Predicting relevant empty spots in social interaction

a r X i v :0711.1466v 3 [c s .A I ] 21 F e

b 2008Jrl Syst Sci &Complexity (*)*:1–11

PREDICTING RELEV ANT EMPTY SPOTS IN

SOCIAL INTERACTION

Yoshiharu MAENO ·Yukio OHSA W A Received:August 15,2007c 2006Springer Science +Business Media,Inc.Abstract An empty spot refers to an empty hard-to-?ll space which can be found in the records of the social interaction,and is the clue to the persons in the underlying social network who do not appear in the records.This contribution addresses a problem to predict relevant empty spots in social interaction.Homogeneous and inhomogeneous networks are studied as a model underlying the social interaction.A heuristic predictor function method is presented as a new method to address the problem.Simulation experiment is demonstrated over a homogeneous network.A test data set in the form of market baskets is generated from the simulated communication.Precision to predict the empty spots is calculated to demonstrate the performance of the presented method.Key words Communication,Empty spot,Predictor function,Social interaction,Social network 1Problem -empty spot The activity of an organization is often under the in?uence of hidden but relevant persons.The activity refers to decision-making and action-taking.In this contribution,the word hidden means unobserved (unobservable)or invisible by the method used in the observation,rather than anonymous.The invisibility of the hidden persons is caused from the limited capability of the observation method,or from the limited prior understanding of the targets to observe.The organization may be a family,school,company,community,society etc.For example,a ?nancially supporting conspirator,who provides commanders with money,

communication means,or weapons,is often hidden behind terrorism 19885e2cb4daa58da0114aabmanders would appear one after another if such a conspirator were not detected and arrested.It is,therefore,critical to predict the presence of such hidden but relevant persons from the observed records on the social interactions of an organization.Based on the prediction,we can invent a scenario for proactive investigation.The scenario turns the threat of disasters from the terrorism attacks into the opportunity to discover and destroy the hidden conspirator’s social network supporting terrorism.

We de?ne the above problem more speci?cally with three ideas.They are social interaction ,social network ,and empty spot .

本文来源：https://www.bwwdw.com/article/mjaq.html