Effective extraction method of the mutual understanding gap based on the egocentrism Online publication date: Sat, 07-Aug-2010
by Nobuo Suzuki, Kazuhiko Tsuda
International Journal of Computer Applications in Technology (IJCAT), Vol. 38, No. 4, 2010
Abstract: The prospect of widespreading the internet in the world is enabling new ways of solving our several problems with many Q&A web sites. It is difficult to say that smooth communication is carried out in these sites, because a lot of speakers may speak inconsistently in the same site at the same time. Therefore, we proposed to extract the egocentrism from language expressions in words at some Japanese Q&A sites and tried to extract the mutual understanding gap in these words based on the egocentrism in this paper. Specifically, we defined the intensity for properties of the egocentrism with the method that presumed the egocentrism from language expressions in our previous study. This method presumes mutual understanding gap in the text data of Q&A sites that have dialogue form by using the intensity and calculating the score of the egocentrism in each speech. This paper shows the characteristics of the gap are expressed by the shape of graphs with these scores. We also evaluate this method with text data in actual Q&A sites and confirm its effectiveness, describing the precision is 98.8%. It also analyses features for the mutual understanding gap at the Q&A site. It was identified that the score of the mutual understanding gap is evenly distributed and most communications are attempted by the few speeches.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com