A Secure Hierarchical Agglomerative Clustering for Social Media Image Classification

Hierarchical clustering of social media data is frequent. Data points indicate clusters, and it combines the neighbouring clusters until one remains. Segment photos, analyze social networks, and cluster texts using hierarchical clustering. Hierarchical clustering can group related social media data pieces. Topic-grouping social media communications helps identify patterns. Segmenting images by colour, texture, and form may aid object recognition, face detection, and content-based image retrieval. Social connection hierarchical clustering organises persons or communities in social network analysis. This identifies influential persons and groups and explains social networks. Communities, co-authorship networks, and important actors can be identified on social media. This article analyses social media images ' visual and linguistic information using hierarchical agglomerative clustering. For social media content images from a data set named The experimental results were applied to a dataset named YasminNadiaArabcSocialMediaImages in Kaggle which contains images of famous Arabic social media celebrities, the clustering approach groups comparable pictures using TF-IDF vectorization for textual attributes and PCA and t-SNE for visuals.