Semantics-Based News Delivering Service

This paper proposes a semantic computing application for a news delivering service collects and recommends news articles which user feels interested in based on semantic relations between terms in the articles. We define interested articles as the ones that users have curiosity and serendipity. The semantic relations between terms are represented by graphs of Linked Data. We first create News Articles Linked Data, which are news articles for recommendation to users and User's preferences Linked Data created from the users' preferred articles. Then, common subgraphs between two graphs are searched for the recommendation of news articles. The experiment showed that the curiosity score is 3.30 (min:0, max:4), and the serendipity score is 2.93 in our approach, but a baseline method indicated the curiosity score: 3.03 and the serendipity score: 2.79. Thus, we confirmed that our approach is more effective than the baseline method. In the future, we will deploy our semantic technology to practical use for automatically delivering information selected from a vast amount of news sources.