn: Machine Learning in {P}ython. Journal of Machine Learning Research, 12, 2825–2830.
  • Rezaei, A. A., Munoz, J., Jalili, M., & Khayyam, H. (2023). A machine learning-based approach for vital node identification in complex networks. Expert Systems with Applications, 214, 119086. doi:10.1016/j.eswa.2022.119086
  • Sabah, L., & Şimşek, M. (2023). A new fast entropy‐based method to generate composite centrality measures in complex networks. Concurrency and Computation: Practice and Experience, 35(10). doi:10.1002/cpe.7657
  • Salavati, C., Abdollahpouri, A., & Manbari, Z. (2019). Ranking nodes in complex networks based on local structure and improving closeness centrality. Neurocomputing, 336, 36-45. doi:10.1016/j.neucom.2018.04.086
  • Saxena, A., & Iyengar, S. (2020). Centrality measures in complex networks: A survey. doi:10.48550/arXiv.2011.07190
  • Sheng, J., Dai, J., Wang, B., Duan, G., Long, J., Zhang, J., …, & Guan, W. (2020). Identifying influential nodes in complex networks based on global and local structure. Physica A: Statistical Mechanics and its Applications, 541, 123262. doi:10.1016/j.physa.2019.123262
  • Şimşek, M., & Meyerhenke, H. (2020). Combined centrality measures for an improved characterization of influence spread in social networks. Journal of Complex Networks, 8(1), cnz048. doi:10.1093/comnet/cnz048
  • Şimşek, A. (2021). Lexical sorting centrality to distinguish spreading abilities of nodes in complex networks under the Susceptible-Infectious-Recovered (SIR) model. Journal of King Saud University - Computer and Information Sciences, 34(8), 4810-4820. doi:10.1016/j.jksuci.2021.06.010
  • Wang, S., Liu, J., & Jin, Y. (2019). Finding influential nodes in multiplex networks using a memetic algorithm. IEEE Transactions on Cybernetics, 51(2), 1-13. doi:10.1109/TCYB.2019.2917059
  • Wen, T., Pelusi, D., & Deng, Y. (2020). Vital spreaders identification in complex networks with multi-local dimension. Knowledge-Based Systems, 195, 105717. doi:10.1016/j.knosys.2020.105717
  • Yang, Y., Wang, X., Chen, Y., Hu, M., & Ruan, C. (2020). A novel centrality of influential nodes identification in complex networks. IEEE Access, 8, 58742-58751. doi:10.1109/ACCESS.2020.2983053
  • Zengin Alp, Z., & Gündüz Öğüdücü, Ş. (2018). Identifying topical influencers on twitter based on user behavior and network topology. Knowledge-Based Systems, 141, 211–221. doi:10.1016/j.knosys.2017.11.021
  • Zhang, Z., Li, X., & Gan, C. (2021). Identifying influential nodes in social networks via community structure and influence distribution difference. Digital Communications and Networks, 7(1), 131-139. doi:10.1016/j.dcan.2020.04.011
  • Zhao, J., Wang, Y., & Deng, Y. (2020a). Identifying influential nodes in complex networks from global perspective. Chaos, Solitons and Fractals, 133, 109637. doi:10.1016/j.chaos.2020.109637
  • Zhao, G., Jia, P., Huang, C., Zhou, A., & Fang, Y. (2020b). A machine learning based framework for identifying influential nodes in complex networks. IEEE Access, 8, 65462-65471. doi:10.1109/ACCESS.2020.2984286
  • Zhuang, Y.-B., Li, Z.-H., & Zhuang, Y.-J. (2021). Identification of influencers in online social networks: measuring influence considering multidimensional factors exploration. Heliyon, 7(4), e06472. doi:10.1016/j.heliyon.2021.e06472
There are 23 citations in total.

Details

Primary Language Turkish
Subjects Information Systems (Other)
Journal Section Engineering and Architecture / Mühendislik ve Mimarlık
Authors

Aybike Şimşek 0000-0002-1033-1597

Publication Date April 30, 2024
Submission Date August 23, 2023
Published in Issue Year 2024

Cite

APA Şimşek, A. (2024). Sosyal Ağlarda Merkezilik Ölçütleri Kullanılarak Makine Öğrenmesi İle Etkili Bireylerin Tespiti. Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(1), 166-172. https://doi.org/10.53433/yyufbed.1348472