Fig 2 - uploaded by Khaled Shaalan
Content may be subject to copyright.
Source publication
Learning analytics has emerged as a new domain for identifying students’ behaviors, academic performance, academic achievement, and other related learning issues. Given its paramount importance and recency, several review studies were conducted. However, the previous reviews have mainly focused on the behavioral, affective, cognitive, and metacogni...
Context in source publication
Context 1
... shown in Fig. 2, the learning analytics consists of four primary levels, including descriptive, diagnostic, predictive, and perspective. The "descriptive" level describes what learners do and what happens in the teaching and learning environment. The "diagnostic" level refers to the stage that covers the factors that affect students' performance and ...
Similar publications
In order to analyze the non-linear and uncertain relationships among the student-related features, curriculum-related features as well as the environment-related features, and then quantify the corresponding impacts on students’ final MOOC performance in a valid way, we first construct a Students’ performance Prediction Bayesian Network (SPBN) via...
Citations
... Botelho & Lam, 2019) De todo esto se desprende que, existen tres elementos principales que aparecen a través del concepto de analítica de aprendizaje, como son los datos, el análisis y la acción. En este contexto, los datos en bruto son aquellos que requieren varios tipos de análisis utilizando algoritmos de aprendizaje automático para obtener información real y patrones interesantes(Hantoobi et al., 2021). De alguna manera, son una especie de huella digital dejada por los estudiantes en los entornos virtuales de aprendizaje.Los comportamientos de uso de los ingresos electrónicos de los estudiantes, como el número de inicios de sesión, el tiempo dedicado a las plataformas de aprendizaje electrónico y el uso de otros recursos, se han estudiado y se ha encontrado que están asociados positivamente con los resultados de rendimiento académico. ...
RESUMEN Las instituciones de educacion superior se han visto obligadas a regular la calidad de enseñanza virtual, debido al gran auge que esta modalidad tiene en la actualidad. Existen diferentes plataformas utiliza-das para este fin, las cuales nos permiten recoger una gran cantidad de datos que resultan útiles para determinar la analítica de aprendizaje. El siguiente trabajo busca diagnosticar los diferentes aspectos académicos en cuanto al funcionamiento de la mo-dalidad virtual de la Universidad Gabriela Mistral de Chile. Para ello se utiliza la modalidad de investi-gación descriptiva con diseño de campo. Entre los resultados obtenidos se destaca el alto porcenta-je de progresión académica y la valoración de los docentes con un promedio de 4,6 sobre 5. Como conclusión podemos establecer que la analítica de aprendizaje para la educación virtual es una gran aliada, ya que permite diagnosticar patrones en los estudiantes. Palabras clave: Analítica de aprendizaje, Universidad Gabriela Mistral, educación virtual, educacion superior, cali-dad de enseñanza ABSTRACT Higher education institutions have been forced to regulate the quality of virtual teaching, due to the great boom that this modality has nowadays. There are different platforms used for this purpose which allow us to collect a large amount of data that are useful to determine the learning analytics. The following work seeks to diagnose the different academic aspects regarding the functioning of the virtual modality of Gabriela Mistral University of Chile. For this purpose, the descriptive research modality with field design was used. Among the results obtained, the high percentage of academic progression and the valuation of teachers with an average of 4.6 out of 5 stand out. As a conclusion, we can establish that learning analytics for virtual education is a great ally, since it allowed us to diagnose patterns in students.
... Universities are recognizing the benefits of information solutions that not only better students at all stages of their education, even the most challenging, but also implement ever more effective educational resources to enhance the learning experience for students and their instructors [2]. Teaching module organizers and instructors focus on analytics results and the use of algorithms to im-prove their content and flexibility to identify students at risk of academic failure as early as possible and then provide them with more targeted learning solutions [3]. ...
With the immersion of a plethora of technological tools in the early post-COVID-19 era in university education, instructors around the world have been at the forefront of implementing hybrid learning spaces for knowledge delivery. The purpose of this experimental study is not only to divert the primary use of a YouTube channel into a tool to support asynchronous teaching; it also aims to provide feedback to instructors and suggest steps and actions to implement in their teaching modules to ensure students' access to new knowledge while promoting their engagement and satisfaction, regardless of the learning environment, i.e., face-to-face, distance and hybrid. Learners' viewing habits were analyzed in depth from the channel's 37 instructional videos, all of which were related to the completion of a computer-aided mechanical design course. By analyzing and interpreting data directly from YouTube channel reports, six variables were identified and tested to quantify the lack of statistically significant changes in learners' viewing habits. Two time periods were specifically studied: 2020-2021, when instruction was delivered exclusively via distance education, and 2021-2022, in a hybrid learning mode. The results of both paramet-ric and non-parametric statistical tests showed that "Number of views" and "Number of unique viewers" are the two variables that behave the same regardless of the two time periods studied, demonstrating the relevance of the proposed concept for asynchronous instructional support regardless of the learning environment. Finally, a forthcoming instructor's manual for learning CAD has been developed, integrating the proposed methodology into a sustainable academic educational process.
... The global pandemic of coronavirus disease has further accelerated the use of innovative technological tools in an unprecedented way in almost all domains. In particular in the field of education, emerging technologies such as social and collaborative learning tools, intelligent and adaptive tutoring as well as augmented and mixed reality applications, are deployed extensively in traditional educational processes by examining the relationship between digital and learning (Klašnja-Milićević et al., 2017) (Hantoobi et al., 2021). In recent years, the interest in studying the impact of serious games on learning outcomes in formal education has increased (Cheng et al., 2015) (Hainey et al., 2016). ...
In recent years, the interest in the use of serious games as teaching and learning tools in traditional educational processes has increased significantly. Serious Educational Games (SEG) and Learning Analytics (LA) are gaining increasing attention from teachers and researchers, since they both can improve the learning quality. In this article, we aimed to examine, summarize and characterize the current state of the art related to the application of LA to SEGs through a systematic literature review based on a methodological instrument called PRISMA. A qualitative analysis was performed in which 80 significant papers were selected from the ScienceDirect, SpringerLink, Web of Science, and IEEE-Xplore databases. From this analysis, we identified the main features of an efficient use of SEGs in terms of success factors and learning outcomes; we also discussed the benefits and challenges of integrating LA approaches into these environments. Consequently, a new multidimensional taxonomy for using SEGs to categorize these major features was proposed. The findings of this review reveal that SEGs have a beneficial effect on students’ behavior, cognition and emotion; but more future works and empirical studies investigating data science techniques are needed to improve the usability of educational games. This research and the suggested guideline recommendations may be of value to researchers and practitioners willing to deploy SEGs contributing thus to the continuous improvement of digital learning in formal education.
... In such learning environments, the user usually utilizes online tools, such as discussion forums, online chats, and learning management systems. Using those online activities creates a huge amount of data called "big data", which cannot be processed with the traditional analytical methods [2,3]. This creates the need for exploring new techniques to process this type of data. ...
Analytics in educational environments has received much attention during the last few years. Maintaining a high retention rate is still a major concern in higher educational institutions. Therefore, this research aims to early detect students at risk using three machine learning predictive models, namely support vector machine (SVM), neural networks (NN), and K nearest-neighbors (KNN), based on a new dataset collected from 800 students through surveys. The criteria used to evaluate the models were accuracy, sensitivity, and specificity. Regarding the accuracy, the SVM model has outperformed the NN and KNN models, where it achieves 86.7%. Concerning the sensitivity, the NN model was more sensitive to detect failure cases than the other two models. Regarding the specificity, it was very high for the three models. It is believed that the results could assist the educators in early detecting students at risk, and therefore, reducing students’ dropouts.
Remote learning has advanced from the theoretical to the practical sciences with the advent of virtual labs. Although virtual labs allow students to conduct their experiments remotely, it is a challenge to evaluate student progress and collaboration using learning analytics. So far, a study that systematically synthesizes the status of research on virtual laboratories and learning analytics does not exist, which is a gap our study aimed to fill. This study aimed to synthesize the empirical research on learning analyt-ics in virtual labs by conducting a systematic review. We reviewed 21 articles that were published between 2015 and 2021. The results of the study showed that 48% of studies were conducted in higher education, with the main focus on the medical field. There is a wide range of virtual lab platforms, and most of the learning analytics used in the reviewed articles were derived from student log files for students' actions. Learning analytics was utilized to measure the performance, activities, perception, and behavior of students in virtual labs. The studies cover a wide variety of research domains, platforms , and analytical approaches. Therefore, the landscape of platforms and applications is fragmented, small-scale, and exploratory, and has thus far not tapped into the potential of learning analytics to support learning and teaching. Therefore, educators may need to find common standards, protocols, or platforms to build on each others' findings and advance our knowledge.
The complex task of developing an assessment activity and its structure requires determining the appropriate set of elements to link the learning objectives with the expected results. The analysis of learning outcomes through the use of technological techniques are challenges that are still posed in the various research works, when using them in the educational field. This paper presents a model for monitoring and adapting assessment activities in a virtual learning environment. The objective is to determine the characteristics and conditions of assessment activities that allow the teacher to guide the behavior of students in a course according to the monitoring and adaptation of assessment activities in a virtual learning environment. Therefore, this paper presents a model for monitoring and adapting evaluation activities in a virtual learning environment. The results of this study reflect those students achieve an average pass rate of 87% in four courses that actively participate in this work and an attrition rate of 13%. The limitations found suggest external factors such as connectivity and the pandemic, which affect students but can be dealt with in a preventive sense, in the face of a possible academic risk through the learning analytics exhibited to students in the virtual learning environment. The results obtained show a high commitment of the students in achieving the challenges proposed by the teacher, reaching above-average performance values. For future work, this model will be replicable to several engineering subjects in first-year courses. This work contributes to the development of a method for teacher recommendations in VLE environments.KeywordsLearning designLogs of learnersLearning analyticsFollow-up and adaptation of activities
Software requirements are ambiguous due to the ambiguity of natural language in general. The ambiguity of the requirements leads to software development errors. As a result, a multitude of approaches and techniques for detecting ambiguity in software requirements have emerged. This study used three supervised ML algorithms that used Bag-of-Words features to detect grammatical ambiguity in software requirements: support vector machine (SVM), random forest (RF), and k-nearest neighbours (KNN). RF had the highest accuracy of 86.66%, followed by SVM (80%) and KNN (70%).KeywordsSVMRandom forestKNNBags-of-words
The rapid emergence of deep learning (DL) algorithms has paved the way for bringing artificial intelligence (AI) services to end users. The intersection between edge computing and AI has brought an exciting area of research called edge artificial intelligence (Edge AI). Edge AI has enabled a paradigm shift in many application areas such as precision medicine, wearable sensors, intelligent robotics, industry, and agriculture. The training and inference of DL algorithms are migrating from the cloud to the edge. Computationally expensive, memory and power-hungry DL algorithms are optimized to leverage the full potential of Edge AI. Embedding intelligence on the edge devices such as the internet of things (IoT), smartphones, and cyber-physical systems (CPS) can ensure user privacy and data security. Edge AI eliminates the need for cloud transmission through processing near the source of data and significantly reduces the latency; enabling real-time, learned, and automatic decision-making. However, the computing resources at the edge suffer from power and memory constraints. Various compression and optimization techniques have been developed in both the algorithm and the hardware to overcome the resource constraints of edge. In addition, algorithm-hardware codesign has emerged as a crucial element to realize the efficient Edge AI. This chapter focuses on each component of integrating DL into Edge AI such as model compression, algorithm hardware codesign, available edge hardware platforms, and challenges and future opportunities.KeywordsArtificial intelligenceEdge AIMachine learningDeep learningModel compressionAlgorithm-hardware codesign
There is a need for an automated approach to extract current trends and perceptions from literature review material in a field of interest. Manually reviewing a large number of papers is time-consuming, topic modelling will help to avoid this. The text mining technique chosen for this task is topic modelling. The chapter gives an overview of the most widely used topic modelling techniques, as well as a few applications. It also summarizes a few current research trends and the generic processes of topic modelling. A section demonstrates an approach to discovering current perceptions from literature materials focused on data analytics in e-commerce using topic modelling. The case study framework included five steps: data collection, data pre-processing, topic tuning, performance evaluation, and interpretation of topic modelling results. The topic numbers were tuned using MALLET with Gensim wrappers. LDA is used. The Gensim topic coherence framework in Python was used to evaluate the topics. The perceptions in the reviewed material are interpreted using the inter-topic distance map in pyLDAVis. The modelling revealed distinct perceptions or directions of interest in e-commerce and data analytics research. Researchers can use topic modelling to see which areas are getting attention and which aren’t.
Several intelligent transportation systems focus on studying the various driver behaviors for numerous objectives. This includes the ability to analyze driver actions, sensitivity, distraction, and response time. As the data collection is one of the major concerns for learning and validating different driving situations, we present a driver behavior switching model validated by a low-cost data collection solution using smartphones. The proposed model is validated using a real dataset to predict the driver behavior in short duration periods. Multiple Markov Switching Variable Auto-Regression (MSVAR) models are implemented to achieve a sophisticated fitting with the collected driver behavior data. This yields more accurate predictions not only for driver behavior but also for the entire driving situation. The performance of the presented models together with a suitable model selection criterion is also presented. The proposed driver behavior prediction framework can potentially be used in accident prediction and driver safety systems.
