In today's technological landscape, recommender systems provide essential personalized suggestions by leveraging user preferences. This study evaluates the computational performance of User-Based (UBCF) and Model-Based Collaborative Filtering (MBCF) as intelligent computing systems on the MovieLens 1M dataset, comparing performance on complete data versus partitions based on age and occupation. Using MAE and RMSE metrics with an 80/20 train-test split, we assessed UBCF with Euclidean/Cosine similarity and MBCF with NMF/SVD. Results show MBCF with SVD achieved the best performance (MAE: 0.6909, RMSE: 0.8761), outperforming UBCF by approximately 5.2% in MAE and 5.1% in RMSE (p $<$ 0.05). Thi... More >

The growing role of citation relations in identifying research impact has spurred much investigation on assessing the most cited papers and their roles within datasets. Due to the richness of the CORA dataset, this study selects highly cited papers and measures the results of node classification, as well as the H-index of research articles. Besides, it explores the correlations and robustness with regard to the nodes by computing their chances and studying their connections. To these ends, linear transformation was utilized for mapping low-level node features to high-level, and the Graph Attention Networks (GAT) for node classification. The study was able to find highly cited papers and comp... More >