Deep Learning for Automatic Assessment and Feedback in LMS-Based Education

Artificial Intelligence (AI) in learning and education is not new. However, the rise of the Covid-19 pandemic led to a focus on its role in Learning Management Systems (LMS). This study also examined the role of AI in the LMS with features including Natural Language Processing and Reasoning. The researchers used a self-proposed model and gathered data from the mass communication students in two public sector universities in Pakistan. Results revealed that Artificial Intelligence is integral to Learning Management Systems (LMS) in the selected institutions. Further, the effect of Natural Language Processing (NLP) on Reasoning indicated these two factors as interlinked, improving the quality of LMS. Additionally, Natural Language Processing significantly mediated the effect of AI on the LMS, showing that language processing facilitates LMS usage among students. Finally, the results also indicated the significant mediation effect of Reasoning on the relationship s between AI and the LMS. Overall, the results also remained supported towards the incorporation of Artificial Intelligence (AI) along with Natural Language Processing (NLP) and Reasoning in Learning Management Systems (LMS). The researchers conclude that AI in Learning Management Systems is widely applied in Pakistani institutions. The young students also acknowledge the benefits of AI-enabled LMS that have enhanced their learning experiences and provided them with logical solutions and answers to their complex queries. Further, the study limitations are discussed and highlighted accordingly.

This study investigates the effectiveness of Learning Management Systems (LMS) in enhancing the pedagogical skills of teachers through online training. In the context of increasing globalization and the need for quality education, the research aims to identify how LMS can bridge the gap in access to professional development, particularly for educators in remote areas. Utilizing a qualitative approach with phenomenological case studies, data were collected through semi-structured interviews and document analysis involving six teachers from UPT SMP Negeri 6 Siak Hulu. The findings reveal that LMS significantly facilitates structured learning by providing easy access to educational resources, tasks, and assessments. Teachers reported positive experiences, highlighting improved organization and interaction in their teaching practices. However, challenges such as unstable internet connectivity and the need for adaptation to new technology were also identified. The study underscores the importance of ongoing support and training for educators to maximize the benefits of LMS. These findings contribute to the broader discourse on integrating technology in education, emphasizing that effective implementation of LMS can enhance teaching quality and student outcomes. Overall, this research advocates for continued investment in technological resources and training to foster an effective learning environment in modern education.

When a university or an organization wants to offer a program of online courses and online collaborative spaces, one of the major decisions concerns the virtual environment - VLE - Virtual Learning Environment or LMS. This decision is quite difficult to make because looking for an online training system we may get stuck choosing between two similar-sounding, but ultimately different systems: Learning Management Systems (LMS) and Learning Content Management Systems (LCMS). Coping with the boundaries between the two, means to be aware of the key differences and similarities those organizations should keep in mind when looking to add e-learning elements to their training programs. This paper aims to make some conceptual and functional clarifications of the terms in order to cover a comparative analysis of the possibilities of using these systems in the context of an extremely dynamic educational environment and market. UNDERSTAND THE TERMS Using e-learning techniques are a credible and effective response to the challenges of the current educational environment. It can be motivating for users to participate, given the advantages they offer: access to a wide array of formative approaches and supple and flexible learning strategies (active pedagogy, participatory training, meta knowledge, learning focused on problems, games, and conflict resolution, etc..) diversified assessment (self-assessment, formative assessment, summative or certificate etc..) asynchronous approach in time and space via the Internet, dynamic content, collaborative environment, feedback, low cost. These facts are common nowadays and generally accepted, and anyone located on the improvement road seems to recognise the strategic importance and the educational opportunities of formal and ongoing training supported by different type of e-learning systems: CMS, LMS or LCMS. LMS: A platform for managing people A Learning Management System is a software package hosted on the server, and intended for the development, management and delivery of courses and training programs. It provides the platform for managing the experience of students or trainees as they interact with e-learning content. In this case the e-learning content has already been created, and more than that, it is in the right format to be compatible with the LMS system. The services provided by an LMS generally include access control, synchronous and asynchronous communication tools, management of user groups. The following main characteristics of an LMS system could be considered: o emphasis on registering participants, tracking their activity, and gauging their progress through online coursework; o interaction with existing human resource information systems, to track the pool of those eligible for participation, and for reporting back outcomes; o analytics and performance management tools. An LMS can equally be seen as: - a specialized pedagogical content management system - editing and distribution of educational content, the ordering of training modules, training and evaluation management; LMS users are mainly trainees, guided by trainers and tutors; the primary objective of LMS is to deliver and manage training support, focusing especially around courses and less on their content; the limits of such a system are given by the difficulty of creating, modifying or reuse of the content.

Artificial Intelligence (AI) is a fast-growing area of study that stretching its presence to many business and research domains. Machine learning, deep learning, and natural language processing (NLP) are subsets of AI to tackle different areas of data processing and modelling. This review article presents an overview of AI impact on education outlining with current opportunities. In the education domain, student feedback data is crucial to uncover the merits and demerits of existing services provided to students. AI can assist in identifying the areas of improvement in educational infrastructure, learning management systems, teaching practices and study environment. NLP techniques play a vital role in analyzing student feedback in textual format. This research focuses on existing NLP methodologies and applications that could be adapted to educational domain applications like sentiment annotations, entity annotations, text summarization, and topic modelling. Trends and challenges in adopting NLP in education were reviewed and explored. Contextbased challenges in NLP like sarcasm, domain-specific language, ambiguity, and aspect-based sentiment analysis are explained with existing methodologies to overcome them. Research community approaches to extract the semantic meaning of emoticons and special characters in feedback which conveys user opinion and challenges in adopting NLP in education are explored.

Scalable Autograder and LMS Integration

Most learning management systems (LMS) use a file uploader that receives archived source code from a student for programming exercises and requires the teacher to grade it manually. In this approach, students do not learn to use standard professional tools to work on a source code, and the teachers also spend much time grading. There is an opportunity to use source control management (SCM), such as Git via GitHub or GitLab, as a submission method for students. This mechanism helps programming students practice a common process used in the professional world as early as possible. Rather than manual grading, autograders are widely used in Learning Management Systems to help instructors grade student works. Autograders work faster than humans and provide objective grading. This paper discusses an integration model for learning management systems, source control management, and autograders, each of these components is usually used separately. We write a reference implementation that uses Moodle as the LMS and GitLab as the SCM. We also build a minimally functional autograder in place for proof-of-concept in this implementation. Students can submit their work using the merge request feature provided by GitLab from the repository that they fork from the instructor’s original repository. The system captures the merge request event, and the autograder starts grading student works and updates student scores in the LMS. We also discuss how the system performs when dealing with many requests semi-simultaneously to simulate an exam situation. The system follows the Service-Oriented Architecture (SOA) principle to keep each component agnostic, and developers can use any LMS, SCM, and autograder they find suitable. In our experiment, the system can handle 200 submissions in a short period amount of time. The results are that the student learns SCM basic workflow using the system, and the teachers are helped by automated grading.

BackgroundAuthentic assessment and effective feedback are among various strategies that promote learning in the assessment process. These strategies are commonly used during clinical placements. However, they are rarely implemented in the didactic portion of physiotherapy education despite the benefits this type of assessment may bring to achieving students’ learning and outcome.MethodsThis mixed method study investigated how an authentic continuous assessment coupled with rubrics facilitated physiotherapy students’ learning process in a real-life complex skill of exercise prescription and instruction. The study also explored the relationship between different activities in the Learning Management System (LMS) and learning outcomes. Qualitative data was collected using a focus group and an analysis of discussion forum posts. Quantitative data included various information from a questionnaire, the LMS and assessment score.ResultsThematic analyses from the focus group and discussion forum posts suggest that students used a cyclical self-regulated learning process as a result of authentic task design and rubrics for feedback facilitation. Interestingly, the discussion forum access was found to be moderately and significantly correlated with assessment score by Spearman’s rank correlation (ρ = 0.59, p < 0.01), while the students did not find the discussion forum useful.ConclusionsOverall results suggest the promotion of self-regulated learning in this authentic continuous assessment. The roles and goals of each authentic task within the assessment should be made explicit in order to raise cognitive awareness of benefits.

This study aims to examine the effect of Learning Management System (LMS) on the success of blended learning using the Systematic Literature Review (SLR) method. The literature analyzed came from accredited journals indexed in Scopus and Google Scholar databases, with a publication range of 2020-2024 and the selection process was carried out based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) so that 20 journals were obtained that showed that LMS is effective in increasing the success of blended learning. Based on the analysis of articles and journals, this review highlights that LMS significantly increases several aspects of blended learning. Specifically, the use of LMS leads to a significant increase in several aspects of blended learning. LMS has been shown to be a critical determinant in enhancing student engagement within blended learning environments. Furthermore, LMS supports early data detection, which ultimately improves student learning outcomes. Students also experience higher satisfaction levels when LMS is integrated into blended learning courses. Beyond student benefits, LMS facilitates enhanced course management and delivery, providing a robust framework for modern education with effective organization and flexible learning experiences. The effectiveness of teaching is also improved through the integration of technology-mediated learning approaches via LMS. Moreover, LMS can accelerate the adaptation of teachers to distance education, increasing adoption rates and supporting various aspects of blended learning implementation. From this study, it can be seen that in general it shows indicators that LMS can improve student learning outcomes and learning independence in accordance with the objectives of blended learning. However, the effectiveness of LMS varies by educational context, and the intention to continue using LMS is influenced by perceptions of usefulness and satisfaction. The review concludes that several key elements maximize the impact of LMS on blended learning success: positive user experience, active teacher involvement, utilization of LMS data, and consideration of the educational context. LMS adoption is driven by the need for flexibility and to accelerate the digitalization of education, its can be seen from the increased effectiveness and ease of learning with flexible and cost-effective access to materials, as well as increasing learning independence by facilitating students to learn according to their respective speeds and learning styles.Effective implementation, however, requires addressing teacher anxiety by providing adequate support, such as internet and computer/gadget availability. These findings confirm that LMS plays a very important role in increasing the success of blended.

Today many schools, universities and institutions recognize the necessity and importance of using Learning Management Systems (LMS) as part of their educational services. This research work has applied LMS in the teaching and learning process of Bulacan State University (BulSU) Graduate School (GS) Program that enhances the face-to-face instruction with online components. The researchers uses an LMS that provides educators a platform that can motivate and engage students to new educational environment through manage online classes. The LMS allows educators to distribute information, manage learning materials, assignments, quizzes, and communications. Aside from the basic functions of the LMS, the researchers uses Machine Learning (ML) Algorithms applying Support Vector Machine (SVM) that will classify and identify the best related videos per topic. SVM is a supervised machine learning algorithm that analyzes data for classification and regression analysis by Maity [1]. The results of this study showed that integration of video tutorials in LMS can significantly contribute knowledge and skills in the learning process of the students.

The Practical Connection

With the development of online education, online teaching and online learning are playing an increasingly important role in modern teaching. Learning management system (LMS) is basic environment of developing online learning. It has offered a network environment of study and work for teachers and students, it is a conservative technology for managing group, providing tools, and delivering content. Media coverage of Web 2.0 concentrates on the common applications/services such as blogs, video sharing, social networking and podcasting—a more socially connected Web in which people can contribute as much as they can consume.web2.0 created enormous challenges to LMS. According to a literature search and empirical investigation, this study describes the effect of Web2.0 on LMS. The first is integrating Web 2.0 Features into a Learning Management System, using edu2.0 as an example. The second is using web2.0 applications as an LMS. The main advantages of choosing web2.0 as LMS and a case are showed. At last, it tells us how to choose between the LMS and the web2.0.

The purpose of the research is to utilize Deep Learning (DL) algorithms to analyze student behavior and learning management systems, to address the growing need for effective monitoring and intervention strategies in educational environments. This study proposed a novel parallel-computing fruit fly-optimized adjustable recurrent neural network (PFFO-ARNN) to analyze student online temporal behaviors for the early prediction of course performance. For this research, student behavior data was collected from the learning management system used in the college. The data is preprocessed using tokenization and the features are extracted using word2vec to convert words into numerical vectors from preprocessed data. We evaluate the prediction performance of PFFO-ARNN using various parameters and compare it to other conventional techniques. The findings show that early identification of students at risk with a greater level of prediction Accuracy, Precision, Recall, and F1-score was achieved by employing the PFFO-ARNN. Furthermore, compared to other conventional techniques, the PFFO-ARNN approach demonstrated greater generalization and better prediction performance.

Study question Do AI-based and manual embryo selection strategies based on morphological and kinetic evaluation favour male over female embryos? Could the differences enable sex selection? Summary answer Male embryos receive higher-quality scores using both AI-based models and manual grading, but not using deep-learning approaches. The differences, although present, preclude reliable sex selection. What is known already A key aspect of IVF, embryo selection, involves methods executed manually via direct embryo morphological assessment, or by artificial intelligence algorithms which assess parameters such as tPNf, t2, t3, t4, t5, t8, tB and ICM and TE grades using time-lapse imaging. However, all current embryo selection models do not take embryo sex into account despite reported differences in developmental timings between XX and XY embryos. If the predictions of embryo selection algorithms themselves are affected by embryo sex, their accuracy and fairness may be impacted, leading to sex disparities in populations heavily reliant on IVF. Study design, size, duration A retrospective study was conducted on 1411 embryos with known sex information following PGT-A, at a single centre between 2018-202, making this the largest study to date interrogating morphological and morphokinetic sex differences using time-lapse and PGT-A data. Three embryo assessment methods were interrogated: manual morphological grading (Gardener system), KIDScore D3 (VitroLife) and CHLOE (Fairtility). These algorithms are representative of the current embryo grading landscape, encompassing manual selection, traditional machine-learning and modern deep-learning approaches, respectively. Participants/materials, setting, methods Kinetic parameters were annotated using CHLOE on incubator time-lapses. KIDScore computation was implemented according to Petersen et al.,2016 making use of kinetic annotations from CHLOE. Manual morphological grading was done at the blastocyst stage using a modified Gardner system. Mann-Whitney U and chi-squared tests compared XX and XY gradings, with detailed analyses on morphokinetics (tPNf,t2-t9+,cc2,cc3,tM,tSB-tEB,ICM and TE grades). To evaluate the ability of morphokinetic differences to predict embryo sex, four machine learning models were built. Main results and the role of chance Overall, XY embryos (4.182 ± 1.353, N = 692) were more likely to be assigned higher scores than XX embryos (4.022 ± 1.420, N = 642) by the machine learning-based KIDScore (U = 207604, p = 0.0182). Similarly, XY (462/668) blastocysts were more likely to receive good grades than XX (351/614) blastocysts under manual morphological grading (χ2 =19.843, df = 1, p &amp;lt; 0.00001). We pinpoint the source of sex disparities in conventional morphological grading to variations in trophectoderm morphology (male embryos receiving higher TE grades). Nevertheless, the observed differences, although present, were of marginal magnitude, and the overlap between the sexes substantial enough to preclude reliable sex selection. No significant difference was found in the scores assigned by more advanced deep learning methods such as CHLOE EQ scores between XX (0.787 ± 0.276, N = 628) and XY (0.802 ± 0.254, N = 679) embryos (U = 204621, p = 0.208). Limitations, reasons for caution This retrospective, single-centre study encounters limitations such as selection bias and constrained generalisability beyond the specific centre. It focuses on blastocyst-stage sex analysis, which, while statistically-powerful, may not fully represent the societal implications of embryo selection on sex ratios. The use of automated kinetic annotations, while efficient, might introduce inaccuracies. Wider implications of the findings Our findings raise significant questions surrounding the fairness of widely-used embryo assessment methods. We highlight the urgent need for the reproductive health community to recognise and address algorithmic bias, ensuring equitable and ethical treatment of all embryos, especially in the context of increasing global reliance on assisted reproduction. Trial registration number not applicable

Modern information tools have a significant impact on the transformation of basic approaches to education, and learning management systems (LMS) have become an important mechanism in this process. The purpose of this review is to show the state of the art and trends in the use of LMS in modern education. To achieve this goal, the article uses the scientific method of content analysis of scientific literature selected specifically (78 items of literature were analysed in total). The results show that the development of Internet technologies contributes to the emergence of new forms of information exchange, including e-learning platforms. E-learning is convenient and mobile for students and provides an individual approach. Certain e-learning technologies can be used not only in online education, but also in traditional forms of education, such as full-time and part-time. The most popular are the capabilities of Moodle, which was established through the analysis of scientific literature. Blackboard and Google Classroom are also important and popular, but they have more situational applications. Other LMSs are more regionally popular, although they also play a role in the learning process. The results also emphasise that modern LMS technologies make learning more accessible and interesting for students, which makes the process more democratic and accessible to learning. The conclusions draw attention to the importance of continuing research, as digital technologies is evolving, making them a subject for further studies.

Learning Management Systems Use in Science Education