Social Networks for Establishing Clustering Relationships on Instagram Social Media
Keywords:Social Network, Clustering Relationships, Social Media, Instagram.
Instagram is a social media that is widely used for marketing media. The amount of information on social media makes it difficult for users to get information that suits their interests. The growing social network provides opportunities for researchers to use them in research in various fields. Social network can be said to affect user behavior so that in this study the formation of clustering relationships was carried out based on the relationships obtained from social networks. The recommendation system is a system that can sort and narrow the scope of information in making decisions. The previous recommendation system has not considered the relationship between users that can be used as a part that will affect a recommendation system. The steps taken are scrapping first to get the existing relationships on the Instagram account, then building a cluster using the Louvain algorithm. The results of the formation of clusters obtained the best value of modularity is 0.879 with the number of clusters as many as 27 clusters. Rating prediction is done using collaborative filtering so that there are 100% of no unfilled values. This research produces clusters, where in each cluster that is formed has novels that are of interest to the community in the cluster are different novels, so that if there are new users who follow other users, the user will be recommended novels that are appropriate to the community owned by the other user.
How to Cite
Copyright (c) 2021 I T A L I E N I S C H
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.