DIGITAL LIBRARY
AUTOMATIC GENERATION OF EDUCATIONAL QUIZZES FROM DOMAIN ONTOLOGIES
1 INRIA Sophia Antipolis Méditerranée, Sophia Antipolis (FRANCE)
2 University Nice Sophia Antipolis (FRANCE)
About this paper:
Appears in: EDULEARN17 Proceedings
Publication year: 2017
Pages: 4024-4030
ISBN: 978-84-697-3777-4
ISSN: 2340-1117
doi: 10.21125/edulearn.2017.1866
Conference name: 9th International Conference on Education and New Learning Technologies
Dates: 3-5 July, 2017
Location: Barcelona, Spain
Abstract:
Educational quizzes are very valuable resources to test or evaluate the knowledge acquired by learners and to support lifelong learning on various topics or subjects, in an informal and entertaining way. The production of quizzes is a very time-consuming task and its automation is thus a real challenge in e-Education. The research work presented in this paper contributes to answer this challenge. We address the research question of How can we automate the generation of quizzes by taking advantage of existing knowledge sources available on the Web. More specifically, we focus on the exploitation of domain ontologies available on the so-called Semantic Web. Ontologies are formal specifications of shared conceptualizations; they play a fundamental role on the Semantic Web as they enable automatic reasoning. There is a large and increasing number of domain ontologies published on the semantic Web that model various specific domains.

We propose an approach that allows learners to take advantage of the knowledge captured in domain ontologies available on the Web and to discover or acquire a more in-depth knowledge of a specific domain by solving educational quizzes automatically generated from an ontology modelling the domain.

To achieve this, our approach relies on four key features:
(1) Quizzes are first formalized with Semantic Web standards: questions are represented as SPARQL queries and answers as RDF graphs. Natural language questions and answers are generated from these formalization.
(2) We defined different strategies to extract multiple choice questions, correct answers and distractors from domain ontologies.
(3) We defined a measure of the information content of the elements of an ontology, and of the quizzes using them.
(4) We defined different learner profiles to adapt the generated quizzes accordingly.

As a result, a set of questions (and their correct answers) is generated considering the learner's educational profile, and their corresponding distractors are generated taking into account the learner’s learning level.

This paper presents each of the above-cited keystones of our approach, the implementation of our approach, and its experimentation and evaluation on two different domain ontologies, with three different learner profiles.
Keywords:
Semantic Web, Domain Ontologies, e-Education.