CosMovis: Semantic Network Visualization based on Sentiment Words of Movie Review Data by Ajou University

This research facilitates the understanding of each node’s features through Heatmap visualization in creating network visualization, and suggests a clustering of nodes by connecting the sentiment words MDS Map and Social Network. This study on network visualization aims to design an efficient recommendation system which enables users to discover a movie based on sentiment words. And we mainly aimed to design a semantic network that minimizes network learning, and to develop a method to easily understand the node groups. Movie review data from online resources were applied in this research, and the process is as follows: 1) Calculated a frequency of sentiment words from each movie review. 2) Designed a Heatmap visualization to effectively discover the main emotions on each online movie review. 3) Formed a Sentiment-Movie Network combining the MDS Map and Social Network in order to fix the movie network topology, while creating a network graph to enable the clustering of similar nodes. 4) Applied the asterism graphic in order to impart the meaning in accordance with the characteristics of clustering for better cognitive interpretation. This research is expected to be adopted in another recommendation system since our method is applicable regardless of the number of review data, and even to other media contents such as web-based cartoons, music, and books, using assorted constellation images related to target field.