Title: Automatic topic labelling for text document using ontology of graph-based concepts and dependency graph

Authors: Phu Pham; Phuc Do; Chien D.C. Ta

Addresses: Faculty of Information Science and Engineering, University of Information Technology (UIT), VNU-HCM, Quarter 6, Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam ' Faculty of Information Science and Engineering, University of Information Technology (UIT), VNU-HCM, Quarter 6, Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam ' Department of Information Technology, Industrial University of Ho Chi Minh City, No. 12 Nguyen Van Bao, Ward 4, Go Vap District, Ho Chi Minh City, Vietnam

Abstract: Topic labelling is an important task of text mining. It supports assigning proper topic labels to the text documents. In this paper, we present a novel approach of using graph-based concept matching approach in solving automatic topic labelling task. Our proposed model demonstrates that the quality of automatic topic labelling task for text documents can be improved, in comparison with traditional keyword-based concept matching approach. In this paper, we propose a novel approach of automatic ontology-driven topic labelling. Our proposed model is considered as a semi-supervised approach. It uses existed ontologies as the pre-knowledge base for topic identification in text documents. We performed the experiments on the real-world ACM's documents to show the effectiveness of our proposed model in solving topic labelling task. The experimental results on real-world and standard datasets demonstrate that our proposed model can leverage the output accuracy of topic labelling task in text documents.

Keywords: automatic topic labelling; ontology-driven topic labelling; dependency graph parsing; graph-based concept; frequent subgraph mining; FSM.

DOI: 10.1504/IJBIS.2021.112826

International Journal of Business Information Systems, 2021 Vol.36 No.2, pp.221 - 253

Received: 29 Jan 2018
Accepted: 25 Nov 2018
Published online: 05 Feb 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article