Call for Papers: Special Issue on Current Trends in Educational Data Science

Description
Data Science (DS) is the term used by the community to refer to the extraction of knowledge from data by using a series of methods, processes and systems. DS is a discipline with great applicability in different domains, as long as there are enough amounts of data to extract knowledge from. Education is one of those domains where massive data is generated continuously in educational institutions of different types. Manually extracting knowledge from those data is a highly complicated and time-consuming task. That is why computational approaches are needed.

In this regard, the application of Data Mining techniques has demonstrated to be a useful approach, leading to an emerging area known as Educational Data Mining (EDM). EDM is focused on the application of different methods from knowledge extraction from educational data. EDM is complemented by another approach named Learning Analytics (LA), focused on stages before (e.g., data contextualization) and after DM (e.g., tutorial plan design using the extracted knowledge) process. Educational Data Science (EDS) is a global approach including both EDM and LA as well as other trends related to educational data analysis.

Undoubtedly, applying EDS may result of great interest and utility for all the actors involved in the educational process, such as students, instructors, University managers or even higher level state administrators. To mention some, EDS can be useful to improve students’ performance, prevent students’ dropout, design University strategical plans and curricula, or design educational laws in state organizations.

In recent years, lots of works have been proposed by the community in the field of EDS, covering important trends such as deep learning applied to educational data, multimodal educational data fusion, predictive model generalization, interpretability and transferability, just to mention some. This special issue is precisely intended to collect some of the most important works recently conducted in the field of EDS, as long as they represent a major contribution to the present and future of this discipline.

EDS is quite a technical discipline and, therefore, formal technical content is expected but only works with a deep pedagogical analysis of antecedents and implications of the methods proposed will be considered, while some technical applications of computational methods in EDS are not intended to be contained in this collection.

In summary, this special issue seeks original contributions of studies on the application of EDS techniques as long as they represent a real trend in the area and they justify the application of the proposed methods from a pedagogical perspective, as well as analyze the implications of the results obtained with respect to the learning process itself. Priority will be given to papers that demonstrate a strong grounding in learning theory and/or rigorous educational research design. We will consider studies focused on tertiary and further education of any type (e-learning, blended and traditional education). Work should include an exhaustive validation in order to be considered, with position papers being occasionally admitted providing that they are very well written and include extraordinarily new ideas in the area. Survey papers may be also considered as long as they are clearly aligned with the special issue ideas and present interesting challenges and research opportunities in this area.

Subject Coverage 
Suitable topics include, but are not limited to, the following:
•    Educational data mining
•    Learning analytics
•    Educational data visualization
•    Educational data preprocessing
•    Multimodal educational data analysis
•    Educational data fusion/integration
•    Temporal data analysis in education
•    Deep Learning applied to educational data
•    Self-regulated learning data analysis
•    Educational process mining
•    Educational models generalization
•    Ontologies for educational data science
•    Models transferability and generalizability
•    Models interpretability
•    Big Data on educational data
•    Educational open/linked data systems
•    Gamification-related data analysis

Notes for Prospective Authors
This special issue is mainly intended (but not restricted) to contain extended versions of the best papers selected from the conference DATA’23 (https://iares.net/Conference/DATA2022) regarding Educational Data Science. In order to be considered for inclusion in this special issue, all articles sent for the DATA’23 conference (contact the Guest Editors about the conference) must include the following text in the Acknowledgement section: “This paper is intended for publication in the Special Issue on Current Trends in Educational Data Science”. Submitted papers should not have been previously published or be currently under consideration for publication elsewhere. Conference papers may be submitted to the special issue only if the paper has been completely rewritten and if appropriate written permissions have been obtained from any copyright holders of the original paper. All manuscripts should follow APA guidelines and will undergo blind peer review. 

Manuscripts should be submitted to the special issue via the journal’s manuscript-submission and peer-review system at www.editorialmanager.com/jche and must indicate the submission is to the “SI: Trends-EDS” (Please note conference manuscripts must not be submitted to this site. Contact the Guest Editors for instructions on how to submit a paper to the DATA’23 conference).

For further information on the special issue and submission procedures, please contact the Guest Editors. If you are considering submitting a manuscript to the conference and a rewritten manuscript to the special issue, please contact the Guest Editors for specific procedure.

Important Dates 
Submission deadline: 15 July 2023
Review notification: 15 September 2023
Submission of revised papers: 15 December 2023
Notification of final review results: 15 February 2024

Guest Editors
Prof Dr. Shadi A. Aljawarneh, Jordan University of Science and Technology, Irbid, Jordan; saljawarneh@acm.org
Prof. Dr. Juan Alfonso Lara Torralbo, Universidad de Córdoba, Spain; juan.lara@uco.es