A Survey of Semantic Technology and Ontology for e-Learning

Tracking #: 2133-3346

Yi Wang
Ying Wang

Responsible editor: 
Aldo Gangemi

Submission type: 
Survey Article
Semantic technology and ontology (STO) are being investigated in various areas. In the e-learning context, many studies have used STO to address problems such as the interoperability of learning objects (LOs), modeling and enriching learning resources, and personalizing educational content recommendations. This study systematically reviewed research on STO in e-learning systems from 2008 to 2018. The review was guided by three research questions: RQ1: “What are the major uses of ontology in e-learning systems?” RQ2: “What is the state of the art in educational ontology?” and RQ3: “What are the various applications of STO-based learning systems?” Based on 134 papers, we analyzed six types of ontology use and five aspects of educational ontology, as well as e-learning systems that use semantic approaches. The observations obtained from this survey can benefit researchers in this area and help guide future research.
Full PDF Version: 

Major Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Francesco Orciuoli submitted on 07/May/2019
Review Comment:

This manuscript was submitted as 'Survey Article' and should be reviewed along the following dimensions:

(1) Suitability as introductory text, targeted at researchers, PhD students, or practitioners, to get started on the covered topic.
This paper, by using adequate literature, clarifies several uses of ontologies in e-learning applications. Therefore, it is useful for practitioners (in the educational field and in the ontology engineering field) and also for researchers (in different fields).

(2) How comprehensive and how balanced is the presentation and coverage.
The presentation offers a suitable coverage of all aspects related to ontologies in e-learning and provides also information related to ontology design principles and implementation languages.

(3) Readability and clarity of the presentation.
The presentation is clear and readable. The text is well written.

(4) Importance of the covered material to the broader Semantic Web community.
The material provides support for both practitioners and knowledge engineers to understand the background knowledge related to ontologies for e-learning.

Review #2
By Herminio Garcia-Gonzalez submitted on 07/Oct/2019
Major Revision
Review Comment:

The current paper presents a survey of ontology use for the e-Learning field. The paper reviews 123 studies (11 of them survey papers) and survey them along three different dimensions: ontology usage, technical aspects and use cases. The paper is well written and easily understandable and one of its stronger points is the amount of studies surveyed. However, in its current form, there are some issues that must be addressed before its publication.

First of all, it is about the presentation of the paper. The current version is not following the template of the journal and should be adapted in following iterations of this paper. Apart from that, the title does not seem to be clear about the real topic of the survey. The title suggests that the survey is about Semantic Technology and Ontology (which is a semantic technology) for e-Learning but instead the actual content is only about Ontology for e-Learning. Authors must decide if they keep on the Ontology scope or if they survey a broader scope, but state clearly which is the final scope.

In the introduction, the research questions do not seem clear to me. The final work done in the different sections seems to answer different topics. Therefore, I suggest to rephrase these questions in order to be clearer and to fit better what is done in the corresponding sections.

In Sections 2, 3 and 5, when a work is cited the description is too brief in many cases which seems to be the opposite of what is expected from a review. In Section 2, the differences between other surveys and the current one are shortly described and, therefore, it is not clear the necessity of a new study. In Sections 3 and 5 in many cases a lot of works are cited under a topic but then they are never described in detail (e.g., see Section 5.1). In addition, other mechanisms to show the information must be taken under consideration to show the different works (for example, tables like the Table 2) because sometimes it is hard to follow and see the differences and connections between works (especially Section 3).

In the following part, I give some comments and typos per section.

- that uses semantic approaches (actually not semantic approaches only ontologies)
- Semantic technology and Ontology (same problem as with the title)
- as early as -> since
- manage courses resources and design personal recommendations (cite needed)
- the objective of this survey was -> the objective of this survey is
- the reason for using “learning” instead of “e-learning” (why not to use both keywords?)
- papers not accessible online (more details on what is not accessible online and the steps to obtain the papers)
- papers less than six pages (why? A lot of posters and demos can be excluded for no reason)
- section 6 concludes the paper -> Section 6 concludes the paper (notice the capital letter).

Related work
- as early as 2000 -> since 2000
- the application of knowledge-based methods such as rule-based reasoning and intelligent computing methods such as multiagent systems in e-learning environments -> the application of knowledge-based methods (such as rule-based reasoning) and intelligent computing methods (such as multiagent systems in e-learning environments)
- LO -> Learning Object (LO) (first time that the acronym appears apart from the abstract)

Ontology Use in e-Learning Environments
- interoperability issue in Los -> interoperability issue in LOs
- They defined an LO ontology -> They defined a LO ontology
- and IEEE LOM standard -> and the IEEE LOM standard
- characteristics of Los -> characteristics of LOs
- is key to achieving -> is key to achieve
- to realize a costumed learning model -> to realize a personalized learning model
- normally expressed in natural languages -> normally expressed in natural language
- with the feedback generation -> with feedback generation
- competency management (explain this concept)
- Munoz et al. [124] -> Muñoz et al. [124] (check this cite in the references section also)
- to achieve better cooperation (better cooperation between what?)
- with elements emphasizing (emphasizing what?)
- Gutiérrez-carreón, Daradoumis, and Jorba [128] -> Gutiérrez-Carreón, Daradoumis, and Jorba [128] (check this cite in the references section also)

Educational Ontology
- can be used to support adaptive e-learning (not only adaptive e-learning is treated in Section 3)
- RQ2 (as I previously commented RQ2 is not well linked with what is done in this section)
- the IDs of entities -> the entities IDs
- Figure 4 (it would be better for readers’ information to divide other into the different tools)
- to realize adaptive e-learning functions (same problem mentioned at the beginning of this section)

Ontology-Based Educational Application
- can be intelligently adjusted -> can be automatically adjusted (I prefer automatically because intelligently would imply more things)
- a learner’s knowledge status -> the learner’s knowledge status
- The adaptive learning approach presented in [52] could adjust […] (One of the problems is that there is no explanation about the link between e-learning topic and ontologies. This is one example but there are some others.)
- [128] (same problem as in the previous section).
- and Owl ontologies -> and OWL ontologies
- Videolecuture.net -> Videolectures.net
- to create specific ontologies, thus helping developers -> to create specific ontologies, helping developers

- which could help improve the comparison -> which could help to improve the comparison

- Reference -> References (the title)
- (check venues for the proceedings)

Review #3
By Aldo Gangemi submitted on 26/Feb/2020
Major Revision
Review Comment:

The paper is presented as a survey, but only part of it is actually written according to qualitative survey standards.

The paper selection method is quite minimal, e.g. just by simply scrambling the keywords for a Scholar search (“ontology” “semantics” “learning technology” “education” -"ontology learning"), I have got two relevant papers that are not targeted in the survey:

Panagiotopoulos, Ioannis, Kalou, Aikaterini, Pierrakeas, Christos, Kameas, Achilles. An Ontology-Based Model for Student Representation in Intelligent Tutoring Systems for Distance Learning. In Artificial Intelligence Applications and Innovations, springer, 2012

Marilza Pernas, A., Diaz, A., Motz, R. and Palazzo Moreira de Oliveira, J. (2012), "Enriching adaptation in e‐learning systems through a situation‐aware ontology network", Interactive Technology and Smart Education, Vol. 9 No. 2, pp. 60-73. https://doi.org/10.1108/17415651211242215

While seeding the search with a few keywords is a decent bootstrap, after that you'd need to build genealogies of related papers, with appropriate features that eventually provide you material for a useful overall comparison of ontologies and related systems.

Indeed, while some parts of the paper are definitely useful, I miss a formal comparison method, which should be supplemented in order to make this survey a state-of-the-art one.
An immediate advantage would come from a summary table for Section 3, which is only textual at the moment, but would benefit from an organised comparison of the tools/approaches discussed.

A similar consideration can be made about Section 4 (educational ontologies), which only addressed coarse features of ontologies (taxonomy or not, representation language, editing tool, design from scratch or reused ontologies, automatic or not), while nothing is said about the actual types of entities and relations addressed, the semantic expressivity used, how much data in the application, if the design included competency questions, foundational principles, or lexical methods, etc.

The paper also includes many language inaccuracies.

I invite the authors to deepen their work, and revise English, in order to make the article viable to the standards of the SWJ.