An Enhanced Data Analysis Method for Teaching Evaluation Utilizing the Infomap Algorithm

DOI: https://doi.org/10.62517/jhet.202515418

Author(s)

Xiaoxu Xia1, Min Gong1, Kexi Liao2, Chi Zhang1,*, Jun Hong2

Affiliation(s)

1School of Sciences, Southwest Petroleum University, Chengdu, China 2Dean’s Office, Southwest Petroleum University, Chengdu, China

Abstract

With advancing educational informatization, universities now define evaluation indicators and collect extensive teaching data online. This study introduces an integrated analytical method for the evaluation of teaching that addresses persistent challenges of score inflation and limited discriminatory power in traditional methods. By combining the Continuous Golden Section Method (CGSM) with Infomap-based community detection, the method dynamically reconfigures scoring intervals using a golden-ratio-based algorithm (λ=0.618) to compress high-score regions and expand critical lower ranges, thereby resolving classification ambiguities caused by static thresholds. The network architecture employs bidirectional weighted connections derived from dual similarity criteria—k-nearest neighbors (k=6) and absolute distance thresholds (d=0.05)—to enhance clustering robustness in similarity-dense teacher populations through symmetric adjacency relationships. Multidimensional performance profiling is achieved via community-level mean analysis, enabling both comprehensive evaluation results of teachers and specific indicator diagnosis results. Unlike conventional weighted aggregation approaches, this method simultaneously tackles data distribution biases, network construction challenges in high-similarity environments, and holistic evaluation demands. Experimental validation using real-world university data demonstrates the model’s viability, highlighting its ability to redefine rating ranges and improve distinctions among closely clustered teacher cohorts. The method advances educational evaluation by providing a mathematically rigorous, network-enhanced solution that prioritizes fairness and nuanced analysis, moving beyond oversimplified overall scores ranking to deliver actionable insights into specific teaching strengths and weaknesses.

Keywords

Teaching Evaluation; Internet Technologies; Complex Networks; Infomap; Golden Section

References

[1]Chen C. Y., Wang S. Y., Yang Y. F. A Study of the Correlation of the Improvement of Teaching Evaluation Scores Based on Student Performance Grades. International Journal of Higher Education, 2017, 6(2): 162-168. [2]Zhao J. Z. Multiple regression analysis model and its application to teaching level prediction. Science and Technology Wind, 2018, (33): 45-46. [3]Jiang H. F., Zhu W. J. Teaching evaluation model based on entropy method. Proceedings of the Journal of Hubei University of Technology, 2009, 24(4): 91-93. [4]Ding J. L., Ye J. H. Application of Analytic Hierarchy Process and fuzzy comprehensive Evaluation in Classroom teaching quality evaluation. Proceedings of the Journal of Wuhan University (Humanities Edition), 2003, 56(2): 241-246. [5]Yi W. H. Application of Weighted Comprehensive Evaluation Model in Teaching Quality Evaluation System of Computer Class Vocational Education. Applied Mathematics and Nonlinear Sciences, 2024, 9(1): 1-15. [6]Yuan Y. Enhanced EDAS technique for colleges business English teaching quality evaluation based on Euclid distance and cosine similarity measure. Journal of Intelligent & Fuzzy Systems, 2024, 46(1): 75-89. [7]Zhang J. B., Zhang C. Teaching quality monitoring and evaluation of physical education teaching in ordinary college based on edge computing optimization model. Journal of Supercomputing, 2023, 79(15): 16559-16579. [8]He J. J., Ye M. L. Evaluation method of online teaching effect for physical education based on fuzzy k-means clustering. Proceedings of Jilin University (Information Science Edition), 2023, 40(2): 301-306. [9]Sheng W. X., Wang H., Dong X. R., Xie G. H. Research on support vector Machine-based teaching level evaluation model in universities. Proceedings of Computer Knowledge and Technology, 2019, (13): 3165-3168. [10]Liu L. Smart teaching evaluation model using weighted naive bayes algorithm. Journal of Intelligent & Fuzzy Systems, 2020, 40(2): 1-11. [11]Gu Y. R. Exploring the application of teaching evaluation models incorporating association rules and weighted naive Bayesian algorithms. Intelligent Systems with Applications, 2023, 20: 200297. [12]Lou M. S. Evaluation of College English Teaching Quality Based on Improved T-SVM Algorithm. Computational Intelligence and Neuroscience, 2022, 2022: 2974813. 10.1155 [13]Li C. Simulation of University Teaching Achievement Evaluation Based on Deep Learning and Improved Vector Machine Algorithm.". Applied Artificial Intelligence, 2023, 37(1): 2195221. [14]Wang L., Zhang H. J. Research on teaching quality evaluation system with integrated neural network. Proceedings of Modern Electronic Technology, 2021, 44(3): 6-73. [15]Liu T., Ning L. Deep convolutional neural network and weighted Bayesian model for evaluation of college foreign language multimedia teaching. Proceedings of Wireless Communications and Mobile Computing, 2021, 2021(3): 1-7. [16]Lin X. Q., “Research on teaching evaluation methods based on multivariate outlier detection,” East China jiaotong university. [17]Kong L. Performance evaluation model for operation research teaching based on IoT and Bayesian network technology. Soft Computing, 2024, 28: 3613-3631. [18]Ke W. J., Wei J. G., Xiong N. X., Hou Q. Z. GSS: A group similarity system based on unsupervised outlier detection for big data computing.". Proceedings of Information Sciences 2023, 619: 1-15. [19]Rosvall M., Axelsson D., Bergstrom C.T. The map equation. European Physical Journal Special Topics, 2010, 178: 13-23. [20]Rosvall M., Ergstrom C. T. Maps of random walks on complex networks reveal community structure. Proceedings of the National Academy of Sciences, 2008, 105(4): 1118-1123. [21]Li H., Chen F. C., Zhang J. P., Wu Z., Li S. M., Huang R. Y. Community discovery algorithms in complex networks. Application Research of Computers, 2021, volume 38 (6): 1611-1618. [22]Liu Y. C., Gao X. D., Guo H. W., Wu S. Combination evaluation method of cluster validity. Computer Engineering and Applications (19): 15-17.