Degree
Master of Science in Data Science
Department
Department of Computer Science
Faculty/ School
School of Mathematics and Computer Science (SMCS)
Date of Submission
Fall 2022
Supervisor
Dr. Faraz Ahmed Zaidi, Assistant Professor, Department of Computer Science, School of Mathematics and Computer Science (SMCS)
Keywords
Machine Learning, Deep Learning, Social Network Analysis, Centrality Matrix, Influence Maximization
Abstract
Influential nodes in the system play a critical role in the structure and dynamics of the network. Identifying influential nodes in these networks is a major issue that has attracted considerable attention in recent years. It is useful to understand the behaviour of complex networks, such as social networks, biological networks, communication, transportation networks, etc. The aim of this research is to identify these significant nodes or influencers so that they can be targeted for controlling disease outbreaks, identifying infectious nodes in computer networks, finding super spreaders for viral marketing in social networks, and information dissemination purposes. In order to do this, it is necessary to analyze the network structure and identify influential nodes that have a high degree of connectivity or centrality. Centrality measures provide an indication of how important a particular node is in terms of its influence within the network. This paper proposes an approach to solve this problem by modeling it as a supervised machine learning problem. The experiments are conducted on both artificial and real-world networks to demonstrate the effectiveness of our approach in selecting influential nodes with nodal and network level attributes that are used to train supervised learning models, considering two approaches machine learning and deep learning, results showed that machine learning approach is better in identifying influential nodes in the network and less time consuming than deep learning approach. Moreover, our approach is robust to changes in network topology or node attributes. In conclusion, this paper provides an effective framework for selecting influential nodes from real-world networks. Finally, the results presented in this paper can serve as a baseline for future work on selecting influential nodes from real-world networks.
Document Type
Restricted Access
Submission Type
Research Project
Recommended Citation
Moin, H. (2022). Influence maximization in City Network using Supervised Machine Learning and Deep Learning (Unpublished graduate research project). Institute of Business Administration, Pakistan. Retrieved from https://ir.iba.edu.pk/research-projects-msds/11
The full text of this document is only accessible to authorized users.
