.png){kind=icon}
.png){kind=icon}
Return
Modeling journal quality evaluation by enhancing population diversity based gene expression programming
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.127666.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Journal evaluation plays a crucial role in academic development and significantly influences the direction and quality of scholarly research. To address the limitations of traditional evaluation methods in integrating multidimensional indicators, this paper proposes a journal evaluation system based on Enhanced Population Diversity Gene Expression Programming (EPD-GEP). By incorporating a dual population generation strategy (DP) and a low fitness gene recombination mechanism (LR), the model's performance is substantially improved. Experimental results indicate that, compared with the traditional GEP algorithm, the EPD-GEP algorithm enhances optimal solution search and computational efficiency. Model validation demonstrates that the average prediction error of this evaluation system is only 0.11511, while its correlation coefficient with the journal impact factor reaches 0.9959, indicating outstanding predictive accuracy. Furthermore, the classification results of journals based on the proposed evaluation indexes achieve up to 95% consistency with the classification of Journal Citation Reports (JCR), fully confirming the model's reliability and practical applicability.
Keywords:
Journal evaluation
Gene Expression Programming
Multi-criteria evaluation
Population diversity
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W