Educational data mining and learning analytics for 21st century higher education: A review and synthesis

Evolution and current state of research into E-learning

This article aims to undertake a bibliometric review along with a conceptual and intellectual analysis of research on distance learning and e-learning. The purpose of this study is to focus on several academic fields and offer a comprehensive approach on how research on distance learning and e-learning has been approached since 1970. This work applies several bibliometric techniques to assess the research evolution of topics addressed, the most productive authors and the most influential journals. The findings revealed an exponential increase of publications over the last 20 years, highlighting the evolution of topics. The research themes include four main groups: the first relates to pedagogical processes in terms of effectiveness, outcomes, learning strategies, interaction, and self-regulation; the second group includes aspects associated with ICT applied in distance education; the third group focuses on the perceived value, usefulness, acceptance, and satisfaction of e-learning; and the last group portrays the forced application of distance learning strategies to deal with the consequences of the pandemic. This work contributes to expanding the existing literature devoted to study the structure of research on e-learning. It analyses the most representative authors, institutions, and documents, and gathers the growing literature on e-learning, from distance learning in the seventies until the implementation of online learning in the COVID-19 era.

Disembodied AI and the limits to machine understanding of students' embodied interactions

The embodiment turn in the Learning Sciences has fueled growth of multimodal learning analytics to understand embodied interactions and make consequential educational decisions about students more rapidly, more accurately, and more personalized than ever before. Managing demands of complexity and speed is leading to growing reliance by education systems on disembodied artificial intelligence (dAI) programs, which, ironically, are inherently incapable of interpreting students' embodied interactions. This is fueling a potential crisis of complexity. Augmented intelligence systems offer promising avenues for managing this crisis by integrating the strengths of omnipresent dAI to detect complex patterns of student behavior from multimodal datastreams, with the strengths of humans to meaningfully interpret embodied interactions in service of consequential decision making to achieve a balance between complexity, interpretability, and accountability for allocating education resources to children.

Cognitive Web Service-Based Learning Analytics in Education Systems Using Big Data Analytics

In the field of education, digital learning plays an important part. For each passing day, digital learning is displacing the traditional method of education. An accurate analysis of a student's qualities improves their academic performance. With the advancement of technology and big data, there are many applications for big data analytics, including education. Huge volumes of academic information are being generated, and discovering a technique to harness and analyze this information effectively is a challenging issue among many educational organizations. In this paper, educational clustering big data mining system (ECBDMS) has been proposed. The cognitive web service based learning analytic(CWS-LA) system is integrated to securely categorize and provide ease of access to the data. ECBDMS has been found to improve performance gains of 92.8%, prediction ratios of 88.6%, clustering error ratios of 2.3 percent, learning percentages of 94%, and forecasting accuracy of 97.1 percent when compared to other existing methods.

How do the kids speak? Improving educational use of text mining with child-directed language models

Purpose

Most educational assessments tend to be constructed in a close-ended format, which is easier to score consistently and more affordable. However, recent work has leveraged computation text methods from the information sciences to make open-ended measurement more effective and reliable for older students. The purpose of this study is to determine whether models used by computational text mining applications need to be adapted when used with samples of elementary-aged children.

Design/methodology/approach

This study introduces domain-adapted semantic models for child-specific text analysis, to allow better elementary-aged educational assessment. A corpus compiled from a multimodal mix of spoken and written child-directed sources is presented, used to train a children’s language model and evaluated against standard non-age-specific semantic models.

Findings

Child-oriented language is found to differ in vocabulary and word sense use from general English, while exhibiting lower gender and race biases. The model is evaluated in an educational application of divergent thinking measurement and shown to improve on generalized English models.

Research limitations/implications

The findings demonstrate the need for age-specific language models in the growing domain of automated divergent thinking and strongly encourage the same for other educational uses of computation text analysis by showing a measurable difference in the language of children.

Social implications

Understanding children’s language more representatively in automated educational assessment allows for more fair and equitable testing. Furthermore, child-specific language models have fewer gender and race biases.

Originality/value

Research in computational measurement of open-ended responses has thus far used models of language trained on general English sources or domain-specific sources such as textbooks. To the best of the authors’ knowledge, this paper is the first to study age-specific language models for educational assessment. In addition, while there have been several targeted, high-quality corpora of child-created or child-directed speech, the corpus presented here is the first developed with the breadth and scale required for large-scale text modeling.

Multi-Layer Perception model with Elastic Grey Wolf Optimization to predict student achievement

This study proposes a Grey Wolf Optimization (GWO) variant named Elastic Grey Wolf Optimization algorithm (EGWO) with shrinking, resilient surrounding, and weighted candidate mechanisms. Then, the proposed EGWO is used to optimize the weights and biases of Multi-Layer Perception (MLP), and the EGWO-MLP model for predicting student achievement is thus obtained. The training and verification of the EGWO-MLP prediction model are conducted based on the thirty attributes from the University of California (UCI) Machine Learning Repository dataset's student performance dataset, including family features and personal characteristics. For the Mathematics (Mat.) subject achievement prediction, the EGWO-MLP model outperforms one model's prediction accuracy, and the standard deviation possesses the stable ability to predict student achievement. And for the Portuguese (Por.) subject, the EGWO-MLP outperforms three models' Mathematics (Mat.) subject achievement prediction through the training process and takes first place through the testing process. The results show that the EGWO-MLP model has made fewer test errors, indicating that EGWO can effectively feedback weights and biases due to the strong exploration and local stagnation avoidance. And the EGWO-MLP model is feasible for predicting student achievement. The study can provide reference for improving school teaching programs and enhancing teachers' teaching quality and students' learning effect.

Predicting Student Academic Performance at Higher Education Using Data Mining: A Systematic Review

Recently, educational institutions faced many challenges. One of these challenges is the huge amount of educational data that can be used to discover new insights that have a significant contribution to students, teachers, and administrators. Nowadays, researchers from numerous domains are very interested in increasing the quality of learning in educational institutions in order to improve student success and learning outcomes. Several studies have been made to predict student achievement at various levels. Most of the previous studies were focused on predicting student performance at graduation time or at the level of a specific course. The main objective of this paper is to highlight the recently published studies for predicting student academic performance in higher education. Moreover, this study aims to identify the most commonly used techniques for predicting the student's academic level. In addition, this study summarized the highest influential features used for predicting the student academic performance where identifying the most influential factors on student’s performance level will help the student as well as the policymakers and will give detailed insights into the problem. Finally, the results showed that the RF and ensemble model were the most accurate models as they outperformed other models in many previous studies. In addition, researchers in previous studies did not agree on whether the admission requirements have a strong relationship with students' achievement or not, indicating the need to address this issue. Moreover, it has been noticed that there are few studies which predict the student academic performance using students’ data in arts and humanities major.

Exploring Factors That Affected Student Well-Being during the COVID-19 Pandemic: A Comparison of Data-Mining Approaches

COVID-19-related school closures caused unprecedented and prolonged disruption to daily life, education, and social and physical activities. This disruption in the life course affected the well-being of students from different age groups. This study proposed analyzing student well-being and determining the most influential factors that affected student well-being during the COVID-19 pandemic. With this aim, we adopted a cross-sectional study designed to analyze the student data from the Responses to Educational Disruption Survey (REDS) collected between December 2020 and July 2021 from a large sample of grade 8 or equivalent students from eight countries (n = 20,720), including Burkina Faso, Denmark, Ethiopia, Kenya, the Russian Federation, Slovenia, the United Arab Emirates, and Uzbekistan. We first estimated a well-being IRT score for each student in the REDS student database. Then, we used 10 data-mining approaches to determine the most influential factors that affected the well-being of students during the COVID-19 outbreak. Overall, 178 factors were analyzed. The results indicated that the most influential factors on student well-being were multifarious. The most influential variables on student well-being were students' worries about contracting COVID-19 at school, their learning progress during the COVID-19 disruption, their motivation to learn when school reopened, and their excitement to reunite with friends after the COVID-19 disruption.

Investigating the relationships between MOOC consumers' perceived quality, emotional experiences, and intention to recommend: an NLP-based approach

Purpose

The paper aims to explore and examine the factors that influence the post-consumption behavioral intentions of education consumers with the help of online reviews from a Massive Open Online Course (MOOC) platform in the knowledge payment context.

Design/methodology/approach

The paper adopted a novel mixed-method approach based on natural language processing (NLP) techniques. Variables were identified using topic modeling drawing upon 14,585 online reviews from a global commercial MOOC platform (Udemy.com). The relationships among identified factors, such as perceived quality dimensions, consumption emotions, and intention to recommend, were then tested from a cognition-affect-behavior (CAB) perspective using partial least squares structural equation modeling (PLS-SEM).

Findings

Results indicate that course content quality, instructor quality, and platform quality are strong predictors of consumers' emotions and intention to recommend. Interestingly, course content quality displays a positive effect on invoking negative emotions in the MOOC context. Additionally, positive emotions mediate the relationships between three perceived qualities and the intention to recommend.

Originality/value

Limited research has been conducted regarding MOOC consumers' post-consumption intentions in the knowledge payment context. Findings of this study address the limited literature on MOOC qualities and consumer post-consumption behaviors, which contribute to a comprehensive understanding of MOOC learners' experiences at a meso-level for future paid-MOOC creators.

Peer review

The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-09-2021-0482/

The Design of Academic Programs Using Rough Set Association Rule Mining

Program accreditation is important for determining whether or not a program or institution meets quality standards. It helps employers to evaluate the programs and qualifications of their graduates as well as to achieve its strategic goals and its continuous improvement plans. Preparing for accreditation requires extensive effort. One of the required documents is the program’s self-study report (SSR), which includes the PEO-SO map (which allocates the program’s educational objectives (PEOs) to student learning outcomes (SOs)). It influences program structure design, performance monitoring, assessment, and continuous improvement. Professionals in each academic engineering program have designed their PEO-SO maps in accordance with their experiences. The problem with the incorrect design of map design is that the SOs are either missing altogether or cannot be assigned to the correct PEOs. The objective of this work is to use a hybrid data mining approach to design the correct PEO-SO map. The proposed hybrid approach utilizes three different data mining techniques: classification to find the similarities between PEOs, crisp association rules to find the crisp rules for the PEO-SO map, and rough set association rules to find the coarse association rules for the PEO-SO map. The work collected 200 SSRs of accredited engineering programs by the ABET-EAC. The paper presents the different phases of the work, such as data collection and preprocessing, building of three data mining models (classification, crisp association rules, and rough set association rules), and analysis of the results and comparison with related work. The validation of the obtained results by different fifty specialists (from the academic engineering field) and their recommendations were also presented. The comparison with other related works proved the success of the proposed approach to discover the correct PEO-SO maps with higher performance.

Early Prediction of At-Risk Students in Secondary Education: A Countrywide K-12 Learning Analytics Initiative in Uruguay

This paper describes a nationwide learning analytics initiative in Uruguay focused on the future implementation of governmental policies to mitigate student retention and dropouts in secondary education. For this, data from a total of 258,440 students were used to generate automated models to predict students at risk of failure or dropping out. Data were collected from primary and secondary education from different sources and for the period between 2015 and 2020. Such data contains demographic information about the students and their trajectories from the first grade of primary school to the second grade of secondary school (e.g., student assessments in different subjects over the years, the amount of absences, participation in social welfare programs, and the zone of the school, among other factors). Predictive models using the random forest algorithm were trained, and their performances were evaluated with F1-Macro and AUROC measures. The models were planned to be applied in different periods of the school year for the regular secondary school and for the technical secondary school ((before the beginning of the school year and after the first evaluation meeting for each grade). A total of eight predictive models were developed considering this temporal approach, and after an analysis of bias considering three protected attributes (gender, school zone, and social welfare program participation), seven of them were approved to be used for prediction. The models achieved outstanding performances according to the literature, with an AUROC higher than 0.90 and F1-Macro higher than 0.88. This paper describes in depth the characteristics of the data gathered, the specifics of data preprocessing, and the methodology followed for model generation and bias analysis, together with the architecture developed for the deployment of the predictive models. Among other findings, the results of the paper corroborate the importance given in the literature of using the previous performances of the students in order to predict their future performances.

Chicken Swarm-Based Feature Subset Selection with Optimal Machine Learning Enabled Data Mining Approach

Data mining (DM) involves the process of identifying patterns, correlation, and anomalies existing in massive datasets. The applicability of DM includes several areas such as education, healthcare, business, and finance. Educational Data Mining (EDM) is an interdisciplinary domain which focuses on the applicability of DM, machine learning (ML), and statistical approaches for pattern recognition in massive quantities of educational data. This type of data suffers from the curse of dimensionality problems. Thus, feature selection (FS) approaches become essential. This study designs a Feature Subset Selection with an optimal machine learning model for Educational Data Mining (FSSML-EDM). The proposed method involves three major processes. At the initial stage, the presented FSSML-EDM model uses the Chicken Swarm Optimization-based Feature Selection (CSO-FS) technique for electing feature subsets. Next, an extreme learning machine (ELM) classifier is employed for the classification of educational data. Finally, the Artificial Hummingbird (AHB) algorithm is utilized for adjusting the parameters involved in the ELM model. The performance study revealed that FSSML-EDM model achieves better results compared with other models under several dimensions.

Can avatar homophily influence flow and exploratory behaviour of online users?

Virtual learning environments have been recognized as an area of particular importance by which educators can use to improve desirable learning behaviours. Investigating the impact of different virtual environments on learners' behaviours has become the centre of attention of researchers, especially during COVID-19. The homophily effect of avatar-identity on individuals' perceptions of an environment can be a key for understanding their learning behaviours. This study examined the relationship between key constructs related to avatar homophily (background and attitude) and learners' flow and exploratory behaviour. An online survey was distributed to 157 students (93 males and 64 females with age ranging from 19 to 21 years) who took part in an online learning activity using an avatar-mediated environment (Second Life). The results showed that users' flow experience can be influenced by the function of perceived background and attitude homophily in an avatar-mediated environment. Flow experience was found to mediate the relationship between avatar homophily and learners' exploratory behaviour. This study offers a conceptual understanding of the relationship between homophily and individual's flow state.

Graph Neural Network for Senior High Student’s Grade Prediction

Senior high school education (SHSE) forms a connecting link between the preceding junior high school education and the following college education. Through SHSE, a student not only completes k-12 education, but also lays a foundation for subsequent higher education. The grade of the student in SHSE plays a critical role in college application and admission. Therefore, utilizing the grade of the student as an indicator is a reasonable method to instruct and ensure the effect of SHSE. However, due to the complexity and nonlinearity of the grade prediction problem, it is hard to predict the grade accurately. In this paper, a novel grade prediction model aiming to handle the complexity and nonlinearity is proposed to accurately predict the grade of the senior high student. To deal with the complexity, a graph structure is employed to represent the students’ grades in all subjects. To handle the nonlinearity, the multi-layer perceptron (MLP) is used to learn (or fit) the inner relation of the subject grades. The proposed grade prediction model based on graph neural network is tested on the dataset of Ningbo Xiaoshi High School. The results show that the proposed method performs well in the prediction of senior high school student grades.

Data Mining Techniques and Machine learning Algorithms in the Multimedia System to Enhance Engineering Education

In the current digital era, engineering education worldwide faces a massive challenge in education and career development. By authorizing educators and administrators to migrate to the actions, cloud services technology has transformed into the educational environment. A Multimedia assisted smart learning system (MSLS) has been suggested in this paper where universities/colleges will advocate future development and begin skill-set enhancement courses by e-learning. To classify their employment prospects at the early stage of graduation, this proposed system measures learners' academic/skill data. Machine learning and Data mining are advanced research fields whose accelerated advancement is attributable to developments in data processing research, database industry growth, and business requirements for methods capable of extracting useful information from massive data stores. In addition, for skill set evaluation, a practical algorithm is suggested to find different groups of students that lack the appropriate skill set. The anticipated student groups can be provided with opportunities by e-learning to enhance their required skill set. The findings suggest that more critical choices can boost employment prospects and overall educational development by implementing the new engineering education system.

UBUMonitor: An Open-Source Desktop Application for Visual E-Learning Analysis with Moodle

An inherent requirement of teaching using online learning platforms is that the teacher must analyze student activity and performance in relation to course learning objectives. Therefore, all e-learning environments implement a module to collect such information. Nevertheless, these raw data must be processed to perform e-learning analysis and to help teachers arrive at relevant decisions for the teaching process. In this paper, UBUMonitor is presented, an open-source desktop application that downloads Moodle (Modular Object-Oriented Dynamic Learning Environment) platform data, so that student activity and performance can be monitored. The application organizes and summarizes these data in various customizable charts for visual analysis. The general features and uses of UBUMonitor are described, as are some approaches to e-teaching improvements, through real case studies. These include the analysis of accesses per e-learning object, statistical analysis of grading e-activities, detection of e-learning object configuration errors, checking of teacher activity, and comparisons between online and blended learning profiles. As an open-source application, UBUMonitor was institutionally adopted as an official tool and validated with several groups of teachers at the Teacher Training Institute of the University of Burgos.

Online engagement and performance on formative assessments mediate the relationship between attendance and course performance

In traditional school-based learning, attendance was regarded as a proxy for engagement and key indicator for performance. However, few studies have explored the effect of in-class attendance in technology-enhanced courses that are increasingly provided by secondary institutions. This study collected n = 367 undergraduate students' log files from Moodle and applied learning analytics methods to measure their lecture attendance, online learning activities, and performance on online formative assessments. A baseline and an alternative structural equation models were used to investigate whether online learning engagement and formative assessment mediated the relationship between lecture attendance and course academic outcomes. Results show that lecture attendance does not have a direct effect on academic outcomes, but it promotes performance by leveraging online learning engagement and formative assessment performance. Findings contribute to understanding the impact of in-class attendance on course academic performance and the interplay of in-class and online-learning engagement factors in the context of technology-enhanced courses. This study recommends using a variety of educational technologies to pave multiple pathways to academic success.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1186/s41239-021-00307-5.

Towards teaching analytics: a contextual model for analysis of students' evaluation of teaching through text mining and machine learning classification

Recent trends in educational technology have led to emergence of methods such as teaching analytics (TA) in understanding and management of the teaching-learning processes. Didactically, teaching analytics is one of the promising and emerging methods within the Education domain that have proved to be useful, towards scholastic ways to make use of substantial pieces of evidence drawn from educational data to improve the teaching-learning processes and quality of performance. For this purpose, this study proposed an educational process and data mining plus machine learning (EPDM + ML) model applied to contextually analyze the teachers' performances and recommendations based on data derived from students' evaluation of teaching (SET). The EPDM + ML model was designed and implemented based on amalgamation of the Text mining and Machine learning technologies that builds on the descriptive decision theory, which studies the rationality behind decisions the learners are disposed to make based on the textual data quantification and statistical analysis. To this effect, the study determines pedagogical factors that influences the students' recommendations for their teachers, what role the sentiment and emotions expressed by the students in the SET play in the way they evaluate the teachers by taking into account the gender of the teachers. This includes how to automatically predict what a student's recommendation for the teachers may be based on information about the students' gender, average sentiment, and emotional valence they have shown in the SET. Practically, we applied the Text mining technique to extract the different sentiments and emotions (intensities of the comments) expressed by the students in the SET, and then utilized the quantified data (average sentiment and emotional valence) to conduct an analysis of covariance and Kruskal Wallis Test to determine the influential factors, as well as, how the students' recommendation for the teachers differ by considering the gender constructs, respectively. While a large proportion of the comments that we analyzed (n = 85,378) was classified to be neutral and predominantly interpreted to be positive in nature considering the sentiments (76.4%), and emotional valence (88.2%) expressed by the students. The results of our analysis shows that for the students' comments which contain some kind of positive or negative sentiment (23.6%) and emotional valence (11.8%); that females students recommended the teachers taking into account the sentiments (p = .000). While the males appear to be slightly borderline in terms of emotions (p = .056) and sentiment (p = .077). Also, the EPDM + ML model showed to be a good predictor and efficient method in determining what the students' recommendation scores for the teachers would be, going by the high and acceptable values of the precision (1.00), recall (1.00), specificity (1.00), accuracy (1.00), F1-score (1.00) and zero error-rate (0.00) which we validated using the k-fold cross-validation method, with 63.6% of optimal k-values observed. In theory, we note that not only does the proposed method (EPDM + ML) proves to be useful towards effective analysis of SET and its implications within the educational domain. But can be utilized to determine prominent factors that influences the students' evaluation and recommendation of the teachers, as well as helps provide solutions to the ever-increasingly need to advance and support the teaching-learning processes and/or students' learning experiences in a rapidly changing educational environment or ecosystem.

Predictive Model Using a Machine Learning Approach for Enhancing the Retention Rate of Students At-Risk

Student retention is a widely recognized challenge in the educational community to assist the institutes in the formation of appropriate and effective pedagogical interventions. This study intends to predict the students at-risk of low performances during an on-going course, those at-risk of graduating late than the tentative timeline and predicting the capacity of students in a campus. The data constitutes of demographics, learning, academic and educational related attributes which are suitable to deploy various machine learning algorithms for the prediction of at-risk students. For class balancing, Synthetic Minority Over Sampling Technique, is also applied to eliminate the imbalance in the academic award-gap performances and late/timely graduates. Results reveal the effectiveness of the deployed techniques with Long short-term Memory (LSTM) outperforming other models for early prediction of at-risk students. The main contribution of this work is a machine learning approach capable of enhancing the academic decision making related to student performance.

Predicting Academic Performance of Immigrant Students Using XGBoost Regressor

The education sector has been effectively dealing with the prediction of academic performance of the Immigrant students since the research associated with this domain proves beneficial enough for those countries where the ministry of education has to cater to such immigrants for altering and updating policies in order to elevate the overall education pedagogy for them. The present research begins with analyzing varied educational data mining and machine learning techniques that helps in assessing the data fetched form PISA. It’s elucidated that XGBoost stands out to be the ideal most machine learning technique for achieving the desired results. Subsequently, the parameters have been optimized using the hyper parameter tuning techniques and implemented on the XGBoost Regressor algorithm. Resultant there is low error rate and higher level of predictive ability using the machine learning algorithms which assures better predictions using the PISA data. The final results have been discussed along with the upcoming future research work.

How Does Learning Analytics Contribute to Prevent Students’ Dropout in Higher Education: A Systematic Literature Review

Retention and dropout of higher education students is a subject that must be analysed carefully. Learning analytics can be used to help prevent failure cases. The purpose of this paper is to analyse the scientific production in this area in higher education in journals indexed in Clarivate Analytics’ Web of Science and Elsevier’s Scopus. We use a bibliometric and systematic study to obtain deep knowledge of the referred scientific production. The information gathered allows us to perceive where, how, and in what ways learning analytics has been used in the latest years. By analysing studies performed all over the world, we identify what kinds of data and techniques are used to approach the subject. We propose a feature classification into several categories and subcategories, regarding student and external features. Student features can be seen as personal or academic data, while external factors include information about the university, environment, and support offered to the students. To approach the problems, authors successfully use data mining applied to the identified educational data. We also identify some other concerns, such as privacy issues, that need to be considered in the studies.

For Learning Analytics to Be Sustainable under GDPR—Consequences and Way Forward

Personalized learning is one of the main focuses in 21st-century education, and Learning Analytics (LA) has been recognized as a supportive tool for enhancing personalization. Meanwhile, the General Data Protection Regulations (GDPR), which concern the protection of personal data, came into effect in 2018. However, contemporary research lacks the essential knowledge of how and in which ways the presence of GDPR influence LA research and practices. Hence, this study intends to examine the requirements for sustaining LA under the light of GDPR. According to the study outcomes, the legal obligations for LA could be simplified to data anonymization with consequences of limitations to personalized interventions, one of the powers of LA. Explicit consent from the data subjects (students) prior to any data processing is mandatory under GDPR. The consent agreements must include the purpose, types of data, and how, when and where the data is processed. Moreover, transparency of the complete process of storing, retrieving, and analysing data as well as how the results are used should be explicitly documented in LA applications. The need for academic institutions to have specific regulations for supporting LA is emphasized. Regulations for sharing data with third parties is left as a further extension of this study.

Machine learning based approach to exam cheating detection

The COVID-19 pandemic has impelled the majority of schools and universities around the world to switch to remote teaching. One of the greatest challenges in online education is preserving the academic integrity of student assessments. The lack of direct supervision by instructors during final examinations poses a significant risk of academic misconduct. In this paper, we propose a new approach to detecting potential cases of cheating on the final exam using machine learning techniques. We treat the issue of identifying the potential cases of cheating as an outlier detection problem. We use students’ continuous assessment results to identify abnormal scores on the final exam. However, unlike a standard outlier detection task in machine learning, the student assessment data requires us to consider its sequential nature. We address this issue by applying recurrent neural networks together with anomaly detection algorithms. Numerical experiments on a range of datasets show that the proposed method achieves a remarkably high level of accuracy in detecting cases of cheating on the exam. We believe that the proposed method would be an effective tool for academics and administrators interested in preserving the academic integrity of course assessments.

A New Application in Biology Education: Development and Implementation of Arduino-Supported STEM Activities

Considering that generations that have grown up in the 21st-century have grown alongside technology, it is thought that integrating technology into lessons helps students learn the subject. This study aims to develop five STEM activities for the lesson of the human body systems by integrating the coding-based Arduino into STEM education. The activities were implemented to 6th-grade students for seven weeks and the effects on students' skills of establishing a cause-effect relationship. The study method was pre-test-post-test quasi-experimental design, and the cause-effect relationship scale and semi-structured view form were used as data collection tools. As a result of the study, a significant difference was found between the Arduino-supported STEM activities developed and the students' skills of establishing a cause-effect relationship. The students who received the Arduino-supported STEM education found the course to be entertaining and educational, and the future goals of these students were affected. In order to bring individuals who love their profession into the future, Arduino-supported STEM education should be applied and expanded in other branches and class levels.

Learning analytics in higher education: a preponderance of analytics but very little learning?

In a context where learning mediated by technology has gained prominence in higher education, learning analytics has become a powerful tool to collect and analyse data with the aim of improving students' learning. However, learning analytics is part of a young community and its developments deserve further exploration. Some critical stances claim that learning analytics tends to underplay the complexity of teaching-learning processes. By means of both a bibliometric and a content analysis, this paper examines the publication patterns on learning analytics in higher education and their main challenges. 385 papers that were published in WoScc and SciELO indexes between 2013 and 2019 were identified and analysed. Learning analytics is a vibrant and fast-developing community. However, it continues to face multiple and complex challenges, especially regarding students' learning and their implications. The paper concludes by distinguishing between a practice-based and management-oriented community of learning analytics and an academic-oriented community. Within both communities, though, it seems that the focus is more on analytics than on learning.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1186/s41239-021-00258-x.

Effects of COVID-19 Pandemic on University Students’ Learning

The risk of COVID-19 in higher education has affected all its degrees and forms of training. To assess the impact of the pandemic on the learning of university students, a new reference framework for educational data processing was proposed. The framework unifies the steps of analysis of COVID-19 effects on the higher education institutions in different countries and periods of the pandemic. It comprises both classical statistical methods and modern intelligent methods: machine learning, multi-criteria decision making and big data with symmetric and asymmetric information. The new framework has been tested to analyse a dataset collected from a university students’ survey, which was conducted during the second wave of COVID-19 at the end of 2020. The main tasks of this research are as follows: (1) evaluate the attitude and the readiness of students in regard to distance learning during the lockdown; (2) clarify the difficulties, the possible changes and the future expectations from distance learning in the next few months; (3) propose recommendations and measures for improving the higher education environment. After data analysis, the conclusions are drawn and recommendations are made for enhancement of the quality of distance learning of university students.

Research on Personalized Recommendation Methods for Online Video Learning Resources

It is not easy to find learning materials of interest quickly in the vast amount of online learning materials. The purpose of this study is to find students’ interests according to their learning behaviors in the network and to recommend related video learning materials. For the students who do not leave an evaluation record in the learning platform, the association rule algorithm in data mining is used to find out the videos that students are interested in and recommend them. For the students who have evaluation records in the platform, we use the collaborative filtering algorithm based on items in machine learning, and use the Pearson correlation coefficient method to find highly similar video materials, and then recommend the learning materials they are interested in. The two methods are used in different situations, and all students in the learning platform can get recommendation. Through the application, our methods can reduce the data search time, improve the stickiness of the platform, solve the problem of information overload, and meet the personalized needs of the learners.

Artificial Intelligence and Reflections from Educational Landscape: A Review of AI Studies in Half a Century

Artificial intelligence (AI) has penetrated every layer of our lives, and education is not immune to the effects of AI. In this regard, this study examines AI studies in education in half a century (1970–2020) through a systematic review approach and benefits from social network analysis and text-mining approaches. Accordingly, the research identifies three research clusters (1) artificial intelligence, (2) pedagogical, and (3) technological issues, and suggests five broad research themes which are (1) adaptive learning and personalization of education through AI-based practices, (2) deep learning and machine Learning algorithms for online learning processes, (3) Educational human-AI interaction, (4) educational use of AI-generated data, and (5) AI in higher education. The study also highlights that ethics in AI studies is an ignored research area.

DeepLMS: a deep learning predictive model for supporting online learning in the Covid-19 era

Coronavirus (Covid-19) pandemic has imposed a complete shut-down of face-to-face teaching to universities and schools, forcing a crash course for online learning plans and technology for students and faculty. In the midst of this unprecedented crisis, video conferencing platforms (e.g., Zoom, WebEx, MS Teams) and learning management systems (LMSs), like Moodle, Blackboard and Google Classroom, are being adopted and heavily used as online learning environments (OLEs). However, as such media solely provide the platform for e-interaction, effective methods that can be used to predict the learner’s behavior in the OLEs, which should be available as supportive tools to educators and metacognitive triggers to learners. Here we show, for the first time, that Deep Learning techniques can be used to handle LMS users’ interaction data and form a novel predictive model, namely DeepLMS, that can forecast the quality of interaction (QoI) with LMS. Using Long Short-Term Memory (LSTM) networks, DeepLMS results in average testing Root Mean Square Error (RMSE) \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<0.009$$\end{document}<0.009, and average correlation coefficient between ground truth and predicted QoI values \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$r\ge 0.97$$\end{document}r≥0.97\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(p<0.05)$$\end{document}(p<0.05), when tested on QoI data from one database pre- and two ones during-Covid-19 pandemic. DeepLMS personalized QoI forecasting scaffolds user’s online learning engagement and provides educators with an evaluation path, additionally to the content-related assessment, enriching the overall view on the learners’ motivation and participation in the learning process.

A Learning Analytics Theoretical Framework for STEM Education Virtual Reality Applications

While virtual reality has attracted educators’ interest by providing new opportunities to the learning process and assessment in different science, technology, engineering and mathematics (STEM) subjects, the results from previous studies indicate that there is still much work to be done when large data collection and analysis is considered. At the same time, learning analytics emerged with the promise to revolutionise the traditional practices by introducing new ways to systematically assess and improve the effectiveness of instruction. However, the collection of ‘big’ educational data is mostly associated with web-based platforms (i.e., learning management systems) as they offer direct access to students’ data with minimal effort. Thence, in the context of this work, we present a four-dimensional theoretical framework for virtual reality-supported instruction and propose a set of structural elements that can be utilised in conjunction with a learning analytics prototype system. The outcomes of this work are expected to support practitioners on how to maximise the potential of their interventions and provide further inspiration for the development of new ones.

Challenges and Future Directions of Big Data and Artificial Intelligence in Education

We discuss the new challenges and directions facing the use of big data and artificial intelligence (AI) in education research, policy-making, and industry. In recent years, applications of big data and AI in education have made significant headways. This highlights a novel trend in leading-edge educational research. The convenience and embeddedness of data collection within educational technologies, paired with computational techniques have made the analyses of big data a reality. We are moving beyond proof-of-concept demonstrations and applications of techniques, and are beginning to see substantial adoption in many areas of education. The key research trends in the domains of big data and AI are associated with assessment, individualized learning, and precision education. Model-driven data analytics approaches will grow quickly to guide the development, interpretation, and validation of the algorithms. However, conclusions from educational analytics should, of course, be applied with caution. At the education policy level, the government should be devoted to supporting lifelong learning, offering teacher education programs, and protecting personal data. With regard to the education industry, reciprocal and mutually beneficial relationships should be developed in order to enhance academia-industry collaboration. Furthermore, it is important to make sure that technologies are guided by relevant theoretical frameworks and are empirically tested. Lastly, in this paper we advocate an in-depth dialog between supporters of "cold" technology and "warm" humanity so that it can lead to greater understanding among teachers and students about how technology, and specifically, the big data explosion and AI revolution can bring new opportunities (and challenges) that can be best leveraged for pedagogical practices and learning.

Artificial Intelligence Visual Metaphors in E-Learning Interfaces for Learning Analytics

This work proposes an innovative visual tool for real-time continuous learners analytics. The purpose of the work is to improve the design, functionality, and usability of learning management systems to monitor user activity to allow educators to make informed decisions on e-learning design, usually limited to dashboards graphs, tables, and low-usability user logs. The standard visualisation is currently scarce, and often inadequate to inform educators about the design quality and students engagement on their learning objects. The same low usability can be found in learning analytics tools, which mostly focus on post-course analysis, demanding specific skills to be effectively used, e.g., for statistical analysis and database queries. We propose a tool for student analytics embedded in a Learning Management System, based on the innovative visual metaphor of interface morphing. Artificial intelligence provides in remote learning immediate feedback, crucial in a face-to-face setting, highlighting the students’ engagement in each single learning object. A visual metaphor is the representation of a person, group, learning object, or concept through a visual image that suggests a particular association or point of similarity. The basic idea is that elements of the application interface, e.g., learning objects’ icons and student avatars, can be modified in colour and dimension to reflect key performance indicators of learner’s activities. The goal is to provide high-affordance information on the student engagement and usage of learning objects, where aggregation functions on subsets of users allow a dynamic evaluation of cohorts with different granularity. The proposed visual metaphors (i.e., thermometer bar, dimensional morphing, and tag cloud morphing) have been implemented and experimented within academic-level courses. Experimental results have been evaluated with a comparative analysis of user logs and a subjective usability survey, which show that the tool obtains quantitative, measurable effectiveness and the qualitative appreciation of educators. Among metaphors, the highest success is obtained by Dimensional morphing and Tag cloud transformation.

Evaluation of higher education services: social media learning

Purpose

This research study aims to examine the quality of life and services of higher education through social media in fostering students' learning and environments.

Design/methodology/approach

Qualitative research methods were used in this study. In the study, as a data collection tool, a semistructured interview form was prepared and questions were asked. A study group was formed with a total of 80 participants in order to analyze the opinions of students studying in the University of Kyrenia.

Findings

According to the findings obtained in the study, it is understood that higher education students generally use Facebook or Instagram especially for following the trainings conducted abroad. It can be said that university students of higher education can follow many educational developments by being members of various educational institutions. In addition to this, university students can be thought to use this tool continuously and intensively in all project or assignment submissions thanks to social media. It is understood that especially university students can communicate with faculty members and access big data when necessary. Again, in this context, thanks to social media, it is understood from the opinions and thoughts received from the participants that they can easily prepare their lessons by making group interviews with each other or with the groups they have formed collectively. It is understood from the findings that the quality can be increased because various trainings can be provided in groups established through social media; thus, the fact that there is an opening to the world and the reason for the exchange of healthy ideas, information and science increases the quality.

Research limitations/implications

Research is limited to numbers of research participants from the University of Kyrenia, Faculty of Education in northern part of Cyprus. Social media is used as a medium of learning and development in the research.

Practical implications

It is a study that ensures that if social media services are used correctly in practice, this research will contribute to the continuous development of students.

Social implications

The research conducted contributes to how social media services can be organized through technology in higher education and measurement of learning can be enriched through social media.

Originality/value

With this research, it has a unique value due to the fact that the problems encountered in the use of social media services in universities reveal the problems and solutions. In this context, it shows the contribution of social media on the value added to the learning and learning environments and the benefit of services in higher education.

Advanced Learning Analytics in Academic Education

The integration of innovative data mining and decision-making techniques in the context of higher education is a bold initiative towards enhanced performance. Predictive and descriptive analytics add interesting insights for significant aspects the education. The purpose of this article is to summarize a novel approach for the adoption of artificial intelligence (AI) techniques towards forecasting of academic performance. The added value of applying AI techniques for advanced decision making in education is the realization that the scientific approach to standard problems in academia, like the enhancement of academic performance is feasible. For the purpose of this research the authors promote a research in Saudi Arabia. The vision of the Knowledge Society in the Kingdom of Saudi Arabia is a critical milestone towards digital transformation. The human capital and the integration of industry and academia has to be based on holistic approaches to skills and competencies management. One of the main objectives of an academic decision maker is to ensure that academic resources are adequately planned and that students are properly advised. To achieve such an objective, an extensive analysis of large volumes of data may be required. This research develops a decision support system (DSS) that is based on an artificial neural network (ANN) model that can be deployed for effective academic planning and advising. The system is based on evaluating academic metrics against academic performance for students. The model integrates inputs from relevant academic data sources into an autonomous ANN. A simulation of real data on an ANN is conducted to validate the system's accuracy. Moreover, an ANN is compared with different mathematical approaches. The system enables the quality assurance of planning, advising, and the monitoring of academic decisions. The overall contribution of this work is a novel approach to the deployment of Artificial Intelligent for advanced decision making in higher education. In future work this model is integrated with big data and analytics research for advanced visualizations