Natural language processing (NLP) tasks can be addressed with several deep learning architectures, and many different approaches have proven to be efficient. This study aims to briefly summarize the use cases for NLP tasks along with the main architectures. This research presents transformer-based solutions for NLP tasks such as Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-Training (GPT) architectures. To achieve that, we conducted a step-by-step process in the review strategy: identify the recent studies that include Transformers, apply filters to extract the most consistent studies, identify and define inclusion and exclusion criteria, assess the strategy proposed in each study, and finally discuss the methods and architectures presented in the resulting articles. These steps facilitated the systematic summarization and comparative analysis of NLP applications based on Transformer architectures. The primary focus is the current state of the NLP domain, particularly regarding its applications, language models, and data set types. The results provide insights into the challenges encountered in this research domain.

Educational Data Mining (EDM) techniques offer unique opportunities to discover knowledge from data generated in educational environments. These techniques can assist tutors and researchers to predict future trends and behavior of students. This study examines the possibility of only using traditional, already available, course report data, generated over years by tutors, to apply EDM techniques. Based on five algorithms and two crossvalidation methods we developed and evaluated five classification models in our experiments to identify the one with the best performance. A time segmentation approach and specific course performance attributes, collected in a classical manner from course reports, were used to determine students' performance. The models developed in this study can be used early in identifying students at risk and allow tutors to improve the academic performance of the students. By following the steps described in this paper other practitioners can revive their old data and use it to gain insight for their classes in the next academic year.

This paper aims to investigate the use of a Romanian data source, different classifiers, and text data augmentation techniques to implement a fake news detection system. The paper focusses on text data augmentation techniques to improve the efficiency of fake news detection tasks. This study provides two approaches for fake news detection based on content and context features found in the Factual.ro data set. For this purpose, we implemented two data augmentation techniques, Back Translation (BT) and Easy Data Augmentation (EDA), to improve the performance of the models. The results indicate that the implementation of the BT and EDA techniques successfully improved the performance of the classifiers used in our study. The results of our content-based approach show that an Extra Trees Classifier model is the most effective, whether data augmentation is used or not, as it produced the highest accuracy, precision, F1 score, and Kappa. The Random Forest Classifier with BT yielded the best results of the context-based experiment overall, with the highest accuracy, recall, F1 score, and Kappa. Furthermore, we found that BT and EDA led to an increase in the AUC scores of all models in both content-based and context-based data sets.

Misinformation poses a significant challenge in the digital age, requiring robust methods to detect fake news. This study investigates the effectiveness of using Back Translation (BT) augmentation, specifically transformer-based models, to improve fake news detection in Romanian. Using a data set extracted from Factual.ro, the research finds that BT-augmented models show better accuracy, precision, recall, F1 score, and AUC compared to those using the original data set. Additionally, using mBART for BT augmentation with French as a target language improved the model’s performance compared to Google Translate. The Extra Trees Classifier and the Random Forest Classifier performed the best among the models tested. The findings suggest that the use of BT augmentation with transformer-based models, such as mBART, has the potential to enhance fake news detection. More research is needed to evaluate the effects in other languages.

The educational ontology we presented in this paper is used to model web-based e-learning systems for higher education. Our main objective was to create domain ontology to play an important role in representing higher education concepts and to assist specialized e-learning systems. We have stressed the need for developing educational models that meet the expectations of higher education community with regards to e-learning adaptation and efficiency by employing ontologies and Semantic Web techniques.

The present work considers the possibility of using Moodle course logs and student performance indicators within the Database Systems course to apply the K-Means clustering algorithm. Clusters of students are identified and explained to partition students with similar study behaviours and performance. Moreover, the understanding of the five groups emerged in cluster analysis allowed us to identify a cluster that contains 86% of students at risk of not completing the course activity. One important aspect that differentiates our study from other similar works is the use of data collected over a long period of time, from 2015 to 2019. The final data set, obtained after preprocessing, contains no less than 185.206 course logs.