Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/183755
Authors: 
Popović, Goran
Year of Publication: 
2016
Citation: 
[Title:] Proceedings of the ENTRENOVA - ENTerprise REsearch InNOVAtion Conference, Rovinj, Croatia, 8-9 September 2016 [ISSN:] 2706-4735 [Volume:] 2 [Pages:] 478-483
Abstract: 
Patents are one of the most valuable sources of technical and commercial knowledge. Although patents are public and can be easily searched on the Web, for most countries, there is no easy way to download bulk patent data. The purpose of this paper is to create a web mining framework used to extract patent data from the Croatian State Intellectual Property Office. Even though framework was created for the purposes of extracting Croatian patents, it can be reused for other web mining cases. The architecture of the proposed framework combines the use of web crawler and big data tools, in order to provide a complete and flexible solution for building general-purpose web mining application. The biggest limitation of this framework comes from the programming knowledge required to implement it. Therefore, this framework is only available to the small number of researchers. Data extracted with web mining methods is only as good as the algorithm used to extract data. Nevertheless, the data from official sources should always be preferred to the one retrieved using web mining methods.
Subjects: 
web mining
data mining
crawling
patent mining
JEL: 
L86
O34
Document Type: 
Conference Paper

Files in This Item:
File
Size





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