A Hybrid Method for Manufacturing Text Mining Based on Document Clustering and Topic Modeling Techniques

Published

September 5, 2016

Author(s)

Peyman Y. Shotorbani, Farhad Ameri, Boonserm Kulvatunyou, Nenad Ivezic

Abstract

As the volume of manufacturing information available online grows steadily, the need for developing dedicated computational tools for information organization and mining becomes more pronounced. This paper proposes a novel approach for facilitating search and organization of textual documents and also extraction of thematic patterns in manufacturing corpora using document clustering and topic modeling techniques. The proposed method adopts K-means and Latent Dirichlet Allocation (LDA) algorithms for document clustering and topic modeling, respectively. Through experimental validation, it is shown that topic modeling, in conjunction with document clustering, facilitates automated annotation and classification of manufacturing webpages, thus improving the intelligence of supplier discovery and knowledge acquisition tools.

Proceedings Title

APMS 2016 International Conference, Advances in Production Management Systems - Production Management Initiatives for Sustainable World

Conference Dates

September 3-7, 2016

Conference Location

Iguassu Falls, BR

Conference Title

none

Pub Type

Conferences

Download Paper

Local Download

Keywords

text mining, topic modeling, document clustering, supplier discovery, manufacturing service, knowledge acquisition

Citation

Shotorbani, P. , Ameri, F. , Kulvatunyou, B. and Ivezic, N. (2016), A Hybrid Method for Manufacturing Text Mining Based on Document Clustering and Topic Modeling Techniques, APMS 2016 International Conference, Advances in Production Management Systems - Production Management Initiatives for Sustainable World, Iguassu Falls, BR, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=920918 (Accessed October 8, 2025)