To read this content please select one of the options below:

Process ontology development using natural language processing: a multiple case study

Ozge Gurbuz (Informatics Institute, Middle East Technical University, Ankara, Turkey) (Huawei Turkey R&D Center, Istanbul, Turkey)
Fethi Rabhi (School of Computer Science and Engineering, University of New South Wales, Sydney, Australia)
Onur Demirors (Izmir Yuksek Teknoloji Enstitusu, Urla, Turkey) (School of Computer Science and Engineering, University of New South Wales, Sydney, Australia)

Business Process Management Journal

ISSN: 1463-7154

Article publication date: 28 December 2018

Issue publication date: 12 September 2019

463

Abstract

Purpose

Integrating ontologies with process modeling has gained increasing attention in recent years since it enhances data representations and makes it easier to query, store and reuse knowledge at the semantic level. The authors focused on a process and ontology integration approach by extracting the activities, roles and other concepts related to the process models from organizational sources using natural language processing techniques. As part of this study, a process ontology population (PrOnPo) methodology and tool is developed, which uses natural language parsers for extracting and interpreting the sentences and populating an event-driven process chain ontology in a fully automated or semi-automated (user assisted) manner. The purpose of this paper is to present applications of PrOnPo tool in different domains.

Design/methodology/approach

A multiple case study is conducted by selecting five different domains with different types of guidelines. Process ontologies are developed using the PrOnPo tool in a semi-automated and fully automated fashion and manually. The resulting ontologies are compared and evaluated in terms of time-effort and recall-precision metrics.

Findings

From five different domains, the results give an average of 70 percent recall and 80 percent precision for fully automated usage of the PrOnPo tool, showing that it is applicable and generalizable. In terms of efficiency, the effort spent for process ontology development is decreased from 250 person-minutes to 57 person-minutes (semi-automated).

Originality/value

The PrOnPo tool is the first one to automatically generate integrated process ontologies and process models from guidelines written in natural language.

Keywords

Citation

Gurbuz, O., Rabhi, F. and Demirors, O. (2019), "Process ontology development using natural language processing: a multiple case study", Business Process Management Journal, Vol. 25 No. 6, pp. 1208-1227. https://doi.org/10.1108/BPMJ-05-2018-0144

Publisher

:

Emerald Publishing Limited

Copyright © 2018, Emerald Publishing Limited

Related articles