Support System for Summarizing Multiple Sentences by Displaying Common Related Words

Abstract

In recent years, advances in Internet technology have made it possible for people to obtain large amounts of data. When analyzing such data, the process of finding commonalities can be time-consuming, or people tend to focus only on commonalities that are easy to imagine, making it difficult to discover new knowledge. The purpose of this study is to support the prevention of missing simple commonalities and the discovery of difficult to imagine commonalities among multiple sentences by collecting words that can be commonalities using Web search and creating and displaying a network of these words. Experimental results show that the system can support the discovery of both easy to imagine commonalities and difficult to imagine commonalities.