QML Based Community Detection in the realm of Social Network Analysis

Social network analysis (SNA) has been the topic of interest for researchers and analysts for quite a while as social networks have become the indispensable part of the semantic web. SNA has now forked itself into community detection to cater to the needs of business analytics, health monitoring, military, academia, recommendation systems, etc.; thus utilizing and processing huge amount of data. In this regard, quantum computing (QC) has has come in time to augment the classical systems with quantum characteristics ensuring unprecedented data storage and manipulation capabilities. It thus becomes necessary to facilitate effective data utility in SNA by incorporating emerging technologies like QML (Quantum machine learning) in the domain of community detection. The paper aims to present a brief insight into social network analysis and community detection highlighting the limitations prevalent in the current technologies. A systematic analysis of evolution of QML from QC has been presented whilst reviewing and discussing the relevance of QML based community detection algorithms in resolving the issues associated with the current approaches. Lastly, QML has been proposed as a novel approach to harness the power of ML (Machine learning) in quantum empowered systems by illustrating its supremacy to classical ML based community detection algorithms.