Kaoru Sumi

Public opinion channel for communities in the information age

In this paper, we propose as a new challenge a public opinion channel which can provide a novel communication medium for sharing and exchanging opinions in a community. Rather than simply developing a means of investigating public opinion, we aim at an active medium that can facilitate mutual understanding, discussion, and public opinion formation. First, we elaborate the idea of public opinion channels and identify key issues. Second, we describe our first step towards the goal using the talking virtualized egos metaphor. Finally, we discuss a research agenda towards the goal.

Telme: a personalized, context-aware communication support system

True global communication will require more than just language translation technologies. To fully understand each other, people also need context-specific information. The authors have developed Telme, a support system that gives users real-time information to help bridge the knowledge and experience gap. The authors explain the Telme framework for wearable computers connected to a central knowledge base server. The server controls a background knowledge database and downloads data on user request.

Takealook: personalizing information presentation according to user's interest space

In this paper, we present a system called Takealook, which personalizes information presentation according to individual interests and knowledge of the user. The basic idea is that the system infers a users interests and personalizes information presentation by processing the users operation history and the interest space. The users interest space is structured from the presenters individual conceptual space and the users operation history, which is acquired through question-answer interactions between the user and the system. We employ a method similar to collaborative filtering for improving interest spaces.

Communication support system adapted to a user's background knowledge and the topic context

This paper proposes a technique for interpolating the information in a real-time conversation via computer between a speaker and listener to compensate for differences in the knowledge presumed for the conversation and introduces Telme, a communications support system that uses this technique. The basic premises are that the system infers the context of the current topic based on the terms used by the speaker and infers the listeners degree of knowledge from the listeners questions and a history of operations such as operations for saving certain data. It then supplements the text information of the words dictated by the speaker with information that the listener should require based on those inferences and displays it on the screen. The degree of knowledge is inferred based on the users conceptual space, which was generated by using multiple conceptual spaces that were created based on the views and opinions of specialists in various fields. The users conceptual space, which consists of a set of key words having interrelationships, is adapted to the user by functions for inferring those relationships and the users degree of knowledge through the users interactions with the computer. This paper proposes a technique, explains basic mechanisms, and reports on and examines application examples and evaluation experiments.