Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Web mining based extraction of problem solution ideas

 
: Thorleuchter, Dirk; Van den Poel, Dirk

:
Preprint urn:nbn:de:0011-n-2418025 (572 KByte PDF)
MD5 Fingerprint: 82f917b7377fa17bf51e690e37dccf39
Created on: 24.7.2013


Expert Systems with Applications 40 (2013), No.10, pp.3961-3969
ISSN: 0957-4174
English
Journal Article, Electronic Publication
Fraunhofer INT ()
web mining; R&D planning; idea mining; text mining

Abstract
The internet is a valuable source of information where many ideas can be found dealing with different topics. A few numbers of ideas might be able to solve an existing problem. However, it is time-consuming to identify these ideas within the large amount of textual information in the internet. This paper introduces a new web mining approach that enables an automated identification of new technological ideas extracted from internet sources that are able to solve a given problem. It adapts and combines several existing approaches from literature: approaches that extract new technological ideas from a user given text, approaches that investigate the different idea characteristics in different technical domains, and multi-language web mining approaches. In contrast to previous work, the proposed approach enables the identification of problem solution ideas in the internet considering domain dependencies and language aspects. In a case study, new ideas are identified to solve existing technological problems as occurred in research and development (R&D) projects. This supports the process of research planning and technology development.

: http://publica.fraunhofer.de/documents/N-241802.html