Fine-grained sentiment analysis of massive open online courses evaluation

Introduction . Modernity, characterized by the expansion of digital educational environments, defines key challenges for the implementation of the principles of social justice. The “fading” of the inclusive potential of massive open online courses (MOOCs), the understanding of their availability solely as a technical possibility of registration – all this makes us return to understanding true equality in global online education. A new study of MOOC problems is determined by the need to overcome systemic barriers to sustainable and equitable educational development. Methodology and sources . The study of structural limitations of social justice and accessibility in MOOCs, the identification of factors of digital, economic, cultural and linguistic inequality are based on a synthesis of sociological analysis and socio-philosophical reflection of the concepts of “justice as fairness”. A systemic approach allows us to consider MOOCs as a holistic but contradictory ecosystem that reproduces social disparities. The sociocultural approach makes it possible to analyze the conditions of real, rather than formal, participation of various groups in the educational process. Results and discussion. The concept of “pedagogical justice” helps to counteract the illusion of universal accessibility of MOOCs. Its main idea is to ensure equality of educational results by overcoming the digital divide, economic barriers, language hegemony and cultural irrelevance of content. The philosophy of “equality of opportunity” has similar principles of ensuring the “quality of educational functioning”, denying “technological determinism”, and asserting the priority of inclusiveness over scalability. Effective participation in MOOCs depends on a set of “access opportunities”: the ability to overcome technological limitations, financial barriers, language barriers, and cultural alienation. The wider the range of these opportunities for each student, the higher the level of social justice in online education. The philosophy of “pedagogical justice” is associated with the concept of sustainable development of the digital educational environment. Models of “inclusive MOOCs” implementing the practices of adaptation, support and multicultural design try to put into practice the principles of justice, creating a balance between mass and equality, technology and human-centeredness. Conclusion . Combining a critical analysis of barriers with the principles of pedagogical justice can give a new impetus to the development of MOOCs and change the content of their mission, strengthening its humanistic and inclusive focus. The integration of these principles into the technological, economic and pedagogical foundations of MOOCs is a condition for their transformation into an instrument of genuine educational equality.

The massive open online course (MOOC) movement gained particular prominence during the COVID-19 pandemic, serving as a key instrument for knowledge transfer and ensuring the continuity of the educational process. The aim of this study is to identify and analyze faculty attitudes toward the use of the AshykBilim platform. The term «AshykBilim» derived from the Kazakh language, means «Open Education». A total of 28 instructors participated in the study. The primary motivations for faculty engagement in developing and delivering courses on the AshykBilim platform include the desire to share professional knowledge and experience, to gain pedagogical and methodological expertise that enhances the effectiveness of face-to-face teaching, to strengthen professional visibility, and to receive financial incentives. Both qualitative (content analysis) and quantitative methods were employed to analyze the respondents’ answers. The study examined several factors, including instructors’ perceptions of the significance and potential of MOOC practices, directions for their further development, motivations for designing and delivering online courses, characteristics of instructional materials used, and the extent to which acquired experience is transferred into formal education courses. A survey was conducted to evaluate MOOCs on the AshykBilim platform from the instructors’ perspective, including aspects such as the integration of learners with diverse social and educational backgrounds, flexibility in learning schedules, and system usability. In particular, the study highlights the need to strengthen institutional support, increase recognition and visibility, and promote the formal acknowledgment of learning outcomes through equivalency and official certification in Kazakhstan. The findings indicate that instructors perceive MOOCs on the AshykBilim platform as an important component of the digital transformation of education, encompassing asynchronous learning formats, interactivity, blended and student-centered approaches, knowledge assessment, and content development. To support the effective operation of the platform, a regulatory framework has been developed, defining platform usage, role distribution, user support, and integration with the curriculum.

ABSTRACT Massive Open Online Courses (MOOCs) have become a prominent platform for teacher professional development, particularly in Teaching English to Speakers of Other Languages (TESOL). This exploratory study employs corpus linguistics methods, specifically keyword, collocation, and thematic analyses, to examine learner perspectives on the ‘TESOL specialization’ MOOCs on Coursera, which consist of eight courses designed for English language teachers. By analysing a corpus of 6776 online reviews, the study identifies the major themes characterising learners’ experiences. Key findings reveal that learners highly value these MOOCs for their engaging and informative content, well-presented, easy-to-follow materials, thought-provoking peer-reviewed assignments, practical applicability to classroom teaching, and contribution to professional growth. These insights provide valuable implications for MOOC designers, highlighting the need for courses that are not only pedagogically rich but also user-friendly and directly relevant to teaching practice. This research contributes to understanding effective MOOC design in teacher education, offering a data-driven approach to enhancing online learning experiences.

<span>Self-regulated learning (SRL) has been well documented in the literature for its benefits for students’ learning success. However, there is still a dearth of imperial intervention that helps promote students’ self-regulation, and a theoretical justification for such a program is essential. To date, literature has shown three prominent theories: social cognitive, social-cultural, and cognitive constructivist. The goal is to explore the conceptualization of SRL, which, despite it is long history, lacks a universally accepted definition. We analyze these theories and their models to determine which best supports the design of a SRL strategy intervention for university students in massive open online course (MOOC) environments. Based on this analysis, we propose a working definition of SRL that fits the unique demands of MOOCs. The results suggest that the social-cognitive theory offers the most suitable framework, as it integrates cognitive, metacognitive, motivational, and social aspects of learning. Additionally, it provides a practical model of strategies that can be implemented in MOOC-based learning environments.</span>

ABSTRACT With the advent of various “AI +” scenarios, the integration of Artificial Intelligence (AI) with Massive Open Online Courses (MOOCs) represents a significant trend in the digital transformation of education. This paper presents two studies: one focused on AI and MOOCs in general, and the other on AI and tourism-specific MOOCs. we conducted a bibliometric analysis on Web of Science (WoS) publications, applying co-word (keyword co-occurrence) analysis, LLR-based clustering, burst detection, and timeline mapping to visualize knowledge structures and emerging trends. Two datasets were analyzed: AI – MOOC studies (2014–2023, n = 73) and AI – tourism MOOC studies (2014–2024, n = 19), both processed and visualized in CiteSpace. The findings demonstrate the close relationship between AI and MOOCs, contributing to a more up-to-date understanding of this evolving field. The study identifies four potential opportunities and four key challenges in applying AI technologies to MOOCs, along with specific insights into their application and development within the tourism discipline. AI is poised to drive the robust development of MOOC-based education by enhancing access to educational resources, increasing participation efficiency, enabling effective evaluation, and supporting more forward-looking predictions. However, at the same time, it is essential to address concerns regarding the accuracy and reliability of AI technologies, ensure learner privacy and data security, and tackle ethical issues, which remain critical considerations in this context.

While the role of human capital is central in realizing smart cities, a skilled workforce is significantly lagging behind demand, hindering the incorporation of technological advancements in urban management. To curb this gap, upskilling and training will be a critical investment in future cities. While various educational means and types are suggested in the literature, the actual training offered remains inadequate. This paper assessed the use of massive open online courses (MOOCs) as a continuing training approach for the smart city workforce by examining the learners’ perceived relevance, quality and usefulness and acquisition of knowledge and skills. Results showed that MOOCs can be an effective approach for continuing professional development of the smart city workforce, as the vast majority of the participants considered the MOOC engaging, offering them useful and relevant skills, while reporting a significant improvement in their skills. A competency-based structure, multidisciplinary training modules, multiple smart city stakeholder engagement, certification, and updated content of good quality have been identified as key factors for developing effective MOOCs for this professional sector. Our findings contribute to understanding how continuing education programs for smart city workers should be designed and developed, offering critical guidance to various stakeholders, such as educational providers, municipal authorities and current and prospective smart city professionals.

Accurately predicting student dropout in Massive Open Online Courses (MOOCs) remains a critical challenge in educational data mining. While Spatio-Temporal Graph Neural Networks (STGNNs) have shown promise, established frameworks typically rely on first-order temporal dependencies, recursively deriving the current state solely from its immediate predecessor. We argue that such recursive compression fails to capture complex student behaviors, which are driven by the interplay between immediate short-term shocks and accumulated long-term patterns. To address this, we propose the Multi-Scale Spatio-Temporal Graph Network (MST-GCN). The core of our framework is a novel MST-RGCN layer featuring a Spatially-Conditioned Adaptive Gate. This mechanism dynamically modulates the fusion of short-term and long-term memories by explicitly conditioning on the evolving heterogeneous graph context. Comprehensive experiments on two large-scale benchmarks, KDD Cup 2015 and XuetangX, demonstrate that MST-GCN yields superior predictive performance compared to established baselines. Notably, our model exhibits remarkable robustness in unstructured, self-paced learning environments. Furthermore, qualitative analysis reveals that the model learns an interpretable policy: prioritizing long-term history to identify at-risk students while leveraging short-term momentum to predict successful learners. Our source code is publicly available at https://github.com/wudongze9/MST-GCN .

Massive Open Online Courses (MOOCs) have significantly altered the higher education landscape by promoting accessible and flexible learning opportunities across the globe. This review critically examines research published over the past decade on MOOCs and their implications for teaching, learning, and institutional strategies. It explores emerging trends, pedagogical innovations, and common barriers such as completion rates, learner engagement, and digital inequities. While MOOCs have expanded access and encouraged lifelong learning, challenges related to quality assurance, accreditation, and localized adaptation remain unresolved. The review also highlights future prospects, including personalized learning through artificial intelligence, blended models, and sustainable implementation strategies.

This study investigates the use of meaning forms within video lectures in Massive Open Online Courses (MOOCs), revealing that different configurations of meaning forms fulfill social, instructional, and semiotic functions. The findings highlight that some meaning forms are frequently used, while others are less prevalent. A key discovery is the positive correlation between the variety of meaning forms and learner perceptions, where a broader range of forms was associated with more favorable evaluations. Notably, contextual objects, social speech acts, and camera edits or changes in angle were positively perceived, whereas use of images and text had a negative impact. These insights suggest that the mise-en-scène of video lectures plays a critical role in shaping learner experiences. The study also introduces transpositional grammar as a new theoretical lens for analyzing these meaning forms, contributing a fresh perspective to the field. Areas for future research include underexplored elements such as the role of silence, branding, and editing techniques in creating meaning. These findings offer valuable guidance for MOOC designers, emphasizing the importance of deliberate design choices in enhancing learner engagement and perception.

Rapid technological advancements have revolutionized educational delivery, making learning more accessible and flexible than ever before. Among the most revolutionary advancements in education are Massive Open Online Courses (MOOCs), which is a web-based platforms that provide open access to high-quality educational resources for learners worldwide. In India, the government’s SWAYAM initiative embodies a significant effort aiming at making education more accessible through MOOCs, particularly targeting the nation’s youth. Nevertheless, there remain ongoing inquiries about how effectively these platforms convert theoretical potential into practical learning outcomes. This paper develops an integrated conceptual framework grounded in constructivism, connectivism, self-regulated learning theory, and the community of inquiry model to examine SWAYAM-MOOCs’ potential and limitations in educating Indian youth. Drawing on existing literature and the specific context of education in India, the authors undertake a comprehensive analysis of the the platform’s features, benefits, prospects, and ongoing challenges associated with the implementation of the platform. The analysis reveals that while MOOCs hold transformative potential for youth education, their success depends critically on addressing infrastructure gaps, supporting learner autonomy, and building meaningful learning communities, challenges that remain particularly acute in India’s diverse and often underserved educational landscape.

Effective interprofessional collaboration (IPC) is essential for patient safety; yet, poor teamwork and communication remain key challenges in high-pressure settings like the emergency department (ED), contributing to medication errors. Although Team Strategies and Tools to Enhance Performance and Patient Safety (TeamSTEPPS)-based interprofessional education addresses these issues, adaptation in clinical settings remains difficult. To bridge this gap, we developed Emergency Room Virtual Simulation-Based Interprofessional Education (ER-VIPE), a multimodal, TeamSTEPPS-integrated intervention designed to enhance IPC and reduce medication errors. The aim of the study is to evaluate the effectiveness of ER-VIPE in enhancing IPC performance among emergency physicians, nurses, and pharmacists and in reducing medication errors. The primary objective is to assess changes in IPC performance in both real-world ED settings and in computer-based simulations. The secondary objective is to examine the intervention's impact on medication error rates in the ED. This quasi-experimental study involved 15 interprofessional teams (each comprising 1 physician, 1 pharmacist, and 2 nurses), undergoing the ER-VIPE training. This multimodal intervention included 2 medical films, a massive open online course on TeamSTEPPS and IPC, and a computer-based simulation session on acute chest pain and cardiac arrest scenarios via the simulation-based interprofessional education (SIMBIE) platform. Co-debriefings were provided as a complement to the SIMBIE session, guiding participants through positive feedback and areas of improvement. TeamSTEPPS performance was measured using the Modified TeamSTEPPS and Team Performance Observation Tool (mTPOT) in both simulation and real-world ED settings. Generalized estimating equations with a Gaussian family, identity link, and exchangeable correlation structure were used to evaluate IPC score changes. Chi-square and Fisher exact tests were applied to compare near-miss and actual medication errors before and after the intervention. A 2-tailed P value <.05 was considered statistically significant. The study was conducted from November 2023 to January 2024 at a university hospital with 60 participants. Following the co-debriefing session in the simulation, overall mTPOT scores increased by 2.00 points (P<.001), with the greatest improvement among physicians (+2.70), followed by nurses (+1.75) and pharmacists (+1.56). In the ED, most mTPOT domains improved significantly across all professions 2 months after the intervention (P<.001). Although no significant reduction in harmful medication errors was observed, reporting of near-miss prescription errors increased significantly (P=.01). ER-VIPE enhanced IPC among ED physicians, nurses, and pharmacists, with sustained effects observed up to 2 months in real-world settings. The combination of medical films and massive open online courses provided accessible foundational knowledge, while computer-based virtual SIMBIE with co-debriefing reinforced practical communication and teamwork. Increased near-miss reporting suggests improved situational awareness and a more transparent safety culture. This multimodal training model shows promise for advancing collaboration and patient safety in emergency care.

Studies highlighting the prevalence of inappropriate prescribing and preventable harm emphasize the need to enhance prescribing competencies. This paper describes distinctive features, launch and evaluation of massive open online course (MOOC) Prescribing Skills Course (PSC) designed for medical interns and registered medical practitioners (RMPs). PSC development funded by Indian Council of Medical Research (ICMR), guided by national and international experts, with content aligned with the national medical curriculum and inputs from stakeholders, included video lectures with case scenarios, demonstration videos, assignments (pre- and post-course MCQ tests, prescription analysis) and structured feedback. Hosted on Government of India's online learning platform, course infrastructure enabled data collection for evaluation and analysis. PSC having 50 modules was conducted with interns' enrolment/completion 4327/1164 (26.9%), 4098/815 (19.9%), 665/ 129 (19.4%) in 2020, 2021, 2022 and RMPs 1984/557(28.1%), 448/138 (30.8%) in 2021, 2022, respectively. Enrolment was significantly lower in regions with weaker health indices (rate ratio 0.35 with 95% CI: 0.32-0.38; P < 0.001; Poisson regression test). Participants rated course content, relevance, quality, assignment usefulness 'excellent' to 'very good'. RMPs demonstrated higher baseline scores and greater improvement (from 60% to 73.3% p < 0.001 in cycle 3) compared to interns. The PSC- MOOC is convenient, accessible with experiential learning for large numbers. Performance of RMPs may suggest practical relevance and applicability. Module-wise performance analysis and enrolment variation provided insights for future strategy. Limitations include inability to assess the impact on prescribing practices. PSC-MOOC represents a promising, scalable educational strategy. Our experience would be useful to other countries.

With the rapid expansion of digital learning in education, Massive Open Online Courses (MOOCs) have emerged as valuable platforms for enhancing access and quality in teacher education. This study investigates the perception of secondary grade prospective teachers towards MOOCs, with a focus on how gender and academic stream influence these perceptions. The study employed a quantitative cross-sectional survey research design. A total of 259 B.Ed. students from Mysore were selected using a stratified random sampling technique and surveyed using a validated 30-item perception scale covering five domains: study habits, learning outcomes, benefits and accessibility, usability and experience, and multimedia and resource sharing. The instrument demonstrated good reliability (Cronbach’s alpha = 0.843). The data were analyzed using descriptive statistics and independent samples t-tests followed by Cohen’s d for effect size. Results indicated that a majority of participants (79.9%) held a moderate perception of MOOCs. While gender differences in overall perception were not statistically significant, female participants rated higher in benefits and multimedia-related domains. Science stream students exhibited significantly more positive perceptions across multiple dimensions compared to their humanities counterparts. The findings suggest integrating structured MOOC orientation within B.Ed. programs, curricular integration of platforms such as SWAYAM for supplementary learning, and institutional initiatives to strengthen the digital competencies of prospective teachers for effective engagement with online learning environments.

Access online courses, and they can be studied anywhere, anytime. The Thai government supports the use of Thai MOOC (Massive Open Online Courses) as part of Thailand’s 20-year national strategy to build competitiveness, emphasizing new ways of learning by creating the Thai MOOC Open Learning Service. This platform provides useful information to all users for accessing learning in their fields of interest. Thai MOOC offers a safe environment for individuals from diverse backgrounds to acquire valuable knowledge. This model benefits Thai MOOC by providing a system that offers a clearer picture of overall users, including the Thai Cyber University and lectures within the Thai MOOC system. Data collection and analysis employed a mixed-method approach. Qualitative research involved 21 experts in Thai MOOC, with expert consensus achieved through the rough set Delphi approach. Quantitative research gathered data from 800 actual Thai MOOC users. The analysis utilized both descriptive and inferential statistical methods. The results identified seven key factors: 1) Knowledge Sharing, 2) Thai MOOC Features, 3) Motivation and Usage, 4) Perceived Usefulness, 5) Perceived Ease of Use, 6) Attitude Toward Use, and 7) Actual Use. These factors are essential for Thai MOOC developers to understand user attitudes and improve the platform accordingly.

Massive open online courses (MOOCs) are well-known for offering flexible learning; however, they also pose challenges for English-as-a-foreign-language (EFL) learners, particularly in maintaining motivation and engagement in such self-paced learning online courses. This study explored the factors influencing EFL students' participation in a MOOC through the lens of Expectancy-Value Theory and Socio-Cognitive Theory. Employing a qualitative design, involving 31 EFL students from a private university in the Mekong Delta enrolled in a public speaking MOOC, the study collected data of 20 reflective journals and 12 semi-structured interviews from these participants. The data was analyzed using reflexive thematic analysis. The findings revealed that student engagement increased when learners expected success, perceived the course as valuable, and employed self-regulated learning strategies. Motivation was sustained through goal setting, time management, and persistence; however, language barriers, technological issues, and social isolation impeded learning. Despite these obstacles, students use goal setting, time management, and persistence to sustain motivation. Expectancy–value theory (EVT) explains how perceived value and expectations of success shape engagement, whereas social cognitive theory (SCT) emphasizes self-efficacy and self-regulation as key drivers of motivation. These findings can inform educators, curriculum designers, and policymakers in developing more supportive online learning environments. Alongside recommending inclusive instructional strategies, including linguistic support, interactive content, and community-building, the study urges research into the long-term effects of SRL strategies and the effectiveness of SRL-based training for EFL learners in varied MOOC contexts.

ABSTRACT This study develops and validates a multidimensional benchmarking instrument to evaluate the pedagogical quality of sNOOCs (social massive open online courses), integrating dimensions related to pedagogical design, usability, artificial intelligence (AI) and the metaverse. Through an instrumental validation study with a sequential-explanatory mixed methodology design. Using a sequential explanatory mixed-methods approach, a 24-item questionnaire was designed and administered in a peer assessment conducted by 135 postgraduate students at UNED (Spanish University of Distance Education), generating 937 assessments. The psychometric results confirm the excellent reliability of the instrument (Cronbach’s α = 0.97) and its structural validity, with a factor analysis explaining 77.6% of the variance. The findings reveal that pedagogical design is the highest-rated dimension, followed by usability and the quality of AI, showing a strong correlation among them. By contrast, the integration of the metaverse emerges as the main challenge, receiving the lowest rating and showing the greatest dispersion, indicating a lack of effective pedagogical alignment. The research validates peer assessment as a robust methodological strategy and offers a practical tool for continuous improvement of instructional design in advanced digital educational settings, while underlining the need for intentional pedagogical integration of emerging technologies.

Online entrepreneurship education (EE) courses experienced a sharp 66% spike in demand around March 2020, attributed to the COVID-19 pandemic and the subsequent surge in digital entrepreneurship uptake. Completion rates serve as a key indicator of online MOOC efficacy, with students’ psychological attributes and contextual factors often examined as explanatory variables in assessing online course completion. This mixed-methods study explores influential factors in student retention in an EE Massive Open Online Course (MOOC) by using survey responses from 222 Malaysian youths who voluntarily registered for an EE MOOC, which was active from February to October 2021. A Decision Tree approach was chosen to predict the course completion likelihood based on sociodemographic and psychological factors, while qualitative content analysis was conducted to explore participant course enrollment motivations from their textual responses. The results indicated that entrepreneurial intention (EI) does not necessarily translate into EE MOOC completion. Instead, internal locus of control and socioeconomic factors held more priority in predicting completion status. These results were reflected in the students’ thematic narratives from their textual responses. Both completed (CP) and dropout participants (DP) expressed similar entrepreneurial interests and, indeed, in the transferability of entrepreneurial skills and knowledge beyond entrepreneurial settings. However, there was a distinction in clarity; most CPs had well-defined and detailed enrolment goals, whereas the narratives from DPs were mainly ambiguous. Overall, the study contributes to the methodological discussion of using decision tree modelling, expands the application of Social Cognitive Career Theory (SCCT) and informs practical implications in online EE context.

The use of machine learning (ML) in education has had a profound impact on institutional decision-making, student evaluation programs, and teaching strategies. Massive amounts of educational data are produced every day as a result of the quick digitization of education brought about by learning management systems (LMS), massively open online courses (MOOCs), and smart classrooms. Predictive analytics, adaptive learning systems, automated grading, and early detection of students who are at danger are all made possible by machine learning approaches. The main algorithms, practical applications, advantages, difficulties, and potential avenues for further research are all covered in this paper's thorough analysis of machine learning applications in education. The results show that while ML-driven educational systems boost academic achievement and student engagement, they also raise issues with data privacy, algorithmic bias, and model interpretability. The study concludes that the quality and accessibility of international educational systems can be greatly improved by the responsible application of ML technology

Abstract The rapid advancement of digital technologies has fundamentally transformed educational systems worldwide, significantly impacting teacher professional development (TPD). This analytical study explores how digital transformation reshapes teacher learning processes, structures, and outcomes in contemporary educational environments. The increasing integration of Learning Management Systems (LMS), Massive Open Online Courses (MOOCs), mobile learning applications, artificial intelligence (AI), and virtual collaborative platforms has shifted TPD from traditional, workshop-based models to more flexible, personalized, and continuous learning frameworks. Digital TPD empowers teachers to access high-quality training resources, engage in self-paced learning, collaborate through online communities, and implement innovative pedagogical strategies in the classroom. Despite these advancements, the study highlights several challenges that hinder the successful adoption of digital TPD. These include disparities in digital infrastructure, variations in teachers' technological capabilities, the increased workload associated with digital content creation, and limited institutional support. Overall, the analysis suggests that a blended, holistic, and inclusive approach to digital TPD is capable of meeting the learning demands of the 21st century and can significantly contribute to the development of a future-ready teaching workforce. Keywords: Digital transformation, Teacher professional development (TPD), Educational technology, Learning Management Systems (LMS), Massive Open Online Courses (MOOCs), Virtual learning environments, Digital pedagogy, Online training, Professional learning communities (PLCs), ICT integration, Digital competence, Blended learning, E-learning platforms, Continuous professional development (CPD)