Extended framework for target oriented network intelligence collection

Liron Samama-Kachko, Rami Puzis, Roni Stern, Ariel Felner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

The Target Oriented Network Intelligence Collection (TONIC) problem is the problem of finding profiles in a social network that contain publicly available information about a given target profile via automated crawling. Such profiles are called leads. Leads can be found by crawling the network using the profiles’ friend lists (immediate neighborhood) in order to decide which profile will be crawled next. Assuming that leads tend to cluster together, prior work limited the search for new leads only to immediate neighbors of the leads previously found. In this paper we relax this limitation, and extend the scope of the search to a wider neighborhood, including the possibility of crawling to non-leads, i.e., profiles that have no publicly available information about the target. We propose a set of heuristics that guide this search. Experimental results show that with the new setting more leads can be found and leads are found faster. In addition, we perform a cost benefit analysis of the search, weighing the reward of finding leads with the costs of the search.

Original languageEnglish
Title of host publicationProceedings of the 7th Annual Symposium on Combinatorial Search, SoCS 2014
EditorsStefan Edelkamp, Roman Bartak
PublisherAAAI press
Pages131-138
Number of pages8
ISBN (Electronic)9781577356769
StatePublished - 2014
Externally publishedYes
Event7th Annual Symposium on Combinatorial Search, SoCS 2014 - Prague, Czech Republic
Duration: 15 Aug 201417 Aug 2014

Publication series

NameProceedings of the 7th Annual Symposium on Combinatorial Search, SoCS 2014
Volume2014-January

Conference

Conference7th Annual Symposium on Combinatorial Search, SoCS 2014
Country/TerritoryCzech Republic
CityPrague
Period15/08/1417/08/14

Bibliographical note

Publisher Copyright:
Copyright © 2014,Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Fingerprint

Dive into the research topics of 'Extended framework for target oriented network intelligence collection'. Together they form a unique fingerprint.

Cite this