Advances in Web-Based Learning – ICWL 2019

A number of studies in personalized adaptive learning have focused on generating suitable learning paths based on user’s model, considering the current level of knowledge of the user, preferred learning styles and a model of the subject domain. These factors are sufficient in many e-learning applications, where users consume the learning content at their own pace. In other applications, such as within organized curricula there are other factors to be considered too. At the university, we deliver courses featuring project work and examination which the students have to deliver based on a schedule of deadlines. This time axis, therefore, presents a significant factor in recommending the most suitable learning objects at the given time of the term. To tackle this issue we have designed a courseware platform where time is one of the key factors determining the learner’s context. In this paper, we focus especially on modelling the time access using an ontology and we show some preliminary results that are implied by this approach.

The Conceptual Framework for e-Learning and Training (COFELET) constitutes a design standard for the enhancement of cyber security education by guiding the development of effective game-based approaches (e.g., serious games). The COFELET framework envisages cyber security serious games as highly organized and parameterized learning environments which monitor learner’s actions, evaluate their efforts and adapt to their needs. To this end, the COFELET framework employs well known cyber security standards (e.g., MITRE’s CAPEC, Lockheed Martin’s Cyber Kill Chain model or CKC) as a vehicle for organizing educational environments which model learners’ actions and strategies. In this light, the COFELET ontology is proposed aiming at providing a foundation for the development of a universal knowledge base for modeling such environments. The COFELET ontology provides an analytical description of the key elements of COFELET’s compliant serious games along with the appropriate classes and their properties. These elements include the cyber security domain elements that model the actions attackers perform to unleash cyber security attacks (i.e., the tasks) and the strategies they employ to achieve their malicious objectives (e.g., CAPEC’s attack patterns, the CKC model). The cyber security domain elements are associated with the educational elements (e.g., hints, utilized knowledge, exercised skills) that provide the means to infuse the didactics in the COFELET compliant approaches. A set of instances is presented to provide a better appreciation of the COFELET ontology rational, usage and usefulness. The proposed ontology is a cause and effect of the design and development process of a prototype COFELET compliant game.

The retrieval and composition of educational material are topics that attract many studies from the field of Information Retrieval and Artificial Intelligence. The Web is gradually gaining popularity among teachers and students as a source of learning resources. This transition is, however, facing skepticism from some scholars in the field of education. The main concern is about the quality and reliability of the teaching on the Web. While online educational repositories are explicitly built for educational purposes by competent teachers, web pages are designed and created for offering different services, not only education. In this study, we analyse if the Internet is a good source of teaching material compared to the currently available repositories in education. Using a collection of 50 queries related to educational topics, we compare how many useful learning resources a teacher can retrieve in Google and three popular learning object repositories. The results are very insightful and in favour of Google supported by the t-tests. For most of the queries, Google retrieves a larger number of useful web pages than the repositories ($$p < .01$$), and no queries resulted in zero useful items. Instead, the repositories struggle to find even one relevant material for many queries. This study is clear evidence that even though the repositories offer a richer description of the learning resources through metadata, it is time to undertake more research towards the retrieval of web pages for educational applications.

Given the importance of a well-constructed educational gaming interface and the costs involved in its development, it is important to identify the ergonomic requirements to be considered during the design process to ensure that the game be adapted to the characteristics of seniors. In a study of seniors aged 55 and older, we created and tested an educational game, “In Anticipation of Death”, in order to measure usability in the sense of determining the intuitive capacity of the game (user-friendliness). This paper presents the variables of the study, the way we adapted the game Solitaire for seniors and the results of an experiment done with 42 older players. The latter showed a high degree of satisfaction with game navigation, the display mode and gameplay equipment. Recommendations are presented to guide the development of online educational games for seniors.

Online learning communities are predicated on the assumption that social interaction among participants will lead to learning. Yet, research has shown that not all interactions result in learning and that there is a need to develop a more nuanced understanding of the nature of activities in online communities and their relationship with learning. We analyzed data from the Scratch™ online learning community, a platform designed to teach Computational Thinking (CT) through block-based activities, using the Differentiated Overt Learning Activities (DOLA) framework to assess learning. We found that users who engaged in constructive activities demonstrated higher learning, as illustrated by the complexity of their contributions, compared to users who were merely active on the platform. We compared users across two sub-communities within Scratch and found that participation and contributions across the two domains resulted in different learning outcomes, showcasing the effect of context on learning within online communities.

One advantage of small group collaboration in online courses is that it can enrich the students learning experience with regard to interactional and social dimensions. In this paper we apply a previously tested method of sequential analysis on group activity sequences. These activity sequences stem from an online course on computer mediated communication where the group tasks consisted of collaborative text production. Students activities in a group forum and a shared wiki were recorded and classified as coordination, monitoring, major/minor contribution. Analyses of clusters of similar sequences show, that there are characteristic patterns indicating productivity, fair work distribution, as well as satisfaction with the group work. Our findings are a step towards automatic diagnosis of collaboration problems in online group work to facilitate early interventions.

In learning situations that do not occur exclusively online, the analysis of multimodal evidence can help multiple stakeholders to better understand the learning process and the environment where it occurs. However, Multimodal Learning Analytics (MMLA) solutions are often not directly applicable outside the specific data gathering setup and conditions they were developed for. This paper focuses specifically on authentic situations where MMLA solutions are used by multiple stakeholders (e.g., teachers and researchers). In this paper, we propose an architecture to process multimodal evidence of learning taking into account the situation’s contextual information. Our adapter-based architecture supports the preparation, organisation, and fusion of multimodal evidence, and is designed to be reusable in different learning situations. Moreover, to structure and organise such contextual information, a data model is proposed. Finally, to evaluate the architecture and the data model, we apply them to four authentic learning situations where multimodal learning data was collected collaboratively by teachers and researchers.

Cheating in examinations destroys the principles of fairness and justice in evaluation. Cheating detection is of great practical significance. Traditional cheating detection methods have many disadvantages, such as difficult to detect covert equipment cheating, multi-source cheating, difficult to distinguish plagiarists from plagiarists, difficult to distinguish plagiarists from victims, or plagiarism from coincidences. In this paper, the concept of knowledge point mastery Index is introduced to measure students’ mastery of a certain knowledge point, and a test method of cheating based on improved cognitive diagnostic model is proposed. This method calculates the weight of each knowledge point in every examination question through linear regression and EM algorithm according to students’ historical learning behavior, and then calculates students’ mastering degree of knowledge point based on historical answers. Then calculate the mastering degree of knowledge point based on the examination results. Finally, we compare the mastering degree of knowledge point based on the examination results and the historical answers to detect students’ cheating situation. The experiments show that the precision and recall rate of this method are significantly higher than those of the method based on the false-same rate, the method based on the false-same rate and the right-same rate and the method based on the Person-Fit index.

Emotions and stress have considerable impact to wellbeing, growth and academic achievement. However, while devices with signal accuracy that is valid for clinical field research have become available, there is still a significant gap in knowledge about the relevance of such devices for digital learning. In this pilot study, a group of 17 university students of computing wore a moodmetrics smart ring device for one week. In addition, students kept short diaries about their study-related activities. Results from statistical analysis show a strong correlation between non-study and study-related stress level averages. Even when comparing the daily stress values, the correlation was strong and significant within the 95% confidence level. A total of 53 non-study and study average pairs were observed in the data. Our results reveal that stress of these students seemed not to vary between short-term study-events but it was found to be a more comprehensive issue. In the future, larger samples and more data are needed for more reliable research on individual study activities.

Writing in a foreign language is a struggle for learners and revising their writings is time consuming for teachers as well. For this reason, writing support systems have been widely proposed and one of its main functions is to automatically detect and revise errors in learners’ writings. However, the detection technologies are a work in progress and the effectiveness of error revision feedback is arguable. Meanwhile, numerous efforts have been made to enhance learners’ writing proficiency and reduce errors. Reading is considered as one of the important strategies. However, few studies have reported the linguistic knowledge that learners pay attention to and how they use the knowledge of web-based learning in their writings. In this paper, we performed a reading-to-write experiment in a web-based writing environment and analyzed reading materials and learners’ writings to explore how to observe learners’ awareness of syntactic structures in materials. Sentence patterns, proposed in our previous studies, have been introduced to categorize sentences, and the syntactic similarities between reading materials and learners’ writings have been calculated. The experimental results revealed that students showed higher comprehension of content but displayed poor attention towards syntactic structures in reading activities, if the structures were not significantly salient. It is assumed that the similarity measure is effective in observing students’ awareness of syntactic structures in materials, and further studies are needed to automatically observe the awareness.

The paper focuses on the perception of innovations from the perspective of students. By innovations, in this case, we understand information and communication technologies. The aim of the research project is to compare the perception of innovations from the view of Czech and Asian students. We proceeded from Rogers’ theory of diffusion of innovations (Rogers uses the words technology and innovation as synonyms), which defines five categories of adopters as classification of individual members of the social system, based on innovativeness. Diffusion is seen as a process, while innovations are passed on to other members of a particular social system during a certain time unit and through certain information channels. As a research tool, we used the Kankaarinta questionnaire. The research group consisted of Czech and Asian university students. Given the expansion and use of technology in Asian countries, we assumed that Asian students would be more inclined to innovate than the Czech ones. We worked with comparable groups (186 Czech students and 159 Asian students). Due to the fact that Czech students were from the Faculty of Education, female students prevailed in that group. Asian group of students was gender-balanced. In both groups, early majority prevailed, with a statistically significant difference between the two groups. Asian students seemed more innovative.

During the learning process students need time, space and interaction with peers and tutors. One way to fulfil these conditions is to apply e-learning tools, for example blogs. An important part of teacher training is reflection, and it needs attention. The learning process is influenced by several factors and one is the participation of the tutor. Previous studies have indicated that tutor participation in the learning process can influence student reflection, but not all the activities by the tutor are effective. However, it is important to examine more specifically how tutors can support student reflection through interacting in the blog. The aim of this study is to find out what characteristics of tutor blogging predict the level of reflection in blog posts by student teachers and induction year teachers. The sample consisted of 207 student teachers and induction year teachers, and 29 tutors from two Estonian universities. All students had the opportunity to communicate with each other and with their tutor in the blog. Characteristics of tutor blogging and the level of student reflection were identified in blog posts using a quantitative content analysis. A stepwise multiple regression analysis indicated that five significant characteristics of the content of blog posts by tutors and one characteristic of how active their blogging was predicted reflection in the blog on the part of the students. These include communication with students, actively writing in the blog, blog posts about success, reflective blog posts, posts about the tutors’ experience and posting questions in the blog.

Organizing groups is a critical process in implementing cooperative learning. The grouping strategy based on the degree of complementarity is a popular grouping strategy at present. However, the existing collaborative learning grouping strategy based on the degree of complementarity has disadvantages such as insufficient modeling accuracy for students’ ability and lack of rationality for the reasons of regrouping. This paper proposes a collaborative learning grouping strategy with early warning function based on the degree of complementary mastery of knowledge points. First, we take knowledge points as the minimum unit, and use linear regression and expectation maximization algorithm to accurately model each student’s mastery of each knowledge point. Then we use the inverse clustering algorithm based on knowledge points to classify students. Finally, we use LSTM neural network to predict the scores of each group in the next week, and early warning was given to the groups with significantly reduced predicted scores, and targeted suggestions were put forward for them according to the types of the warned groups. Experimental results show that the grouping strategy proposed in this paper can effectively improve the learning effect of students. The average precision and average recall of LSTM based group early warning were 30.1% and 27.6% higher than that based on linear regression, respectively.

This study investigated students’ collaborative inquiry learning with 5th grade (N = 58, Mage = 11.3 years) and 6th grade (N = 74, Mage = 12.4 years) participants. Students were divided into two- and four-person groups to study whether group size affects their learning with asymmetric collaborative simulations. They worked in online digital learning spaces using tablet computers and communicated face-to-face. The Collaborative Rate of Photosynthesis Lab from the Go-Lab portal (golabz.eu) was used to establish the condition of asymmetric collaboration, and tasks related to it were developed to assess students’ inquiry. To assess students’ collaboration, we used an adapted self-assessed collaboration skills instrument to measure three dimensions: contribution, interaction with others and team learning. The results show that collaboration did not statistically significantly differ depending on group size in the 5th grade, but did in the 6th grade, with 2-person groups reporting better collaboration. Regarding students’ inquiry, analysis of performance on the asymmetric collaborative tasks showed that there were no statistically significant differences between groups in either grade. However, the inquiry task scores were generally low (28% and 40% for 5th and 6th graders respectively), indicating that asymmetric collaborative inquiry is challenging for students in these grades.

Assessments are an important phase in the learning process. Information and communication technologies advancements determined the development of e-learning software tools which support e-learning activities, including e-assessment. The increasing usage of summative and formative e-assessments led to the challenge of managing items. The concept of an item bank is meant to support teachers and students alike, to provide an overview when taking assessments or creating exams. This article presents an on-going R&D project towards the design and deployment of an item bank for computer-based tests, and discusses its role within a service-oriented system architecture which enables the execution of activities related to e-assessment, ranging from item design and test creation, to the analysis of event logs generated by test-takers. The research methodology followed for the requirements elicitation and main findings are presented, and directions for future work are discussed.

Mastering self-regulation strategies would seem to be essential in distance and online university studies since the workload is much greater and students need to be more independent and responsible for their own learning. By self-regulation strategies, we mean the student’s mental activities aimed at creating favorable conditions for learning, including managing their concentration, motivation, time and tasks. With the aim of identifying self-regulation strategies used or not by students enrolled in distance and online learning, an initial study of 1,060 students was conducted. Various analyses were carried out. The results indicate that at least 29% of students have difficulty setting and adhering to a study schedule and trouble getting down to work. They also have difficulty focusing on their course and maintaining attention and concentration. They generally feel tense or under pressure during their studies and afraid or worried when performing learning activities in a course. When they need help, they find it difficult to turn to other students and communicate with them in order to support their learning process. In addition, three respondent profiles were identified. They stand out in relation to strategies for task management, concentration and asking for help: (1) living alone, single and under 25 years old, (2) living with a common-law partner and 25 to 34 years old and (3) living with a spouse and children, 35 to 44 years old.

The paper takes a critical look at the existing approaches and online tools that are supposed to enhance the sharing and reusing of innovative pedagogical scenarios among teachers, such as IMS LD, LAMS, LessonPlanner, etc. We argue that there is a need for new ways of sharing pedagogical scenarios that would promote innovative approaches to learning and teaching, would be easy to use and would scale up the sharing and reusing of innovative pedagogical scenarios among teachers. As a potential solution to this challenge, the paper introduces a framework and online tool called LePlanner. We summarise the results of the first evaluation study, which engaged 20 teachers in actively using the tool over a period of 4 months.

Students learning Health Informatics in the degree course of Medicine and Surgery of the University of L’Aquila (Italy) are required – to pass the exam – to submit solutions to assignments concerning the execution and interpretation of statistical analyses. The paper presents a tool for the automated grading of such a kind of solutions, where the statistical analyses are made up R commands and outputs, and the interpretations are short text answers. The tool performs a static analysis of the R commands with the respective output, and uses Natural Language Processing techniques for the short text answers. The paper summarises the solution regarding the R commands and output, and delves into the method and the results used for the automated classification of the short text answers. In particular, we show that through FastText sentence embeddings and a tuned Support Vector Machines classifier, we obtained an accuracy of 0.89, Cohen’s K = 0.76, and F1 score of 0.91 on a binary classification task (i.e. pass or fail). Other experiments including additional linguistically-motivated features, whose goal was to capture lexical differences between the students’ answer and the gold standard sentence, did not yield any significant improvement. The paper ends with a discussion of the findings and the next steps to be taken in our research.

Audience response systems (ARS) allow lecturers to run quizzes in large classes by handing to technology the time-consuming tasks of collecting and aggregating students’ answers. ARSs provide immediate feedback to lecturers and students alike. The first commercial ARSs emerged in the 1990s in form of clickers, i.e., transmitters equipped with a number of buttons, which impose restrictions on possible questions – most often, only multiple choice and numerical answers are possible.Starting from the early 2010s, the ubiquity of smartphones, laptops, and tablet computers paved the way for web-based ARSs which, while running on technology that provides more means for input and a graphical display, still have much in common with their precursors: Even though more types of questions besides multiple choice are supported, the full capability of web-based technology is still not fully exploited. Furthermore, they also do not adapt to a student’s needs and knowledge, and often restrict quizzes to two phases: Answering a question and viewing the results.This article first examines the current state of web-based ARSs: Question types found in current ARSs are identified and their support in a variety of ARSs is examined. Afterwards, three axes on which ARSs should advance in the future are introduced: Means of input, adaption to students, and support for multiple phases. Each axis is illustrated with concrete examples of quizzes.

Health literacy constitutes an important step towards patient empowerment and the Web is presently the biggest repository of medical information and, thus, the biggest medical resource to be used in the learning process. However, at present, web medical information is mainly accessed through generic search engines that do not take into account the user specific needs and starting knowledge and so they are not able to support learning activities tailored to the specific user requirements. This work presents “ULearn” a meta engine that supports access, understanding and learning on the Web in the medical domain based on specific user requirements and knowledge levels towards what we call “balanced learning”. Balanced learning allows users to perform learning activities based on specific user requirements (understanding, deepening, widening and exploring) towards his/her empowerment. We have designed and developed ULearn to suggest search keywords correlated to the different user requirements and we have carried out some preliminary experiments to evaluate the effectiveness of the provided information.

Search history visualization provides a medium to organize and quickly re-find information in searching. Scientific studies show that a good visualization of a user search history should not only present the explicit activities represented by search queries and answers but also depict the latent information exploration process in the searcher’s mind. In this paper, we propose the LogCanvasTag platform for search history visualization. In comparison to existing work, we focus more on helping searchers to re-construct the semantic relationship among their search activities. We segment a user’s search history into different sessions and use a knowledge graph to represent the searching process in each of the sessions. The knowledge graph consists of all queries and important related concepts as well as their relationships and the topics extracted from the search results of each query. Especially to help searchers not get lost in complicated history graph, we provide a function wherein sub-graphs can be extracted for each topic from the session graph for deeper insights. We also provide a collaborative perspective to support a group of users in sharing search activities and experience. Our experimental results indicate that searching experience of both independent users and collaborative searching groups benefit from this search history visualization. We present novel insights into the factors of graph-based search history visualization that help in quick information re-finding.

Open Educational Resources (OER) have been declared by UNESCO as a promising tool to address inclusion in educational settings. However, recent studies support the need to pay more attention to the accessibility and inclusion capacity of OER. In this context, this paper provide evidence about the benefits of adopting Universal Design for Learning and the Web Content Accessibility Guidelines to support the OER creation considering the variability of students in Vocational Education and Training (VET) programs. For doing so, it was created some OER using CO-CREARIA model and it was validated on VET setting in Colombia. Results evidence that the OER created support the achievement of high level of motivation and academic performance.

In consideration of the growing availability of mobile devices for students, web-based and shared annotations of learning materials are becoming more popular. Annotating learning material is a method to promote engagement, understanding, and independence for all learners in a shared environment. Open educational resources have the potential to add valuable information and close the gap between learning materials by automatically linking them. However, current popular web-based text annotation tools for learners, such as Hypothesis and Diigo, do not support learners in discovering new learning resources based on the context, metadata and the content of the annotated resource. In this article, we present SALMON, a collaborative web-based annotation system, which dynamically links and recommends learning resources based on annotations, content and metadata. It facilitates methods of semantic analysis in order to automatically extract relevant content from lecture materials in the form of PDF web documents. SALMON categorizes documents automatically in a way that finding similar resources becomes faster for the learners and they can discover communities for interesting topics.

Nowadays, personalization and adaptivity becomes more and more important in most systems. When it comes to education and learning, personalization can provide learners with better learning experiences by considering their needs and characteristics when presenting them with learning materials within courses in learning management systems. One way to provide students with more personal learning materials is to deliver personalized content from the web. However, due to information overload, finding relevant and personalized materials from the web remains a challenging task. This paper presents an adaptive recommender system called WEBLORS that aims at helping learners to overcome the information overload by providing them with additional personalized learning materials from the web to increase their learning and performance. This paper also presents the evaluation of WEBLORS based on its recommender system acceptance using data from 36 participants. The evaluation showed that overall, participants had a positive experience interacting with WEBLORS. They trusted the recommendations and found them helpful to improve learning and performance, and they agreed that they would like to use the system again.

To reduce the cognitive overhead of understanding and organizing online learning materials using topic models, especially for new learners not familiar with related domains, this paper proposes an efficient and effective approach for generating high-quality labels as better interpretation of topics discovered and typically visualized as a list of top terms. Compared with previous methods dependent on complicated post-processing processes or external resources, our phrase-based topic inference method can generate and narrow down label candidates more naturally and efficiently. The proposed approach is demonstrated and examined with real data in our corporate learning platform.

AI-based learning platforms (AILPs) are becoming an increasingly important component of knowledge-based societies. AILP development and exploitation is deeply rooted in the PEST environment and requires a thorough strategic plan of the social, and research impacts over a mid to long-term perspective. This paper presents the learning technology-profiled part of the strategic impact planning for an innovative intelligent learning platform and knowledge repository, referred to as ‘the Platform’, developed within a Horizon 2020 project. It also discusses selected results of the recent Delphi survey on the learning platform’s future and the methodological background of the strategy building process for an AILP. This four-round/real-time forward-looking activity combined policy and decision Delphi focused on the identification of factors influencing the future performance and educational impact of the Platform. The strategy building involved two stages. Stage 1 was devoted to establishing the boundary conditions for the Platform’s activity and user community building, while Stage 2 delivered the final action plan aimed at ensuring the Platform’s digital sustainability, financial viability, and social acceptance. Plausible exploitation scenarios were complemented by an impact model established with anticipatory networks. All this information was used in the final collaborative roadmapping, which situated the Platform exploitation in the real-life context.

Research suggests that an interdisciplinary approach, where students can gather and evaluate evidence, and make sense of information they receive, can enhance students’ learning and better model various processes and phenomena in the real world [1]. However, it might create challenges for teachers to design integrated learning scenarios in authentic outdoor settings. The general aim of the paper is to analyze the content of integrated learning scenarios supported with technologies (mobile devices, online applications, sensors and educational robotics) in outdoor settings created by teachers from 6 K-12 schools to understand the characteristics of outdoor learning scenarios, the type of knowledge and level of contextualization these scenarios anticipate. The content analysis of the integrated learning scenarios demonstrates that the teachers tend to design learning scenarios, which hardly embrace learning contexts and enable to support higher order knowledge building types.

The main aim of the research was to designate and describe phases of orientation learning process in a designed theoretical model, which would integrate blended learning in the studies of tourism management. Blended learning works with advanced technologies such as smart phones, applications, smart watches, or GPS devices. On the other hand, traditional approach is based on use of paper map and compass in the terrain practice. A study (n = 55) was carried out to evaluate the level of students’ spatial orientation skills, their self-estimation and to find out their experience with maps and modern IT devices in orientation and navigation. The results of the study were used to support the actual need for a blended learning model.

After leaving school, many students in Germany are not sure which discipline they should take, when they decided to study at a university. As support in this orientation phase, quite a lot of universities in Germany offer “Juniorstudy” programs. Here, students can get deeper insight into universities and into the topics they are interested in. Most of these offers are difficult for students to realize, since there are classroom sessions at the university. The University of Rostock can look back on a more than ten year long experience in offering a digital Juniorstudy program. Accompanied by advanced student mentors, they work with digital material to look deeper into their courses. By participating in presence phases, they can also get a feeling for our university. In this paper, insights from this program are sketched – both on the computer science and on the learning psychological level.

Mobile and ubiquitous learning models have been widely adopted in technology-enhanced learning (TEL) practices. Apart from potential benefits, these models introduce additional complexity in designing, monitoring and evaluating learning activities, as learning happens across different spaces. In recent years, literature on learning design (LD) and learning analytics (LA) has started to address these issues. This paper presents a systematic review on how LD and LA communities understand mobile and ubiquitous learning, as well as their respective contributions in these fields. The search included seven main academic databases in TEL, resulting in 1722 papers, from which 54 papers were included in the final analysis. Results point out the lack of common definitions for mobile and ubiquitous learning, raises research trends and (unexploited) synergies between LD and LA communities, and identifies areas that require further attention from these communities.

Skin cancer is one of the common and most fatal cancers. In most cases, the similarity between benign (healthy) and malignant (harmful) makes it so difficult to diagnose the lesion correctly. Moreover, there are two levels of categorization for skin lesions. In addition to benign vs malignant (basic level), each skin lesion can also be categorized as one of the sub-types of benign or malignant (subordinate level). In most medical schools the distinction between skin lesions is taught to students in just four sessions and at the basic level - i.e. benign vs malignant.In this research, we designed a learning system which can assist students in learning skin lesions effectively in only a few sessions through an application using skin lesion images. We also compared these two levels, basic level and subordinate level, and found that indeed learning skin lesions at the basic level is more effective at distinguishing harmful cases than at the subordinate level as it could be hypothesized.

E-assessment systems that provide automated feedback are a well-known part of modern education. Extensibility of e-assessment system with respect to domain-specific features is an import aspect of system design. This paper reports on two successful cases in which an existing e-assessment system was extended with domain-specific features.

Traditional classroom teaching is changing with modern technologies. A mobile-assisted classroom teaching is designed in the study and is proved an efficient teaching mode. The most popular mobile App WeChat in China is used as a course platform which could be easily tailored for any course exclusively. At the same time, several English learning mobile Apps are introduced to assist the English Reading class for college students, for example Xiao Huasheng App, Liuli Reading App, Ximalaya App. In the WeChat course platform, we integrate these mobile Apps at different times in classroom teaching and motivate students to participate in the course learning in class and after class. Mobile technologies plus linguistic knowledge and a well-planned teaching design are three key factors for a successful course teaching. Furthermore, this WeChat course platform is easy to build and makes a mobile-assisted language teaching accessible to every language teacher who may have a limited knowledge about technology.

MicroLearning (ML) was identified as one of the trends that can profile e-Learning now or in the near future. The author already conducted two experiments, where he tested newly created MicroLearning courses in comparison with “classic” e-Learning courses and got promising results [10]. The paper describes the creation of MicroLearning course “Creation of webpages”. The author focuses on design of newly created course taking into account subject matter and concepts of creation of individual ML units using among others step by step instructional design. Mentioned is the way ML learning units for this course were created, also making use of video tutorials enriched with interactions and quizzes. LMS Moodle was chosen for ML course creation with added support for interactive multimedia. This was extended with interactive code exercises “Try, Alter and Execute” (TAE) with pre-prepared HTML codes. The course aims to support more active engagement of students as they try code alterations within LMS and offer benefits of numerous quizzes.

This paper presents the concept of a mobile learning companion which uses sensor data to support self-regulated learning. Based on design considerations derived from previous work, a prototype of a mobile learning companion (Charlie) was developed as a student project at HTW Berlin. A first qualitative study with 4 students aimed at validating Charlie’s character as a friendly learning companion and its benefits and limitations for self-regulated learning. Future work will focus on improving Charlie to provide a positive learning support as a mobile learning companion.

The Fully Online Learning Community (FOLC) model is intended to operate within a co-created Digital Space to (a) reduce transactional distance, and (b) incorporate newcomers into an established learning community. An operationalized version of the General Technology Competency and Use (GTCU) framework was used with a convenience sample of Ontario Tech University students to determine readiness to work in the Digital Space. Initial findings confirm the results of an earlier study, which found positive correlations between self-reported scores and overall performance quality at the high and low ends of the continuum. We suspect that while the GTCU aids in the identification of a threshold-based approach to identifying readiness to work in the Digital Space, the instrument is insufficiently granular to identify a precise readiness point. This led the team to continue to develop a more sophisticated version of the GTCU, the current Digital Competency Profiler (DCP), and its companion, the Fully Online Learning Community Survey (FOLCS).

In this article we propose an automatic system that informs students of abnormal deviations of a virtual learning path that leads to the best grades in the course. Our motivation is based on the fact that by obtaining this information earlier in the semester, may provide students and educators an opportunity to resolve an eventual problem regarding the student’s current online actions towards the course. Our goal is therefore to prevent situations that have a significant probability to lead to a pour grade and, eventually, to failing. Our methodology can be applied to online courses that integrate the use of an online platform that stores user actions in a log file, and that has access to other student’s evaluations. The system is based on a data mining process on the log files and on a self-feedback machine learning algorithm that works paired with the Moodle LMS. Our results shown that it is possible to predict grade levels by only taking interaction patterns in consideration.