E-Assessment Data Compatibility Resolution Methodology with Bidirectional Data Transformation

Abstract

Electronic Assessment (E-Assessment) also known as computer aided assessment for the purposes involving diagnostic, formative or summative examining using data analysis. Digital assessments come commonly from social, academic, and adaptive learning in machine readable forms to deliver the machine scoring function. To achieve real-time and smart e-assessment, data modeling needs dramatic improvements at the level of representation which will improve examinees to gain prompt response instantly after attempting exams. Whereas, computer based inference to gain intelligence in assessing results through computations is becoming a useful feature in todays' testing systems. Induction of rule base linked data is desired to be reformed from the old tradition data model found either in spread sheet or relational database used for data storage. These data forms are essential to be converted into semantical annotated form to support Artificial Intelligence. This can be done with the use of Semantic Web data model Resource Description Framework (RDF) built-up using hierarchal and linked data representation. Updating assessment source data later for results is one of the hardest problem of all viabilities in traditional and semantically augmented systems when combined for evaluating. This study purposes a methodology of bidirectional data transformation back and forth from Relational Database (RDB) and RDF. A case study representing qualitative analysis of transforming student's results information into RDF store reforming data as ready to be analyzed. At the end of this study outcomes show how data updating becomes feasible by following proposed data transformation procedure.

A Review of Artificial Intelligence (AI) in Education from 2010 to 2020

“…With the support of the natural language process, it could automatically create new themes, theories, and pedagogical contents as a response to learners' feedback, to help teachers save time and effort [31]. It constructed a human-computer interaction and widely used to generate real-time and intelligent feedback according to learners' input, which has been regarded as a reliable feature in modern assessment system [32]. (4) Deep learning, or machine learning, is a comprehensive approach of big data processing and learning behaviour analysis.…”

“…Instead, the machine can improve predictions by learning from big data without being specifically programmed. Two studies on deep learning were first mentioned in the selected papers in 2017 [23,32]. In 2018, one empirical study [37] was published and it focused the deep learning technology on the modelling of scoring-based data.…”

Hybrid approach for big data localization and semantic annotation

“…The process of data transformation between RDFS and RDB Schema followed by either Document Type Definition (DTD) or XML Schema 6 . The bi‐directional transforms from and back to RDB using XML as intermediate data form 16 . Data and metadata during transformation phase should not get lost in the transition from one form to another.…”

“…6 The bi-directional transforms from and back to RDB using XML as intermediate data form. 16 Data and metadata during transformation phase should not get lost in the transition from one form to another. Then, by mapping common datasets XML gained during the back and forth data transformation process, detection of a change in data or metadata requires to be measured.…”