International audience

Summary Traditional feature‐based semantic similarity (SS) approaches exploit the Wikipedia features in term of sets. They evaluate the similarity of concepts based on the commonalities among their feature sets. However, these feature‐based approaches treat all the features equally in similarity evaluation. Therefore, they ignore the underlying statistics of the features and consequently lose the essential semantic details about them. One solution is that each feature can be assigned a specific weight using its statistics. This weight will reflect the relative importance of a feature in similarity evaluation. Therefore, in this paper, based on two statistical models, ie, information content and TFIDF, we propose some hybrid semantic similarity measurement methods. Firstly, we propose some new methods called weighting functions to compute the weights of the features and feature sets in Wikipedia. Secondly, based on the weighting functions, we propose some new weighted feature‐based SS approaches for Wikipedia concepts. Thirdly, we evaluate the proposed methods on well‐known benchmarks for English, German, French, and Spanish languages. Finally, we compare the performance of our methods with the traditional feature‐based and some state‐of‐the‐art SS approaches. The experimental evaluation shows that our weighted methods perform better than the traditional feature‐based and some state‐of‐the‐art approaches in similarity evaluation.

In the era of Big Data, users prefer to get knowledge rather than pages from Web. Linked Data, a rather new form of knowledge representation and publishing described by RDF, can provide a more precise and comprehensible semantic structure to satisfy the aforementioned requirement. Besides, as the standard query language for RDF data, SPARQL has become the foundation protocol of Linked Data querying. The core idea of RDF Schema (RDFS) is to extend upon RDF vocabulary and allow attachment of semantics to user defined classes and properties. However, RDFS cannot fully utilize the potential of RDF since it cannot express the implicit semantics between linked entities in Linked Data sources. To fill this gap, in this paper, we design a new semantic annotating and reasoning approach that can extend more implicit semantics from different properties. We firstly establish a well-defined semantically enhanced annotation strategy for Linked Data sources. In particular, we present some new semantic properties for predicates in RDF triples and design a Semantic Matrix for Predicates (SMP). We then propose a novel general Semantically Extended Scheme for Linked Data Sources (SESLDS) to realize the semantic extension over the target Linked Data source through semantically enhanced reasoning. Lastly, based on the experimental analyses, we verify that our proposal has advantages over the initial Linked Data source and can return more valid results.

The data stored in E-Learning and academic social networking system databases can reveal useful insight into the behavior of the users of these systems. The statistical analysis and machine learning techniques can be used to make meaningful inferences from this data. Moreover, Education Data Mining (EDM) and Learning Analytics (LA) practices can help educators and administrators to take educated decisions related to the wellbeing of learners and the learning system overall. In this paper, we present descriptive statistical analysis of SCHOLAT E-Learning data to expose interesting information about the behavior of learners and the data gathering practices. The data was fetched from SCHOLAT Courses module database, and then univariate and bivariate analysis was performed to get an insight. This data represents the activities of students when they were undergoing a blended learning course. The analysis revealed that students' interest lies in activities which are related to improve their grades, e.g. submitting homework on time where mean value approaches the maximum value. However, they do not show the same enthusiasm in other activities. Moreover, a loophole was also discovered in data gathering practices as a result of analysis. The analysis lays a foundation for more complicated analysis in future and improving the system's data gathering practices.