A Methodology for Brand Name Hierarchical Clustering Based on Social Media Data

Clustering of brand names is a common technique for identification of different groups of brand names with maximum effectiveness and similarities. In this study, we proposed a methodology for brand name clustering, based on data from social media like Twitters. Dataset consist of tweets mentioning various garment brands in them. In order to cluster the brand names, we have proposed an algorithm, named BNACA (Brand Names Agglomerate Clustering Algorithm), an extension to the standard hierarchical clustering algorithm. In the proposed algorithm, we used single linkage as a similarity measure. The proposed clustering algorithm provides consistent clustered results for various sets of brand names of garment industry. Finally, clusters of garment brand names are visualized through dendogram. The dendogram clearly shows the maximum similarities among garment brand names.