Interpreted social graph traversal algorithms for enhanced recommendation precision and efficiency in computational applications
Amita Yadav, Bijay Kumar Paikaray, Sandipan Pine, Jayanta Mondal, Shalu Mehta · International Journal of Applied Nonlinear Science · 2024
The social network recommendation algorithms focusing on two novel approaches: interpreted social breadth first search (BFS) and the interpreted social depth first search (DFS). These algorithms aim to enhance the recommendation process by leveraging insights from social network analysis, graph traversal techniques, and interpreted relevance measures. This investigation utilising a real dataset sourced from Amazon, we compare the performance of BFS and DFS against conventional recommendation methods such as item-based collaborative filtering and hybrid approaches. This research finding reveals that BFS and DFS not only exhibit commendable precision but also demonstrate superior efficiency in terms of runtime. Moreover, our analysis indicates that these algorithms effectively narrow down the search space within the dataset, contributing to computational savings. This report sheds light on the potential of integrating social network structures and Interpreted user profiles into recommendation systems, offering valuable insights for researchers and practitioners in the field of recommender systems.