Skip to content

Improving engineering information retrieval by combining TD-IDF and product structure classification

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationDS 87-6 Proceedings of the 21st International Conference on Engineering Design (ICED 17) Vol 6: Design Information and Knowledge, Vancouver, Canada, 21-25.08.2017
Subtitle of host publicationDesign Information and Knowledge, Vancouver, Canada, 21-25.08.2017 (Vol. 6, pp. 041-050)
Place of PublicationGlasgow, Scotland
Number of pages10
ISBN (Electronic)9781904670940
DateAccepted/In press - 24 Apr 2017
DatePublished (current) - 21 Aug 2017

Publication series

NameProceedings of the 21st International Conference on Engineering Design
PublisherThe Design Society
ISSN (Print)2226-8790
ISSN (Electronic)2220-4342


Engineering Information Management (EIM) and Information Retrieval (IR) systems are central to the day to day running of large engineering organisations. The capture, interrogation, retrieval and presentation of information from design to disposal is considered to be a key enabler for greater efficiency and decision making and in turn improved productivity, profitability and competitiveness. This paper presents a contribution to the field of engineering IR through combining TF-IDF with classification against the product structure. The results of this initial investigation show that Precision, Recall and F1-Scores can be improved depending on the method of results integration and thus tailored to the search system and context.

    Research areas

  • Knowledge Management, Information Management, Design informatics, Product Lifecycle Management (PLM)



  • Full-text PDF (final published version)

    Rights statement: This is the final published version of the article (version of record). It first appeared online via The Design Society at . Please refer to any applicable terms of use of the publisher.

    Final published version, 1 MB, PDF-document

    Licence: Other


View research connections

Related faculties, schools or groups