Human-Network-based Filtering: The Information Propagation Model based on Word-of-Mouth Communication

• Authors: Susumu TAKEUCHI;Junzou KAMAHARA;Shinji SHIMOJO;Hideo MIYAHARA
• Venue: SAINT '03 Proceedings of the 2003 Symposium on Applications and the Internet
• Year: 2003

In the real world, people get filtered information throughword-of-mouth communication. This type of information is"filtered" because the information from one user to anotheris filtered by the people who pass the information to otherpeople. We propose an Information Propagation Model,which simulates word-of-mouth communication on a computer network. In this model, certain information of interestto a user is automatically distributed to neighboring users.Therefore, this model works as an information filtering system filtered by a human network. In this paper, we describethe concepts of this model, the features found in this model,and the preliminary experiment, which was carried out byreal users. Results of the experiment show both the effectiveness of filtering in our model, and also that the value ofinformation correlates closely with the distance from whichthe information was transferred.