Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-6973
Main Title: Semantic network skeletons - a tool to analyze spreading activation effects
Author(s): Hartig, Kerstin
Karbe, Thomas
Type: Conference Object
Language Code: en
Abstract: Spreading Activation algorithms are a well-known tool to determine relevance of nodes in a semantic network. Although often used, the configuration of a spreading activation algorithm is usually very problem-specific, and experience-driven. There are practically no guidelines or tools to help with the task. In this paper, we present semantic network skeletons, which are essentially a structural summary of a semantic network. We show how to derive the skeleton from a given semantic network, and how to derive conclusions about good configurations from it. Our results are then demonstrated in a case study from the automotive domain.
URI: https://depositonce.tu-berlin.de//handle/11303/7795
http://dx.doi.org/10.14279/depositonce-6973
Issue Date: 2016
Date Available: 15-May-2018
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): spreading activation
information retrieval
semantic network
advisory system
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: eKnow 2016 - The Eighth International Conference on Information, Process, and Knowledge Management
Publisher: IARIA
Publisher Place: Wilmington
Volume: 2016
Page Start: 126
Page End: 131
ISBN: 978-1-61208-472-5
ISSN: 2308-4375
Appears in Collections:FG IT-basierte Fahrzeuginnovationen » Publications

Files in This Item:
File Description SizeFormat 
2016_hartig_karbe.pdf970.38 kBAdobe PDFThumbnail
View/Open


Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.