DADO - Data Analytics Driven by Ontologies

Lead Research Organisation: University of Essex
Department Name: Computer Sci and Electronic Engineering

Abstract

The Data Analytics Driven by Ontologies project (DADO) aims to develop a suite of techniques and methods which will
power the analytics engine of a novel e-assessment platform that will deliver innovative and personalised online education
and assessment services to users. The methods developed will deploy semantic-based techniques and ontologies as well
machine learning algorithms to empower expert and non-expert users (from educators and assessors to individual
learners) to explore data in effective and innovative ways, formulating complex multi-faceted queries, enabling them to
tailor-make their learning journey and assessment, while guiding them and supporting them by identifying and making use
of potential learning pathways that could help them reach their goals.

Planned Impact

Given the size of the education sector worldwide, the project and its outcomes are envisioned to have significant impact.
The project will generate impact both for the company and within the intended application domain (education and training),
but also more generally within the area of data analytics driven by the semantic information captured in ontologies but also
learning from the user behaviour.
Commercial Impact
The project will have direct impact for Obrussa and their work in providing efficient, effective and innovative e-assessment
services. Both partners have significant expertise and experience in the areas of semantic information analysis, modelling
and reasoning over ontologies and learning from user behaviour as well as machine learning techniques applied in a range
of domains, but the combination of skills of Obrussa and the research expertise and experience of the academic member of
staff from the University of Essex is envisaged to bring about significant and tangible outcomes.
More specifically, the project is envisaged to bring about significant improvements to the user/learner services that Obrussa
will be delivering through the e-assessment platform that will be the outcome of the DADO project. In particular, the
deployment of ontologies in combination with machine learning techniques will enable Obrussa to deliver innovative and
personalised e-assessments to users/learners - this is currently lacking from other products in the market and is expected to deliver a competitive advantage to Obrussa over other existing service providers and platforms.
The methods that will be developed as part of the DADO project will enable the delivery of assessment services at different
levels ranging from GCSE and A levels to Continuous Professional Development (CPD) provision. The developed methods
are envisioned to have wider applicability and could be transferable to other domains. In the first instance, Obrussa's client
base will be direct beneficiaries, but we will also work with the company to identify other potential users and beneficiaries in
the wider Education and Higher Education sector, including within our Eastern Arc collaboration (this is a collaboration
between the Universities of Essex, Kent and East Anglia).
Academic impact
The academic impact of this work will be in the areas of semantic analysis, ontology reasoning, techniques for
understanding from user behaviour, modelling and learning from data and adaptive e-assessment. There are several
research groups working in adjacent areas in the UK including in information retrieval (for instance in the Universities of
Sheffield, Glasgow and Strathclyde) as well as research being undertaken in machine learning and artificial intelligence
applications such as for instance at the Universities of Edinburgh and York among others. The research outcomes of the
project will also be relevant to the pedagogical research community, in particular, in the areas of e-assessment and
potentially on modelling learner(user) behaviour. Academic impact will be ensured through publication in appropriate
journals and conferences, presentations to conferences and other more specialist events.
Beyond this domain of application
Beyond the impact on the development of Obrussa's e-assessment platform and product offering, the developed methods
and techniques could be applied to other application areas where information encapsulated in ontologies as well as user
behaviour and data can be used to deliver more efficient services (e-commerce and e-government applications for
instance) or facilitate more effective and novel data exploration.

Publications

10 25 50
 
Description The Data Analytics Driven by Ontologies project (DADO) aimed at developing a suite of techniques and methods which could be used as part of an e-learning system and would enable innovative and personalised online education and assessment services to users. As part of the project, we researched and developed novel semantic-based data exploration methods in the domain of e-learning. These techniques make use of ontologies which facilitate better understanding of learner characteristics and actions which can result in making better recommendations to users/learners and improve their learning experience. We have developed and defined the concept of learning paths consisting of learners' sequences of actions underpinned by ontologies. These enable the identification of user behaviours that lead to outcomes which can then be used to enhance the experience of other users. Machine learning algorithms can be used to learn the more effective patterns of behaviours that lead to better outcomes.
We undertook an experimental validation of the methods developed using a synthetic dataset which was based on a real dataset of user behaviours and interactions through an e-learning and assessment system.
Exploitation Route The work undertaken as part of this project is within an area that is becoming increasingly important, learner analytics. The project has led to an increased understanding of the requirements and needs in this area as well as the methods and techniques of data science and machine learning that can be developed and deployed, but also their limitations.
The outcomes of the project can be used to enhance e-learning systems functionality and support personalized learning and assessment as well as analytics. The outcomes of this project can be extended to cover more complex scenarios of user behaviours which could be beyond the domain of e-learning and assessment.
Sectors Digital/Communication/Information Technologies (including Software),Education

 
Description Contributed to workshop organised by the African Institute for Mathematical Sciences on the use of artificial intelligence techniques for business purposes 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact I delivered a session as part of a workshop/event organised by the African Institute for Mathematical Sciences on the applications of artificial intelligence techniques including machine learning and recommendation technologies to a group of students from various countries in Africa. The event took place in South Africa.
Year(s) Of Engagement Activity 2017
 
Description Roundtable discussion organised by ObjectiveIT 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact This was a presentation given to about 20-25 business representatives on the use of artificial intelligence techniques including machine learning and recommendation technologies to support decision making in industry.
Year(s) Of Engagement Activity 2018