Estimation of friendship and hierarchy from conversation records

Authors:
Yoko Nishihara;Wataru Sunayama
Affiliations:
The University of Tokyo, 7-3-1, Hongo, Bunkyo, Tokyo 113-8656, Japan;Hiroshima City University, 3-4-1, Ozuka-Higashi, Asa-Minami, Hiroshima 731-3194, Japan
Venue:
Information Sciences: an International Journal
Year:
2009

Citing 7
Cited 0

Relevance: communication and cognition

Relevance: communication and cognition
A robust method for understanding NL interface commands in the ICI Intelligent Command Interpreter

Information Sciences—Informatics and Computer Science: An International Journal
Talking to UNIX in English: an overview of UC

Communications of the ACM
Email as spectroscopy: automated discovery of community structure within organizations

Communities and technologies
UK academic web links and collaboration - an exploratory study

Journal of Information Science
Topic and role discovery in social networks

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Previewing semantic web pipes

ESWC'08 Proceedings of the 5th European semantic web conference on The semantic web: research and applications

Quantified Score

Hi-index	0.07

Visualization

Abstract

We have developed a method for estimating the level of friendship between two people and the strength of their hierarchy. This information is important because building the relationships needed to create something new requires an understanding of current relationships. Using records of conversation among people, our method first identifies the sentence types and then uses the identified types to estimate the level of friendship and the strength of the hierarchy. Testing using records for various types of conversation demonstrated that this method can robustly estimate both values from one-person-fixed conversation records.