Keyword co-occurrence analysis is essential for understanding emerging trends in research and discovering specific studies. The process of detecting communities by the group nodes in a network based on their interconnection as a structure is called community detection. The community detection algorithm helps analyze and detect the real connection as clusters as a structure within the network. Visualization is one of the significant ways to understand complex networks like community structures. The main aim of this work focuses on visualizing the detected communities based on the co-occurrence of keywords using traditional community detection algorithms. The methodology involves a process of gathering deep learning-based articles from Scopus Bibliographic Dataset (SBD) information based on three major time frames as network datasets, namely SBD_1 as 2006-2013, SBD_2 as 2014-2016 and SBD_3 as 2017. This data is mainly worked with Indexed keyword fields as nodes and their weighted co-occurrences as edges into networks. This work proposed a framework for converting the bibliographic data into graphs for visualizing the detected communities. This work helps scholars to understand the connections among keywords and patterns for their effective research works like extracting academic research articles through exact keyword matching.
Keywords: Community Detection, Visualization, Scopus Bibliometric Data, co-occurrence Networks, Complex Network.
How to cite this article: R K, Sakkarapani K, Visualizing the Detected Communities Using Traditional Algorithms on Keyword Co-occurrence Networks. Int J Drug Deliv Technol. 2026;16(2s): 1009-1019; DOI: 10.25258/ijddt.16.1009-1019