Prog.PhD STI
Adm. – Grad.2016 – 
Dir.; Codir.Stéphane Gagnon

Business Technology Management Ontology and Knowledge Recommendation

Iyer, Shankar

Business Technology Management (BTM) is a rapidly emerging trans-disciplinary research area and professional discipline in Business Administration. It seeks to provide an integrated framework for the strategic use of Information and Communication Technology (ICT) and leading digital organizations. 

The present thesis proposal is part of the BTM Body of Knowledge (BOK) project, seeking to develop a systematic, exhaustive, and evolving framework for professional practice standards, in service to support IT Human Resources Management (HRM). The project aims to make BTM job knowledge easily accessible, customizable, and reusable for decision-making by professionals, employers, higher education, and other associations involved with IT-related standards, certification, and accreditation.

Our thesis is focused on a key task within the BTM BOK development lifecycle, namely the reuse of the BOK assets stored in XMI/XML, with references and mappings to relevant parts related to BTM BOK core. A key issue is to reuse and add value to the standard job descriptions, their tasks, and job qualifications, which can be used for automated knowledge recommendation from academic research transferred to practice. This will help overcome the difficulties in managing BTM career and learning, as many professionals and their hiring managers face ambiguity as to what BTM standards are the right one for what job roles.

The present thesis proposal is for standards reuse through BTM Ontology technologies for the purpose of Automated Knowledge Recommendation.

The logic of the proposed system relies on the fact that:

• BTM standards are stored in an XMI format conforming to the XML standards by Object Management Group (OMG), namely Software Process Engineering Metamodel (SPEM 2.0).

• Job roles, tasks, and qualifications are clearly separated under their respective component, and can be surgically parsed and integrated within various other XML documents and queries.

• This data can be further annotated using an ontology-driven semantic text mining tool, helping us query them further and ensure their validated integration with other components, e.g., customizing a job profile.

• The semantically linked job profiles can then be used to recommend knowledge for practice, based on tasks and roles specific as per requirements of a given IT project.

This builds upon a text and semantic analysis platform, Adaptive Rules-Driven Architecture for Knowledge Extraction (ARDAKE), developed by UQO graduate Dr. Wassim El-Kass. It can be used to annotate the BTM literature, and then perform semantic queries to extract job roles, tasks, and qualifications, which will then be expanded into accurately recommended knowledge sources, which are then validated using the semantic relationships.

The research methodology will follow an Action Design Research (ADR) cycle. We will develop, validate, test, and implement an Ontology Web Language (OWL) version of the Business Technology Management Body of Knowledge (BTM BOK). We will implement this ontology for the purpose of recommending relevant scientific literature to professional end-users, based on their learning requirements. We will use formal ontology development methods, using such tools as Stanford Protégé and Stardog for ontology design and reasoning. We will work in partnership with a team of contributors from the BTM profession. 

The research process will include the following steps performed by the doctoral candidate:

1. Import BTM BOK assets from XMI into RDF-OWL. 

2. Manually validate, with the help of a team of external contributors, the ontology and its integrity and add 1000+ concepts not yet present in the BTM BOK. 

3. Align the BTM ontology with the YAGO4 ontology, mostly using manual but also automated ontology alignment tools. 

4. Build a small web app to represent the ontology to the team of contributors and involve them in the collective process of ontology editing and finalization. 

5. Build a small web app to allow contributors to make annotation of scientific articles abstracts (at sentence and word level) to indicate how BTM BOK ontology concepts rely to each. 

6. Use this «gold standard» to test the BTM ontology, by attempting to infer through Stardog reasoning whether each abstract line is properly detected to be the specific ontology concepts as prescribed by end users. 

7. Analyze results based on F-measure and Matthews Correlation Coefficient (MCC) to evaluate the quality of our ontology inference capabilities. 

8. Interpret the results as to the necessary improvements in later iterations and identify a work plan for the community to continue maintain the ontology.

The output of step 5 in this research process will be a crucial moment to demonstrate the feasibility of a text mining and semantic annotation platform. The prior semantic annotation of BTM literature using the BTM BOK components will be leveraged to expand and properly recommend the relevant scientific literature for various BTM job roles. This research may have a significant impact on ensuring greater relevance of academic research for professional practice, and interest of practitioners for academic knowledge as well.