Creative learning has enriched on-site museum education by fostering engagement, exploration, and active participation. However, the structured integration of creative learning processes into digital museum education remains relatively underexplored. Although Generative Artificial Intelligence (GenAI) presents considerable potential to support creative learning, its comprehensive application across all stages in non-formal learning environments, such as museums, remains limited. To investigate this potential, we conducted a formative study employing a previously developed prototype with seven learners and four senior experts to identify learners’ specific needs and challenges. Informed by the findings, we designed and developed MuseForge, a platform integrating GenAI with the five stages of the iterative creative development path to support a personalized and dynamic creative learning experience. A between-subjects study with 32 participants demonstrated that learners using MuseForge achieved significantly higher learning motivation, engagement, and learning gain in creative self-efficacy, highlighting its effectiveness in supporting creative learning in digital museum environments.

Virtual Reality (VR) enriches learning and instruction, while background music (BGM) is widely employed to modulate attention and cognition. Understanding how BGM influences learning in VR is essential for optimizing VR learning environments and has the potential to improve educational outcomes, yet this area remains largely unexplored. This study collected fifty-two participants’ self-reports, electroencephalogram signals, eye movements, heart rates, and interview responses to explore their attention and cognition during studying virtual heritage sites with and without BGM, while considering individual traits as influential factors. Results showed that with BGM, participants reported higher levels of engagement and demonstrated longer fixation duration on heritage sites’ image regions, than without BGM. Moreover, participants’ self-reported familiarity with the cultural heritage site and BGM listening frequency moderated the effect of BGM on attention and cognition in VR. This study offers implications for incorporating BGM for learning in VR, and designing personalized VR learning environments.

This study explores the integration of Music Information Retrieval (MIR) techniques into learning analytics to analyze students' background music choices during virtual reality (VR) content creation. Through a mixed-methods approach involving interviews with 16 students and the analysis of background music in 98 VR stories, we examined students' music selection strategies and the emotional and stylistic characteristics of their chosen audio. Findings reveal a preference for calm, low-arousal music aligning with cultural heritage themes. The study demonstrates the potential of MIR in educational contexts, contributing to the emerging field of multimodal learning analytics.

This paper presents the design and implementation of a student-facing Learning Analytics Dashboard (LAD) to support collaborative Virtual Reality (VR) content creation in educational settings. The LAD includes a shared task checklist, class progress statistics, and visualizations of student contributions to promote self-regulated learning (SRL) strategies and group awareness. The effectiveness of the LAD was evaluated through a quasi-experiment in a high school VR creation program with a total of 111 students. Results revealed high adoption rates of the LAD and significant differences in editing behaviours between the control and experimental groups. This study demonstrates the LAD's potentials in fostering iterative improvements and enhancing collaboration in collaborative maker activities.

This systematic literature review explores the application of multimodal learning analysis (MMLA), with physiological signals collected through wearable devices as the primary data source, in immersive virtual reality (IVR) learning environments. By examining 78 peer-reviewed articles published over the past nine years (2016–2024), the paper addresses two core research questions in IVR learning environments: 1) What are the main multimodal learning indicators? 2) What are the ethical considerations associated with multimodal learning analysis? The findings indicate that cognitive indicators are dominant, while studies on emotional and affective learning indicators remain scarce. Real-time monitoring of cognitive load and dynamic task adjustment mechanisms have yet to be fully implemented, suggesting future research on the design of adaptive learning tasks. Additionally, the review calls for improvements in both technological and ethical frameworks to address issues related to privacy, transparency, and fairness. By reviewing and summarizing current research advancements, this paper offers valuable insights into future research and practice of MMLA in IVR learning environments.

Collaborative Problem Solving (CPS) has emerged as a key competence for the 21st century. In support of this, valid assessments of CPS skills have become critical. However, limited research has designed and developed CPS assessments for young students. Based on multimodal learning analytics, we aim to develop and validate a game-based assessment of CPS for primary school students. In this study, evidence centered design approach was used to design and develop the game-based CPS assessment. Specifically, we designed and developed a mobile multiplayer online 3D role-playing game on CPS and a coding scheme for coding students’ gameplay data (i.e., game logs and voice chat) based on the ATC21S CPS framework. A total of 32 primary 5 students participated in this study to play the game in a group of four and complete a questionnaire of CPS skills. The gameplay data were coded based on our coding scheme. Correlation analysis between the coded results and the CPS questionnaire data supported the criterion validity of our game-based assessment measure. Additionally, the results of expert interview facilitated our understanding of assessment design and data use. This study will make methodological and practical contributions to the integration of MMLA into game-based CPS assessments.

With the rise of online learning platforms, the need for effective learning analytics (LA) has become critical for teachers. However, the development of traditional LA dashboards often requires technical expertise and a certain level of data literacy, preventing many teachers from integrating LA dashboards effectively and flexibly into their teaching practice. This paper explores the development of a self-service teacher-facing learning analytics dashboard powered by large language models (LLMs), for improving teaching practices. By leveraging LLMs, the self-service system aims to simplify the implementation of data queries and visualizations, allowing teachers to create personalized LA dashboards using natural languages. This study also investigates the capabilities of LLMs in generating charts for LA dashboards and evaluates the effectiveness of the self-service system through usability tests with 15 teachers. Preliminary findings suggest that LLMs demonstrate high capabilities in generating charts for LA dashboards, and the LLM-powered self-service system can effectively address participating teachers’ pedagogical needs for LA. This research contributes to the ongoing research on the intersection of LLMs and education, emphasizing the potential of self-service systems to empower teachers in daily teaching practices.

This paper reports on the preliminary findings of designing a learning analytical tool to assess and facilitate online collaborative learning in discussion forums. The analytics tool developed is grounded on collaboration theories to unravel students’ online collaboration, encompassing three features: (a) participation and build-on posts, (b) lexical keywords for domain understanding, and (c) communicative acts for dialogic interactions. The tool was designed to analyze students’ online discussions for two classes in a postgraduate educational studies course. Findings unravel student online collaboration behaviour, including (a) high engagement with online posts exceeding course requirements, (b) frequency/ links among keywords used (not used) indicate students’ knowledge networks and gaps, and (3) dialogic communication acts commonly employed while higher-level acts (e.g., coordination) not yet adopted. Findings also indicate student groups using a higher frequency of communication acts (more dialogic in discussion) also obtained higher grades, providing some validation. Implications suggest how the tools can be used to assess social-semantic-dialogic online collaborative behaviour and how instructors can use analytics information to adapt their instructional strategies to address students’ knowledge gaps and provide feedback. Students can also use the analytics information to regulate and improve online discussions.

Well-designed digital games can serve as the vehicle to assess and support young people’ collaborative problem solving (CPS) skills. However, there is limited research leveraging multimodal learning analytics (MmLA) to explore students’ game-based CPS processes and outcomes. Inspired by MmLA methods and approaches, this preliminary study aims to examine students’ demonstration of CPS skills through collecting and analyzing a dataset of combined game logs and verbal discourses from two groups of primary school students with contrasting performances. Based on the Assessment and Teaching of 21st Century Skills CPS framework, we iteratively coded the dataset. Results of descriptive statistics showed that the successful group exhibited cognitive skills more frequently while the unsuccessful group showcased social skills more. Results of epistemic network analysis (ENA) revealed that, in both social and cognitive dimensions, the successful group demonstrated more diverse and stronger associations among various subskills, whereas there were fewer associations in the unsuccessful group. Implications are drawn for MmLA and CPS research and teaching practices of CPS skills.

Many students enjoy listening to background music (BGM) when they read, but it is challenging to measure their meta-cognitive states (e.g., understanding of the passage, engagement in reading). Eye movements, as an approach in multimodal learning analytics (MmLA), can offer continuous fine-grained data that reflect learners’ cognitive processes. This study explored the potential of utilizing eye movement measures to predict learners’ meta-cognition during reading with BGM. Results showed that learners’ eye movement measures integrated with the characteristics of the BGM, learner traits, and text complexity could predict their meta-cognitive states in reading. Findings can advance our understanding of human meta-cognition in multi-channel learning settings and provide insights for personalized BGM recommendations to enhance reading experiences.

In this paper, we present an empirical study on collaborative virtual reality (VR) maker activities. A platform called CLEVR was designed to facilitate real-time VR co-creation with group awareness features. We develop an assessment framework for collaborative quality using log-based learning analytics (LA). By conducting time-series analysis on five pairs of participants, we demonstrate the potential of our platform and methodology for the development of LA tools to understand and support collaborative learning.

Widely accessible online courses provide a feasible platform for teachers' continuous online professional learning. The learning analytics dashboard (LAD) provides fine-grained and actionable feedback that supports learners’ self-regulated learning. However, previous studies on LAD design and evaluation predominantly focused on student-facing LADs, with scarce attention on LADs designed for teacher-learners. This study introduces the LAD in an online learning platform for college teachers and conducts a preliminary evaluation with 18 participants. Results show their largely positive ratings on five criteria (e.g., perceived usefulness, ease of use, and behavioral changes) and offer feedback for further refinements of the LAD. This study will improve our understanding of LA-enabled teacher online professional learning and provide practical implications for designing and evaluating LA tools catered to teacher-learners.

This study employed multimodal learning analytics methods to evaluate different virtual reality (VR) interfaces, exploring their impact on the learning experience of cultural heritage. We recorded and analyzed the participants’ learning behavior, self-reported perceptions from questionnaires’ responses, electroencephalogram (EEG) signals, and visual fatigue. Preliminary results suggested that VR interfaces with more modules per scene led to higher efficiency of use, although more modules did not improve viewing experience. This study provides insights for immersive interface design in cultural heritage learning.

Previous studies have evaluated the affordances and challenges of performing cognitively demanding learning tasks with background music (BGM), yet the effects of various types of BGM on learning still remain an open question. This study aimed to examine the impacts of different music genres and fine-grained music characteristics on learners’ emotional, physiological, and pupillary responses during reading comprehension. Leveraging multimodal learning analytics (MmLA) methods of collecting data in multiple modalities from learners, a user experiment was conducted on 102 participants, with half of them reading with self-selected BGM (i.e., the experimental group), while the other half reading without BGM (i.e., the control group). Results of statistical analyses and interviews revealed significant differences between the two groups in their self-reported emotions and automatically measured physiological responses when the experimental group was exposed to classical, easy-listening, rebellious and rhythmic music. Fine-grained music characteristics (e.g., instrumentation, tempo) could predict learners’ emotions, pupillary, and physiological responses during reading comprehension. The expected contributions of this study include: 1) providing empirical evidence for understanding affective dimensions of learning with BGM, 2) applying MmLA methods for examining the impacts of BGM on learning, and 3) yielding practical implications on how to improve learning with BGM.

Online courses enable wide access to educational resources and thus provide a feasible platform for cross-regional teacher professional learning. Learning analytics dashboards (LAD) can support online learners by providing fine-grained feedback generated from learners’ interactions with platforms. Nevertheless, most studies on teacher online professional learning focus on resource-rich and technology-advanced regions, with scarce attention to the Global South. Furthermore, existing studies on LAD design mainly target students’ learning, rather than teachers’ professional learning. Therefore, it is much needed to develop LAD for teacher-learners online professional learning in the Global South. Contextualized in an international online professional training initiative, this study conducted in-depth interviews with 42 teacher-learners from 19 countries in the Global South, aiming to identify their needs for 1) support on their self-regulated learning (SRL), and 2) potential LA components in dashboards. Findings indicated that teacher-learners needed support for self-regulated learning strategies, including motivation maintenance, time management, environment structuring, help-seeking, and self-evaluation. Nine LA features were identified to design the LADs to support SRL preliminarily. This co-designed LAD study with interviewees improved our understanding on the needs of college teachers in the Global South for LA support during their online professional learning, generating practical insights into needs-driven LAD designs.

While current evaluation of maker activities has rarely explored students’ learning processes, the multi-perspective and multi-level nature of collaboration adds complexity to learning processes of collaborative maker activities. In terms of group dynamics as an important indicator of collaboration quality, extant studies have shown the benefits of synchrony between learners’ actions during collaborative learning processes. However, synchrony of learners’ cognitive processes and visual attention in collaborative maker activities remains under-explored. Leveraging the multimodal learning analytics (MMLA) approach, this pilot study examines learners’ synchrony patterns from multiple modalities of data in the collaborative maker activity of virtual reality (VR) content creation. We conducted a user experiment with five pairs of students, and collected and analyzed their electroencephalography (EEG) signals, eye movement and system log data. Results showed that the five pairs of collaborators demonstrated diverse synchrony patterns. We also discovered that, while some groups exhibited synchrony in one modality of data before becoming not synchronized in another modality, other groups started with a lack of synchrony followed by maintaining synchrony. This study is expected to make methodological and practical contributions to MMLA research and assessment of collaborative maker activities.

Listening to music is a common behavior when people study or work. However, effects of music listening on studying are still disputed in previous studies. To explore the associations between music characteristics and learning performance and engagement and to develop a music recommender for studying in naturalistic settings, we conducted a two-month field experiment with 51 undergraduate and graduate students. A mobile application based on the experience sampling method was designed and implemented to ubiquitously collect participants' learning status and music listening traces. Statistical tests and machine learning were adopted respectively for uncovering the associations between music listening on learning and constructing a music recommendation model. Results first indicated that learners' music preferences and several musical features were positively correlated with self-reported learning performance and concentration. Furthermore, machine learning modeling demonstrated promising results for developing a music recommender for studying in naturalistic settings. Findings are expected to contribute to research on learning with background music and learning-oriented music recommendation.

Assessments of digital maker activities increasingly rely on automatically analyzing student-created products and their components, such as their textual output. In particular, recent learning analytics research has proposed incorporating text analytic feedback for facilitating students' virtual reality (VR) content creation, though lacking direct empirical evidence from student-created artefacts. Thus, this study examined the relationships between metrics on text in student-created VR content and their learning performance. VR narration scripts and performance scores were collected from 102 students in a maker-based general education course. Results of statistical testing and text mining show that high and low-performing students demonstrated significant differences in such metrics as word counts, vocabulary sizes, and frequent unigrams and bigrams. This study makes methodological and practical contributions in the domains of maker education and learning analytics.

Online video courses allow large-scale distribution of educational resources and thus provide a feasible platform for cross-regional teacher professional development (TPD). However, with most studies focusing on TPD using online video courses in developed countries, less attention was paid to factors influencing the online learning experience of teachers from less developed areas. Therefore, this pilot study aims at exploring predictors of 3471 college teachers' online learning engagement. First, the results of a multivariate linear regression (MLR) revealed that at the individual level, there was a significant positive relationship between teachers' age and learning duration. At the institutional level, participants from the partner institutions had longer learning durations. At the country level, there was a significant positive relationship between country literacy rates and learning durations. Then, another MLR on relationships between self-reported learning perceptions after taking the course and learning durations was conducted. Results showed that learners' prior knowledge was negatively associated with learning durations. There was a significantly positive relationship between “recommend this platform to others” and learning duration. The findings can inform us of the factors that may have been overlooked when supporting college teachers' online professional learning in developing countries.

Existing learning analytics (LA) studies on self-regulated learning (SRL) have rarely focused on maker education that emphasizes student autonomy in their learning process. Towards using LA methods for generating evidence of SRL in maker-based courses, this study leverages logs of a learning management system (LMS) with its activity design aligned with the maker-based pedagogy. We explored frequencies and sequential patterns of students’ SRL behaviors as reflected in the LMS logs and their relations with learning performance. Adopting a mixed method approach, we collected and triangulated both quantitative (i.e., system logs, performance scores) and qualitative (i.e., student-written reflections) data sources from 104 students. Based on current LA-based SRL research, we developed an LMS log-based analytic framework to define the SRL phases and behaviors applicable to maker activities. Statistical, data mining, and qualitative analysis methods were conducted on 48,602 logged events and 131 excerpts extracted from student reflections. Results reveal that high-performing students demonstrated some SRL behaviors (e.g., Making Personal Plans, Evaluation) more frequently than their low-performing counterparts, yet the two groups showcased fairly similar sequences of SRL behaviors. Theoretical, methodological and pedagogical implications are drawn for LA-based SRL research and maker education.

Affected by the Covid-19 pandemic, the way adolescents receive their education has changed drastically from offline classrooms to online digital space. Despite the benefits of digital devices, we must also be cautious of the possible negative impacts of using digital devices excessively. In this study, we proposed a smart planning course to support adolescents in managing daily digital device usage. Meanwhile, we examined the effects of this course through a novel multimodal learning analytics (MMLA) approach. Although results of the quasi-experiment indicated few significant effects of the intervention, possibly due to its timing, the proposed MMLA approach was shown to provide more comprehensive and refined data compared to traditional methods. Future studies can use this approach for further activity-based analysis of students’ digital well-being.

Due to the popularity of virtual reality (VR) in education settings and the rise of maker education, this paper presents LAVR, a platform for VR content creation with learning analytics functions. We design the platform where students can easily create VR stories through a web interface. A learning analytics dashboard is implemented to provide students with feedback on their progress and the quality of the textual content in their VR stories. The platform also offers learning management features for helping teachers set up classrooms with assignments. While the platform will be employed in a forthcoming general education course, we have conducted a preliminary usability evaluation with 12 students and one teacher, and gathered feedback for further refinements before its official launch. The platform will contribute to integrating learning analytics with maker activities.

Reading is an essential medium for learning, but it is challenging to measure learners’ cognitive processes during reading. Eye-tracking, as an approach in multimodal learning analytics (MmLA), can provide fine-grained data that reflect cognitive processes during reading. In this study, we investigated whether eye movements could predict passage reading performance in addition to language proficiency and cognitive abilities. In particular, we assessed learners’ eye movement pattern and consistency through a novel method, Eye Movement analysis with Hidden Markov Models (EMHMM), in addition to traditional eye movement measures. We found that longer saccade length predicted faster reading speed Also, higher English proficiency predicted faster reading speed through the mediation of longer saccade length. In contrast, reading comprehension accuracy was best predicted by a more consistent eye fixation at the beginning of reading engagement, which may result from a better developed visual routine due to higher reading expertise. These findings have important implications for ways to assess and facilitate learners’ reading through eye movement measures and to examine factors influencing reading performance. The methods adopted could further the development of MmLA and serve as an empirical example of understanding learners’ cognitive processes through collecting and modeling critical learner-centered metrics in novel modalities.

In times of pandemic-induced challenges, virtual reality (VR) allows audience to learn about cultural heritage sites without temporal and spatial constraints. The design of VR content is largely determined by professionals, while evaluations of content often rely on learners’ self-report data. Learners’ attentional focus and understanding of VR content might be affected by the presence or absence of different multimedia elements including text and audio-visuals. It remains an open question which design variations are more conducive for learning about heritage sites. Leveraging eye-tracking, a technology often adopted in recent multimodal learning analytics (MmLA) research, we conducted an experiment to collect and analyze 40 learners’ eye movement and self-reported data. Results of statistical tests and heatmap elicitation interviews indicate that 1) text in the VR environment helped learners better understand the presented heritage sites, regardless of having audio narration or not, 2) text diverted learners’ attention away from other visual elements that contextualized the heritage sites, 3) exclusively having audio narration best simulated the experience of a real-world heritage tour, 4) narration accompanying text prompted learners to read the text faster. We make recommendations for improving the design of VR learning materials and discuss the implications for MmLA research.

Being a promising constructionist pedagogy in recent years, maker education empowers students to take agency of their learning process through constructing both knowledge and real-world physical or digital products and fosters peer interactions for collective innovation. Learning Analytics (LA) excels at generating personalized, fine-grained feedback in near real-time and holds much potential in supporting process-oriented and peer-supported learning activities, including maker activities. In the context of virtual reality (VR) content creation for cultural heritage education, this study qualitatively solicited 27 students’ needs on progress monitoring, reflection, and feedback during their making process. Findings have inspired the prototype design of a student-facing LA dashboard (LAVR). Leveraging multimodal learning analytics (MmLA) such as text and audio analytics to fulfill students’ needs, the prototype has various features and functions including automatic task reminders, content quality detection, and real-time feedback on quality of audio-visual elements. A preliminary evaluation of the prototype with 10 students confirms its potential in supporting students’ self-regulated learning during the making process and for improving the quality of VR content. Implications on LA design for supporting maker education are discussed. Future work is planned to include implementation and evaluation of the dashboard in classrooms.

Learning analytics (LA) mines, analyzes and visualizes the data of students' learning behaviours on learning platforms such as Learning Management Systems (LMS), but few LA tools built are adaptable to multiple platforms or for general education courses. This study sets out to evaluate a lightweight LA tool implemented on Moodle and Open edX for monitoring students' learning progress. Survey data were collected from 156 students, supplemented by interview responses from 25 students and three instructors. Preliminary results show that a considerable portion of surveyed students used the LA tool and they held positive opinions on its efficacy in monitoring self-progress and the effectiveness of its visualizations for information delivery. Nonetheless, learners who did not use the LA tool raised concerns about it relying only on their online behaviours without considering their offline learning. Coupled with instructors' evaluation results, discussion and implications are presented.

Music is a popular form of entertainment and has become common practice to adjust cognition, affect, and motivation. Regarding the effects of background music on learning tasks, results are inconclusive in the literature. Recent advancement of wearable devices and computing analytics supports automated detection of multimodal physiological signals, such as eye movements, neural responses, and heart rates in a real-time fashion, which can facilitate tracking learners' changes of affect, attention, and cognition while they study with the accompaniment of background music. However, most existing studies focus only on behavioral levels, and few employed signals at physiological levels to investigate the impact of background music on learning. To fill in the research gap, this doctoral project designs two types of visual cognitive tasks, that is, reading comprehension task and art appreciation task. It aims to integrate multimodal data (e.g., eye movements, electroencephalogram (EEG), and peripheral physiological signals) to probe the effect of background music on the tasks. Its findings will extend our knowledge on the interactions among learners' performance, emotion, and engagement at both physiological and behavioral levels in multi-channel learning settings, and contribute to a goal of recommending suitable background music for self-learning.

Minority college students' learning engagement is an important perspective for improving education equity and facilitating learning. Based on responses from a large-scale experience survey among Chinese college students, this study aims to explore minority students' engagement in nine learning activities and its relationship with learning outcomes, as well as their difference from overall student sample. Descriptive statistical analysis, single sample t-test, and multiple linear regression analysis were conducted. The results revealed: (1) Minority students' engagement in learning activities was low, especially in formal learning activities. (2) Interaction with teachers, engagement in arts activities did not predict minority students' learning outcomes, which was different from findings in the overall student sample. (3) Engagement in student organizations did not predict students' learning outcomes in either sample. Based on results, suggestions were discussed for improving students' learning engagement.

The rapid development of wearable technologies has dramatically promoted the potential usages of wearable devices in educational data analytics. However, the large amount of input data and the various types of educational output labels also increase the difficulties in selecting the useful information and discovering the implicit relations between different input data. To address this issue, this paper proposed a new two-layer approach for conducting educational data analytics automatically. In this approach, there are three key components: input layer, output layer and recognition model. For the input layer, we adopted the newly proposed optimization algorithm: Adaptive Multi-Population Optimization (AMPO) to select the most related input features and suitable model structures. For the output layer, we inserted domain-specific constraints during the searching for all combinations of different output labels to discover a meaningful output strategy with a relatively higher accuracy. Based on the input elements and output strategy provided by the input layer and the output layer, the recognition model will produce the corresponding recognition accuracy. With these three components, our proposed method can find out some connotative information to provide guidance for conducting educational data analytics and drawing meaningful conclusions.

Through profiling learners’ music usage in everyday learning settings and depicting their learning experience when studying with a music app powered by a large-scale and real-world music library, this study revealed preliminary observations on how background music impacts learning under varying task load, and manifested intriguing patterns of learners’ music usage and music preferences in various task load conditions. Specifically, we piloted a three-day field experiment in students’ everyday learning environment. During the experiment, participants performed learning tasks with music in the background and completed a set of online surveys before and after each learning session. Our results suggested that learners’ self-selected, real-life background music could enhance their learning effectiveness, while the beneficial effect of background music was more apparent when the learning task was less mentally or temporally demanding. Towards a closer look at the characteristics of preferable music pieces under various task load conditions, our findings showed that music preferred by participants under high versus low temporal demand differs in a number of characteristics, including speechiness, acousticness, danceability, and energy. This study further reveals the effects of background music on learning under varying task load levels and provides implications for context-aware background music selection when designing musically enriched learning environments.

With the rapid development in wearable technology, wearable devices integrating with various sensors have been broadly applied in different areas. Yet there is seldom any previous study which focuses on applying wearable devices and deep learning in learning analytics. This paper considers a sophisticated real-time learning analytics platform for analyzing students' learning states and learning activities with wearable devices and deep learning. During the experimental period of this platform, students will receive instant notifications from an intelligent mobile application when their heart rate are out of their normal range so that the actual learning activities conducted by students can be collected to train deep learning models for recognizing their learning activities. At the same time, students can enjoy the sleeping monitoring and the exercise monitoring functionalities provided by the smart watches in this platform. The results of the interviews conducted after the experiment for this platform demonstrate that 89% of students think that this platform is useful for their daily lives and 65% of students report that this platform brings positive effects on their learning in different aspects. More importantly, this work sheds lights on the possibility of applying wearable devices in learning analytics to improve the learning effectivenesses and life qualities of students.

Empirical evidence of how background music benefits or hinders learning becomes the crux of optimizing music recommendation in educational settings. This study aims to further probe the underlying mechanism through an experiment in naturalistic setting. 30 participants were recruited to join a field experiment which was conducted in their own study places for one week. During the experiment, participants were asked to conduct learning sessions with music in the background and collect music tracks they deemed suitable for learning using a novel mobile-based music discovery application. A set of participant-related, context-related, and music-related data were collected via a pre-experiment questionnaire, surveys popped up in the music app, and the logging system of the music app. Preliminary results reveal correlations between certain music characteristics and learners' task engagement and perceived task performance. This study is expected to provide evidence for understanding cognitive and emotional dimensions of background music during learning, as well as implications for the role of personalization in the selection of background music for facilitating learning.

Abstract Information service providers often require evidence from multiple, heterogeneous information sources to better characterize users and offer personalized service. In many cases, statistic information (for example, users' profiles) and sequentially dynamic information (for example, logs of interaction with information systems) are two prominent sources that can be combined to achieve optimized results. Previous attempts in combining these two sources mainly exploited models designed for either static or sequential information, but not both. This study aims to fill the gap by proposing a novel joint neural network model that can naturally fit both static and sequential user data. To evaluate the effectiveness of the proposed method, this study uses the problem of at‐risk student prediction as an example where both static data (personal profiles) and sequential data (event logs) are involved. A thorough evaluation was conducted on an open data set, with comparisons to a range of existing approaches including both static and sequential models. The results reveal superb performances of the proposed method. Implications of the findings on further research and applications of joint models are discussed.

With the popularity of wearable devices, smart watches containing various sensors have been widely adopted for many healthcare applications. Yet there is rarely any research study on the possible uses of smart watches for learning analytics, particularly for analyzing students' learning activities through the physiological and/or movement data collected on their smart watches. This paper considers a pioneering and sophisticated learning analytics platform using fine-tuned deep learning models to predict students' learning activities based on the real-time data, including their heart rates, calories, three-axis accelerometer and gyroscope data, captured on wearable devices and then uploaded onto a cloud server for thorough analyses. To validate on the actual activities conducted by each student, an intelligent mobile application is developed to push instant notifications for students to report their own activities whenever the change of heart rates are deviated significantly from their normal values. Based on students' heart rates and calories, a long-short term memory (LSTM) model is built to classify students' learning states as active or not with an impressive prediction accuracy of 95% whereas another hybrid model combining both the LSTM and convolutional neural networks attains the highest prediction accuracy of 74% to predict students' specific learning activities as based on their physiological and movement data. The prototype implementation clearly demonstrates the feasibility of the proposed framework for learning analytics. More importantly, this work shed lights on various directions including the integration of noise filters to preprocess the collected data for further investigation.

It is a common phenomenon for students to listen to background music while studying. However, there are mixed and inconclusive Kindings in the literature, leaving it unclear whether and in which circumstances background music can facilitate or hinder learning. This paper reports a study investigating the effects of Kive different types of background audio (four types of music and one environmental sound) on reading comprehension. An experiment was conducted with 33 graduate students, where a series of cognitive, metacognitive, affective variables and physiological signals were collected and analyzed. Preliminary results show that there were differences on these variables across different music types. This study contributes to the understanding and optimizing of background music for facilitating learning.

Gaps between knowledge sources are interesting to various stakeholders: they might indicate potential misconceptions awaiting correction, complex or novel knowledge that requires careful delivery or studying. Motivated by these underlying values, this study explores the knowledge gap phenomenon in the context of student textual responses. In the method proposed in this study, discourses are first mapped into structured knowledge spaces where gaps between correct/incorrect responses and assessed knowledge are measured by network-based metrics. Empirical results demonstrate the effectiveness of the proposed method in measuring gaps in student responses. The networked representation of texts proposed in this study is novel in quantitatively framing gaps of knowledge. It also offers a set of validated metrics for analyzing student responses in research and practice.

Digital platforms enable the observation of learning behaviors through fine-grained log traces, offering more detailed clues for analysis. In addition to previous descriptive and predictive log analysis, this study aims to simultaneously model learner activities, event time spans, and interaction levels using the proposed Hidden Behavior Traits Model (HBTM). We evaluated model performance and explored their capability of clustering learners on a public dataset, and tried to interpret the machine recognized latent behavior patterns. Quantitative and qualitative results demonstrated the promising value of HBTM. Results of this study can contribute to the literature of online learner modeling and learning service planning.

There are existing multi-MOOC level dropout prediction research in which many MOOCs' data are involved. This generated good results, but there are two potential problems. On one hand, it is inappropriate to use which week students are in to select training data because courses are with different durations. On the other hand, using all other existing data can be computationally expensive and inapplicable in practice.

Digitization provides a solution for documentation and preservation of nonmovable cultural heritages. Despite efforts for the preservation of cultural heritages around the world, no well‐accepted metadata schema has been developed for murals and stone cave temples, which are often high‐value heritages built in ancient times. In addition, the literature is scarce on the user‐centered evaluation of metadata schemas of this kind. This study therefore aims to offer insights on developing and evaluating a metadata schema for organizing information of these historic and complex cultural heritages. In‐depth interviews were conducted with a total of 30 users, including 18 professional and 12 public users, and interview transcripts were coded through a qualitative content analysis approach. Findings reveal the importance of specific metadata elements as perceived by the two groups of end users, which correlated with their cultural heritage information‐seeking behaviors. In addition, the issues of standardization of cataloging of cultural heritage information and interoperability among metadata schemas have been raised by users for enhancing the user experience with digital platforms of cultural heritage information. The coding schema developed in this study can serve as a framework for follow‐up evaluations of metadata schemas, contributing to the ongoing development of cultural heritage metadata.

Predicting student learning outcomes is one of the prominent themes in Learning Analytics research. These studies varied to a significant extent in terms of the techniques being used, the contexts in which they were situated, and the consequent effectiveness of the prediction. This paper presented the preliminary results of a systematic review of studies in predictive learning analytics. With the goal to find out what methodologies work for what circumstances, this study will be able to facilitate future research in this area, contributing to relevant system developments that are of pedagogic values.

This poster presents a cross-platform learning analytics dashboard on Moodle and Open edX for monitoring outcome-based learning progress. The dashboard visualizes students' interactions with the platforms in near real-time, aiming to help teachers and students monitor students' learning progress. The dashboard has been used in four large-size general education courses in a comprehensive university in Hong Kong, undergoing evaluation and improvement.

Wikiglass is a learning analytic tool for visualizing collaborative work on Wikis built by groups of secondary or primary school students. This poster presents new features of Wikiglass developed recently based on requests from teachers, including flexible selection of date range, revision network, and thinking order detection. Currently the new features are used and evaluated in two secondary schools in Hong Kong.

This research proposes a framework for music mood classification that uses multiple and complementary information sources, namely, music audio, lyric text, and social tags associated with music pieces. This article presents the framework and a thorough evaluation of each of its components. Experimental results on a large data set of 18 mood categories show that combining lyrics and audio significantly outperformed systems using audio‐only features. Automatic feature selection techniques were further proved to have reduced feature space. In addition, the examination of learning curves shows that the hybrid systems using lyrics and audio needed fewer training samples and shorter audio clips to achieve the same or better classification accuracies than systems using lyrics or audio singularly. Last but not least, performance comparisons reveal the relative importance of audio and lyric features across mood categories.

There has been little research on task complexity and difficulty in music information retrieval (MIR), whereas many studies in the text retrieval domain have found that task complexity and difficulty have significant effects on user effectiveness. This study aimed to bridge the gap by exploring i) the relationship between task complexity and difficulty; ii) factors affecting task difficulty; and iii) the relationship between task difficulty, task complexity, and user search behaviors in MIR. An empirical user experiment was conducted with 51 participants and a novel MIR system. The participants searched for 6 topics across 3 complexity levels. The results revealed that i) perceived task difficulty in music search is influenced by task complexity, user background, system affordances, and task uncertainty and enjoyability; and ii) perceived task difficulty in MIR is significantly correlated with effectiveness metrics such as the number of songs found, number of clicks, and task completion time. The findings have implications for the design of music search tasks (in research) or use cases (in system development) as well as future MIR systems that can detect task difficulty based on user effectiveness metrics.

Music Information Retrieval (MIR) evaluation has traditionally focused on system‐centered approaches where components of MIR systems are evaluated against predefined data sets and golden answers (i.e., ground truth). There are two major limitations of such system‐centered evaluation approaches: (a) The evaluation focuses on subtasks in music information retrieval, but not on entire systems and (b) users and their interactions with MIR systems are largely excluded. This article describes the first implementation of a holistic user‐experience evaluation in MIR, the MIREX Grand Challenge, where complete MIR systems are evaluated, with user experience being the single overarching goal. It is the first time that complete MIR systems have been evaluated with end users in a realistic scenario. We present the design of the evaluation task, the evaluation criteria and a novel evaluation interface, and the data‐collection platform. This is followed by an analysis of the results, reflection on the experience and lessons learned, and plans for future directions.

Music mood recognition (MMR) has attracted much attention in music information retrieval research, yet there are few MMR studies that focus on non‐Western music. In addition, little has been done on connecting the 2 most adopted music mood representation models: categorical and dimensional. To bridge these gaps, we constructed a new data set consisting of 818 Chinese Pop (C‐Pop) songs, 3 complete sets of mood annotations in both representations, as well as audio features corresponding to 5 distinct categories of musical characteristics. The mood space of C‐Pop songs was analyzed and compared to that of Western Pop songs. We also explored the relationship between categorical and dimensional annotations and the results revealed that one set of annotations could be reliably predicted by the other. Classification and regression experiments were conducted on the data set, providing benchmarks for future research on MMR of non‐Western music. Based on these analyses, we reflect and discuss the implications of the findings to MMR research.

In music mood prediction, regression models are built to predict values on several mood-representing dimensions such as valence (level of pleasure) and arousal (level of energy). Many studies have shown that music mood is generally predictable based on music acoustic features, but these experiments were mostly conducted on datasets with homogeneous music. Little research has been done to explore the generalizability of mood regression models cross datasets, especially those with music in different cultures. In the increasingly global market of music listening, generalizable models are highly desirable for automated processing, searching and managing music collections with heterogeneous characteristics. In this study, we evaluated mood regression models built on fifteen acoustic features in five mood-related musical aspects, with a focus on cross-dataset generalizability. Specifically, three distinct datasets were involved in a series of five experiments to examine the effects of dataset size, reliability of annotations and cultural backgrounds of music and annotators on mood regression performances and model generalizability. The results reveal that the size of the training dataset and the annotation reliability of the testing dataset affect mood regression performances. When both factors are controlled, regression models are generalizable between datasets sharing a common cultural background of music or annotators.

This demo presents Wikiglass, a learning analytic tool for visualizing the statistics and timelines of collaborative Wikis built by secondary school students during their group project in inquiry-based learning. The tool adopts a modular structure for the flexibility of reuse with different data sources. The client side is built with the Model-View-Controller framework and the AngularJS library whereas the server side manages the database and data sources. The tool is currently used by secondary teachers in Hong Kong and is undergoing evaluation and improvement.

This study attempts to investigate to what extent indicators of academic writing and cognitive thinking can help measure the writing quality of group collaborative writings on Wikis. Particularly, comparisons were made on Wiki content in different stages of the projects. Preliminary results from a multiple linear regression analysis reveal that linguistic indicators such as engagement markers and self-mention were significant predictors in earlier stages to the projects, whereas verbs indicating cognitive thinking in the evaluation level were significant in later project stages.

Given the importance of reading proficiency and habits for young students, an online e-quiz bank, Reading Battle, was launched in 2014 to facilitate reading improvement for primary-school students. With more than ten thousand questions in both English and Chinese, the system has attracted nearly five thousand learners who have made about half a million question answering records. In an effort towards delivering personalized learning experience to the learners, this study aims to discover potentially useful knowledge from learners' reading and question answering records in the Reading Battle system, by applying association rule mining and clustering analysis. The results show that learners could be grouped into three clusters based on their self-reported reading habits. The rules mined from different learner clusters can be used to develop personalized recommendations to the learners. Implications of the results on evaluating and further improving the Reading Battle system are also discussed.

No abstract available.

Previous work on text mining has almost exclusively focused on a single stream. However, we often have available multiple text streams indexed by the same set of time points (called coordinated text streams), which offer new opportunities for text mining. For example, when a major event happens, all the news articles published by different agencies in different languages tend to cover the same event for a certain period, exhibiting a correlated bursty topic pattern in all the news article streams. In general, mining correlated bursty topic patterns from coordinated text streams can reveal interesting latent associations or events behind these streams. In this paper, we define and study this novel text mining problem. We propose a general probabilistic algorithm which can effectively discover correlated bursty patterns and their bursty periods across text streams even if the streams have completely different vocabularies (e.g., English vs Chinese). Evaluation of the proposed method on a news data set and a literature data set shows that it can effectively discover quite meaningful topic patterns from both data sets: the patterns discovered from the news data set accurately reveal the major common events covered in the two streams of news articles (in English and Chinese, respectively), while the patterns discovered from two database publication streams match well with the major research paradigm shifts in database research. Since the proposed method is general and does not require the streams to share vocabulary, it can be applied to any coordinated text streams to discover correlated topic patterns that burst in multiple streams in the same period.

Given the experimental nature of information retrieval, progress critically depends on analyzing the errors made by existing retrieval approaches and understanding their limitations. Our research explores various hypothesized reasons for hard topics in TREC-8 ad hoc task, and shows that the bad performance is partially due to the existence of highly distracting sub-collections that can dominate the overall performance.