Abstract: With the fast development of online and mobile technologies, individualized or personalized learning is becoming increasingly important. Online courses especially Massive Open Online Courses (MOOCs) often have students from many countries, with different prior knowledge, expectations, and skills. They in particular could benefit from learning materials or learning systems that are customized to meet their needs. On this note, this paper suggests a personalized recommendation system for learners in online courses. The system recommends learning resources such as relevant courses to learners enrolled in formal online courses, by using a combination of association rules, content filtering, and collaborative filtering. Pilot testing of this system in the Shanghai Lifelong Learning Network, a platform for free and open education, indicates that this recommendation system can improve the utilization rate of educational resources and also promote the learning autonomy and efficiency of students.

Abstract: With the rapid advancement of information and communication technologies, e-learning has gained a considerable attention in recent years. Many researchers have attempted to develop various e-learning systems with personalized learning mechanisms for assisting learners so that they can learn more efficiently. In this context, curriculum sequencing is considered as an important concern for developing more efficient personalized e-learning systems. A more effective personalized e-learning recommender system should recommend a sequence of learning materials called learning path, in an appropriate order with a starting and ending point, rather than a sequence of unordered learning materials. Further the recommended sequence should also match the learner preferences for enhancing their learning capabilities. Moreover, the length of recommended sequence cannot be fixed for each learner because these learners differ from one another in their preferences such as knowledge levels, learning styles, emotions, etc. In this paper, we present an effective learning path recommendation system (LPRS) for e-learners through a variable length genetic algorithm (VLGA) by considering learners’ learning styles and knowledge levels. Experimental results are presented to demonstrate the effectiveness of the proposed LPRS in e-learning environment.

Abstract: The learning analytics community has matured significantly over the past few years as a middle space where technology and pedagogy combine to support learning experiences. To continue to grow and connect these perspectives, research needs to move beyond the level of basic support actions. This means exploring the use of data to prove richer forms of actions, such as personalized feedback, or hybrid approaches where instructors interpret the outputs of algorithms and select an appropriate course of action. This paper proposes the following three contributions to connect data extracted from the learning experience with such personalized student support actions: 1) a student–instructor centred conceptual model connecting a representation of the student information with a basic set of rules created by instructors to deploy Personalized Learning Support Actions (PLSAs); 2) a software architecture based on this model with six categories of functional blocks to deploy the PLSAs; and 3) a description of the implementation of this architecture as an open-source platform to promote the adoption and exploration of this area.

Abstract: In the current educational context, school models that leverage technology to personalize instruction have proliferated, as has student enrollment in, and funding of, such school models. However, even the best laid plans are subject to challenges in design and practice, particularly in the dynamic context of a school. In this collective case study, we identify challenges, disruptions, and contradictions as they occur across schools engaged in implementing technology-mediated personalized learning. Using cultural historical activity theory—a theoretical framework concerned with the individual and contextual factors influencing school change—to frame the analysis, we also examine some of the structural and contextual sources of these disruptions and contradictions. Our findings enable us to offer recommendations for policymakers and for practitioners engaged in implementing personalized learning models, as well as directions for future research on this topic.

Abstract: When used in classrooms, personalized learning software allows students to work at their own pace, while freeing up the teacher to spend more time working one-on-one with students. Yet such personalized classrooms also pose unique challenges for teachers, who are tasked with monitoring classes working on divergent activities, and prioritizing help-giving in the face of limited time. This paper reports on the co-design, implementation, and evaluation of a wearable classroom orchestration tool for K-12 teachers: mixed-reality smart glasses that augment teachers' realtime perceptions of their students' learning, metacognition, and behavior, while students work with personalized learning software. The main contributions are: (1) the first exploration of the use of smart glasses to support orchestration of personalized classrooms, yielding design findings that may inform future work on real-time orchestration tools; (2) Replay Enactments: a new prototyping method for real-time orchestration tools; and (3) an in-lab evaluation and classroom pilot using a prototype of teacher smart glasses (Lumilo), with early findings suggesting that Lumilo can direct teachers' time to students who may need it most.

Abstract: Personalized Learning (PL) has been widely promoted. Despite the increasing interest in PL, it is difficult to be implemented, because it can be complicated, costly, and even impossible without the help of powerful and advanced technology. This national survey study aimed at systematically investigating technology usage and needs of teachers in learner-centered schools in the U.S based on the conceptual framework of the Personalized Integrated Education System (PIES). PIES specifies four major functions: recordkeeping, planning, instruction, and assessment. A total of 308 learner-centered schools were identified that met at least three of the five criteria of PL: (1) personalized learning plans, (2) competency-based student progress, (3) criterion-referenced assessment, (4) problem- or project-based learning, and (5) multi-year mentoring. Survey responses of 245 teachers from 41 schools were analyzed. Results indicate that only 12% of teachers responded that they had a technology system that integrated the four major functions. Among the rest, 21% reported that they had no such systems. Technology was most widely used for planning and instruction but not for recordkeeping and assessment.

Abstract: Combined with the ubiquity and constant connectivity of mobile devices, and with innovative approaches such as Data-Driven Learning (DDL), Natural Language Processing Technologies (NLPTs) as Open Educational Resources (OERs) could become a powerful tool for language learning as they promote individual and personalized learning. Using a questionnaire that was answered by language teachers (n = 230) in Spain and the UK, this research explores the extent to which OER NLPTs are currently known and used in adult foreign language learning. Our results suggest that teachers’ familiarity and use of OER NLPTs are very low. Although online dictionaries, collocation dictionaries and spell checkers are widely known, NLPTs appear to be generally underused in foreign language teaching. It was found that teachers prefer computer-based environments over mobile devices such as smartphones and tablets and that teachers’ qualification determines their familiarity with a wider range of OER NLPTs. This research offers...

Abstract: Current initiatives to personalize learning in schools, while seen as a contemporary reform, actually continue a 200+ year struggle to provide scalable, mass, public education that also addresses the variable needs of individual learners. Indeed, some of the rhetoric and approaches reformers are touting today sound very familiar in this historical context. What, if anything, is different this time? In this paper I provide a brief overview of historical efforts to create a scaled system of education for all children that also acknowledged individual learner variability. Through this overview I seek patterns and insights to inform and guide contemporary efforts in personalized learning.

Abstract: Adaptive learning systems stand apart from traditional learning systems by offering a personalized learning experience to students according to their different knowledge states. Adaptive systems collect and analyse students' behavior data, update learner profiles, then accordingly provide timely individualized feedback to each student. Such interactions between the learning system and students can improve the engagement of students and the efficiency of learning. This paper evaluates the effectiveness of an adaptive learning system, “Yixue Squirrel AI” (or Yixue), on English and math learning in middle school. The effectiveness of the Yixue's math and English learning systems is respectively compared against (1) traditional classroom math instruction conducted by expert human teachers and (2) BOXFiSH, another adaptive learning platform for English language learning. Results suggest that students achieved better performance using Yixue adaptive learning system than both traditional classroom instruction by expert teachers and another adaptive learning platform.

Abstract: This Innovate Practice full paper presents a cloud-based personalized learning lab platform. Personalized learning is gaining popularity in online computer science education due to its characteristics of pacing the learning progress and adapting the instructional approach to each individual learner from a diverse background. Among various instructional methods in computer science education, hands-on labs have unique requirements of understanding learner’s behavior and assessing learner’s performance for personalization. However, it is rarely addressed in existing research. In this paper, we propose a personalized learning platform called ThoTh Lab specifically designed for computer science hands-on labs in a cloud environment. ThoTh Lab can identify the learning style from student activities and adapt learning material accordingly. With the awareness of student learning styles, instructors are able to use techniques more suitable for the specific student, and hence, improve the speed and quality of the learning process. With that in mind, ThoTh Lab also provides student performance prediction, which allows the instructors to change the learning progress and take other measurements to help the students timely. For example, instructors may provide more detailed instructions to help slow starters, while assigning more challenging labs to those quick learners in the same class. To evaluate ThoTh Lab, we conducted an experiment and collected data from an upper-division cybersecurity class for undergraduate students at Arizona State University in the US. The results show that ThoTh Lab can identify learning style with reasonable accuracy. By leveraging the personalized lab platform for a senior level cybersecurity course, our lab-use study also shows that the presented solution improves students engagement with better understanding of lab assignments, spending more effort on hands-on projects, and thus greatly enhancing learning outcomes.

Abstract: We report an experimental implementation of adaptive learning functionality in a self-paced Microsoft MOOC (massive open online course) on edX. In a personalized adaptive system, the learner's progress toward clearly defined goals is continually assessed, the assessment occurs when a student is ready to demonstrate competency, and supporting materials are tailored to the needs of each learner. Despite the promise of adaptive personalized learning, there is a lack of evidence-based instructional design, transparency in many of the models and algorithms used to provide adaptive technology or a framework for rapid experimentation with different models. ALOSI (Adaptive Learning Open Source Initiative) provides open source adaptive learning technology and a common framework to measure learning gains and learner behavior. This study explored the effects of two different strategies for adaptive learning and assessment: Learners were randomly assigned to three groups. In the first adaptive group ALOSI prioritized a strategy of remediation - serving learners items on topics with the least evidence of mastery; in the second adaptive group ALOSI prioritized a strategy of continuity - that is learners would be more likely served items on similar topic in a sequence until mastery is demonstrated. The control group followed the pathways of the course as set out by the instructional designer, with no adaptive algorithms. We found that the implemented adaptivity in assessment, with emphasis on remediation is associated with a substantial increase in learning gains, while producing no big effect on the drop-out. Further research is needed to confirm these findings and explore additional possible effects and implications to course design.

Abstract: Intelligent tutoring systems (ITS) have been a topic of great interest for about five decades. Over the years, ITS research has leveraged AI advancements, and has also helped push the boundaries of AI capabilities with grounded usage scenarios. Using ITSs along with classroom instruction to augment traditional teaching is a canonical example of how humans and machines can work together to solve problems that are otherwise overwhelming and non-scalable individually. The experiences of personalized learning created by (1) seamless orchestration of human decision-making at few critical points with (2) scalability of cognitive capabilities using AI systems can drive increased student engagement leading to improved learning outcomes. By considering two particular use-cases of early childhood learning and higher education, we discuss the challenges involved in designing these complex human-centric systems. These systems integrate technologies involving interactivity, dialog, automated question generation, and learning analytics.

Abstract: Artificial Intelligence (AI) thinking is a framework beyond procedural thinking and based on cognitive and adaptation to automatically learn deep and wide rules and semantics from experiments. This paper presents Cloud-eLab, an open and interactive cloudbased learning platform for AI Thinking, aiming to inspire i) Deep and Wide learning, ii) Cognitive and Adaptation learning concepts for education. It has been successfully used in various machine learning courses in practice, and has the expandability to support more AI modules. In this paper, we describe the block diagram of the proposed AI Thinking education platform, and provide two education application scenarios for unfolding Deep and Wide learning as well as Cognitive and Adaptation learning concepts. Cloud-eLab education platform will deliver personalized content for each student with flexibility to repeat the experiments at their own pace which allow the learner to be in control of the whole learning process.

Abstract: Towards the last decade, digital education has become a burning issue in the related scientific literature and involves the production of Intelligent Tutoring Systems (ITSs). ITSs are adaptive educational applications that enrich the tutoring and learning processes with "intelligence" by divulging the abilities and weaknesses of each student, in order to provide him/her with a personalized learning experience. A crucial factor of adaptive learning systems is testing, and indeed adaptive testing. It is a challenge to create an adaptive test that includes the most suitable exercise/question/activity of a large pool of test items for a particular learner taking into consideration her/ his particular learning characteristics, needs and ability. In this paper, a framework for creating automated adaptive tests using multiple-criteria decision analysis and the weighted sum model is presented. The presented framework takes into consideration multiple students' criteria along with the types of exercises and the desirable learning objective. The aforementioned assessment framework was incorporated in two adaptive e-learning systems and was fully evaluated. The evaluation results are very encouraging.

Abstract: Students within this study followed the ICSDR (Identify, Conceptualize/Connect, Storyboard, Develop, Review/Reflect /Revise) development model to create digital video, as a personalized and active learning assignment. The participants, graduate students in education, indicated that following the ICSDR framework for student-authored video guided their video creation process, resulting in focus for their ideas, and increasing motivation to learn more about their content. Finally, the participants indicated that creating a digital video was an authentic and personalized learning experience that fostered personal choice and voice and peer collaboration. Evidence from the qualitative study supports students following a development framework for video creation.

Abstract: A big challenge in educational resources construction is the intelligent and personalized resource recommendation for learners. This paper proposes a semantic recommendation framework of educational resources based on semantic web and pedagogics. In this framework, a domain ontology is constructed to describe the knowledge structure of the domain. All the resources and user portfolio are described with ontology technology and resource description framework to support semantic inference. Based on the semantic resource organization, we made a set of reasoning rules based on pedagogics. These rules are made from the synthesis of the type of the knowledge, the internal structure of knowledge and learner’s learning performance. A case study was implemented on the course “theory and practice of database”. In this case, learners are recommended different learning materials according to the different knowledge structure and different learning performance. Three typical learning modes are proposed to describe the personalized learning experience. This framework can be used as a guide for teachers and resource designers.

Abstract: This Research Full Paper implements a framework that harness sources of programming learning analytics on three computer programming courses a Higher Education Institution. The platform, called PredictCS, automatically detects lower-performing or “at-risk” students in programming courses and automatically and adaptively sends them feedback. This system has been progressively adopted at the classroom level to improve personalized learning. A visual analytics dashboard is developed and accessible to Faculty. This contains information about the models deployed and insights extracted from student’s data. By leveraging historical student data we built predictive models using student characteristics, prior academic history, logged interactions between students and online resources, and students’ progress in programming laboratory work. Predictions were generated every week during the semester’s classes. In addition, during the second half of the semester, students who opted-in received pseudo real-time personalised feedback. Notifications were personalised based on students’ predicted performance on the course and included a programming suggestion from a top-student in the class if any programs submitted had failed to meet the specified criteria. As a result, this helped students who corrected their programs to learn more and reduced the gap between lower and higher-performing students.

Abstract: Background: Positive results can be obtained through game-based learning, but children with physical disabilities have fewer opportunities to participate in enjoyable physical activity. Because intelligent serious games can provide personalized learning opportunities, motivate the learner, teach 21st-century skills, and provide an environment for authentic and relevant assessment, they may be used to help children and adolescents with different kinds of learning disabilities to develop social and cognitive competences. Objective: The aim of the study was to produce and evaluate a suite of intelligent serious games based on accessible learning objectives for improving key skills, personal development, and work sustainability among children with learning difficulties. Methods: We conducted this research between 2016 and 2018, with pupils aged 11 to 12 years with learning disabilities who were integrated into the mainstream educational system. We used a 4-step methodology to develop learner creativity and social competences: (1) needs analysis, (2) development of learning content, (3) development of intelligent serious games, and (4) a usability evaluation focusing on the research questions and hypothesis. This was based on an initial teachers’ evaluation, using a survey, of students using 2 of the games, where the main goal was to determine user motivation and initiative and to improve the games and the evaluation process. The initial evaluation was followed by a pilot evaluation, which was performed for all proposed games, in all partner countries. Results: In an initial evaluation with 51 participants from Slovenia consisting of a pretest, followed by intelligent serious game intervention and concluding with a posttest, we observed statistically significant improvement in social and cognitive competences measured by tests. Based on these findings and observations, we improved the games and evaluation process. In the pilot test, conducted in all participating countries on a sample of 93 participants, the mean score on the teachers’ observation form on the pretest (before students began using the intelligent serious games) was 3.9. In the posttest, after students had used intelligent serious games, the mean score was 4.1. Conclusions: We focused on developing and evaluating intelligent serious games for persons with learning disabilities, particularly for students with disabilities who are integrated into the mainstream educational system. Such games provide an opportunity for personalized learning and should be tailored to ensure that every learner can achieve the highest standard possible. However, we recommend that the games be adapted based on the students’ needs and capabilities and a specially developed curriculum. The collected feedback showed that (1) children with learning disabilities need appropriately developed intelligent serious games, and (2) intelligent serious games, and the pertaining didactic methodology, should be based on an interoperable curriculum, so that teachers and trainers can use them. The student survey confirmed improvements in all aspects.

Abstract: Purpose Change is the operative word in higher education; as roles shift, classrooms are reinvented, and content becomes increasingly more accessible. At the core of these changes is the pervasiveness of learning technology. This papers aims to propose a model for the selection and adoption of emerging learning technologies to enhance learning within the context of higher education. Design/methodology/approach Higher education institutions are resorting to the deployment of learning technologies to address the demands of the twenty-first century learners and to ascertain their competitiveness. This paper draws from the literature to provide a model, composed of five key characteristics of learning, to support the selection and adoption of emerging learning technologies. Findings The model posits that the attainment of each of these five characteristics, personalised, ubiquitous, collaborative, lifelong and authentic needs to be supported by corresponding technologies: adaptive learning technologies, artificial intelligence, mobile technology, social technology, massive open online courses, virtual and augmented reality, gamification and the Internet of Things. Originality/value Higher education is progressively being displaced from the traditional classroom, and as it progresses towards online settings, it requires the support of technology to facilitate that transference. In examining the potential of future learning technologies, this paper contributes to a growing body of research that focuses on the benefits of technology within higher education and assists educators in the selection and adoption of the most relevant technologies.

Abstract: The main objective of e-learning systems is to improve the student learning performance and satisfaction. This can be achieved by providing a personalized learning experience that identifies and satisfies the individual learner’s requirements and abilities. The performance of the e-learning systems can be significantly improved by exploiting dynamic self-learning capabilities that rapidly adapts to prior user interactions within the system and the continuous changes in the environment. In this paper, a dynamic multi-agent system using particle swarm optimization for the e-learning systems is proposed. The system incorporates five agents that take into consideration the variations in the capabilities among the different users. First, the project clustering agent is used to cluster a set of learning resources/projects into similar groups. Second, the student clustering agent (SCA) groups students according to their preferences and abilities. Third, the student-project matching agent is used to map each learner’s group to a suitable project or particular learning resources according to specific design criteria. Fourth, the student-student matching agent is designed to perform the efficient mapping between different students. Finally, the dynamic SCA (DSCA) is employed to continuously track and analyze the student’s behavior within the system such as changes in knowledge and skill levels. Consequently, the DSCA adapts the e-learning environments to accommodate these variations. Experimental results demonstrate the effectiveness of the proposed system in providing near-optimal solutions in considerably less computational time.

Abstract: Using online learning platforms for teaching and learning is common in this generation and development is driving innovation. The advances of information technology have significantly changed ways of teaching and learning in higher education. Online learning platforms take many forms depending on a particular application. In addition to Blackboard, Moodle is one of the most popular online learning platforms nowadays worldwide. Moodle is a learning platform designed to provide educators, administrators and learners with a single robust, secure and integrated system to create personalized learning environments. In addition, the acceptance of the students to the online learning platform will affect the higher education information and the construction of modernization of education in a certain extent. A number of studies have indicated that the successful pedagogical use of technology depends on students’ attitudes and acceptance towards technology. Therefore, the prediction of students’ attitude and acceptance towards online learning platform is crucial for the teaching and learning quality in education. This study is to investigate the acceptance of using online learning platform, i.e. Moodle by using the augmented version of TAM model (A-TAM) to investigate their behavioral intention and use behavior of Moodle for their learning, as Moodle is one of the most common online learning platform in Hong Kong and there are a significant proportion of Institutes adopting Moodle in Hong Kong higher education. In other words, this study investigates how perceived usefulness, perceived ease of use, attitude towards behavior and subjective norm affect behavioral intention so as to actual behavior of using Moodle in Hong Kong higher education.

Abstract: This is the first occasion Smart Learning track is included in TEEM Conference. Our current digital society faces challenges as preparing our students for an uncertain and changing environment. Learning systems based on technology, adapted to the different learning needs, learning styles and learning rhythms, and personalized for our learners, could be a solution to this problem. It is what is called Smart Learning. The contributions to this track cover aspects such as the orchestration of Smart Learning Environments with the support of learning analytics and the Internet of Things, the estimation of the difficulty of learning activities, the use of decision support tools to make systematic searches, or one experience of gamification. These works show the diversity of the discipline and the extent of the research that remains to be done.

Abstract: Adaptive Learning (AL) is a personalized learning technology. It can customize learning based on pre-determined knowledge state on a particular subject or topic. This assessment driven approach not only allows students to have their own learning path with individual learning nodes or steps, but also provides various formative and summative assessments the students' learning performance. With the appropriate mapping between course learning outcomes and program outcomes, the program outcomes can be assessed through the assessment results of AL in selected courses. Colorado Technical University (CTU) has been using AL technology in their Web-based Learning Management System (LMS) since October of 2012. CTU's AL approach is both assessment driven and facilitator/faculty driven. In this paper, we will share our experience and findings on using AL in Online Computer Science (CS) and Information Technology (IT) courses to enhance student learning and assess the program outcomes for continuous improvement and programmatic accreditation.

Abstract: The field of personalized learning currently lacks clearly specified models with research evidence, or even clarity on which practices are essential. A RAND researcher draws on theory, basic principles from learning science, and the limited research that does exist to offer strategic guidance for the designers of such programs to consider while the evidence base is catching up.

Abstract: Lifecycle management questions of educational program and resources in the smart learning environment are considered to provide a convergent process of specialist’s continuous training. The main results of the research are: (a) analysis of the training specialist’s problems, (b) smart environment synthesis to support convergent education processes, (c) lifecycles formalization of the educational environment components, (d) synchronization of lifecycle models, (e) personalized learning paths synthesis, (f) support for the updating of educational resources according to the standards and employer’s requirements. The article describes the results of the development of educational environment components. Functional lifecycle models and a cloud storage model for educational content with ubiquitous access support through the Web portal are proposed. The intellectual management system for the learning process in the information educational environment based on the component’s lifecycle model is implemented. The intellectual platform includes content management system Alfresco, learning management system Moodle, training content presentation Web system, knowledge assessment system, learning activity management system, standards and employer’s requirements analysis system. The system provides support for lifecycle stages of personalized educational programs, electronic educational resources, and specialist training levels.

Abstract: Research has demonstrated that spatial visualization skills are crucial for success in Science, technology, engineering, and mathematics (STEM) disciplines. With an increasing number of students entering STEM disciplines, the question of how to effectively train students» spatial visualization skills has become very important. While a scalable existing solution is to implement online workshops for students, the problem of how to motivate students to participate in these online workshops remains unsolved. In this study, we studied gamification as a way to motivate first year engineering students to take part in an online workshop designed to train their spatial visualization skills. Our game contains eight modules, each designed to train a different component of spatial visualization. The game records players» in-game behavior with high granularity, which allows us to provide automated, scalable feedback on players» problem-solving strategies. Ten students with different levels of spatial ability played our game and expressed a strong interest in using the game to train their spatial visualization skills in the future. In addition, our analysis of players» in-game behaviors shows the potential benefits of implementing adaptive and personalized learning guidance.