Monica, Theodora Monica (2025) Prediction of Citations Increase in Scopus Documents Based on Neural Network / Theodora Monica</p>. Diploma thesis, Universitas Negeri Malang.
Full text not available from this repository.Abstract
p Citation is an important indicator in assessing the contribution and impact of scientific work in the academic world. Citation not only reflects recognition of previous research but also affects the reputation of authors and institutions. Scopus as the largest citation database has an important role in measuring the quality of scientific publications. State University of Malang has many Scopus indexed publications so it is important to analyze and predict the number of citations to understand trends and improve research quality and visibility. This prediction can be done using Neural Network algorithm which excels in handling complex data automatically. This research proves that the Neural Network algorithm can be used effectively to predict the increase in the number of citations on Scopus documents by utilizing several attributes such as document type open access status number of foreign affiliates number of authors number of authors affiliated with foreign institutions as well as labels resulting from the clustering process. After going through the data preparation stage to clustering predictions were made using the Neural Network algorithm with cross-validation and evaluation through accuracy precision recall and F1-Score metrics. The initial model showed a high accuracy rate of 98.46% with excellent performance in the low class (F1-score 99.32%) but very low in the high class (F1-score 0.00%) due to data imbalance. To overcome this data balancing using the SMOTE method was performed which successfully increased the F1-score on the high class to 74.19% but resulted in a decrease in overall accuracy to 81.27%. Although the model became more sensitive to the minority class this data redistribution led to a decrease in performance on the majority class. /p
| Item Type: | Thesis (Diploma) |
|---|---|
| Divisions: | Fakultas Teknik (FT) > Departemen Teknik Elektro (TE) > S1 Teknik Informatika |
| Depositing User: | library UM |
| Date Deposited: | 13 Aug 2025 04:29 |
| Last Modified: | 09 Sep 2025 03:00 |
| URI: | http://repository.um.ac.id/id/eprint/400161 |
Actions (login required)
 |
View Item |