Concept mapping facilitates the externalisation and internalisation of knowledge by individuals during collaborative knowledge construction. However, not much is known about the individual and collaborative learning processes during collaborative concept mapping (CCM) in interdisciplinary knowledge construction. Premised on literature on collaboration scripts to scaffold the collaboration process, this study investigates the effect of an individual preparation phase prior to collaborative work on the epistemic and social processes of knowledge co-construction, as well as the degree of interdisciplinary knowledge integration in collaborative concept mapping. A total of N = 42 third year university students were put into one of the two experimental conditions: with individual preparation phase (WIP) and without individual preparation phase (WOIP). Students worked on a collaborative assignment to integrate interdisciplinary knowledge in collaborative concept mapping. Data for analysis was derived from audio recordings of the collaborative discourse in both experimental conditions. Chi-square test was conducted to investigate if there were significant differences between the effects of WIP and WOIP on the epistemological and social dimension. Findings showed that groups in the WIP condition showed significantly more verification, clarification and positioning statements in the epistemic dimension and also significantly more integration-oriented and conflict-oriented consensus building in the social dimension as compared to groups in the WOIP condition. On the degree of interdisciplinary knowledge integration, independent sample t-tests showed that there was no significant difference for concepts, domains and cross-links between the two experimental conditions. However, there was significant difference in types of cross-links for the CCMs in the WIP condition.

@en

Massive Open Online Courses (MOOCs), delivered on platforms such as edX and Coursera, have led to a surge in large-scale learning research. MOOC platforms gather a continuous stream of learner traces, which can amount to several Gigabytes per MOOC, that learning analytics researchers use to conduct exploratory analyses as well as to evaluate deployed interventions. edX has proven to be a popular platform for such experiments, as the data each MOOC generates is easily accessible to the institution running the MOOC. One of the issues researchers face is the preprocessing, cleaning and formatting of those large-scale learner traces. It is a tedious process that requires considerable computational skills. To reduce this burden, a number of tools have been proposed and released with the aim of simplifying this process. Those tools though still have a significant setup cost, are already out-of-date or require already preprocessed data as a starting point. In contrast, in this paper we introduce ELAT, the edX Log file Analysis Tool, which is browser-based (i.e., no setup costs), keeps the data local (i.e., no server is necessary and the privacy-sensitive learner data is not send anywhere) and takes edX data dumps as input. ELAT does not only process the raw data, but also generates semantically meaningful units (learner sessions instead of just click events) that are visualized in various ways (learning paths, forum participation, video watching sequences). We report on two evaluations we conducted: (i) a technological evaluation and a (ii) user study with potential end users of ELAT. ELAT is open-source and available at https://mvallet91.github.io/ELAT/.

@en

Using Artificial Intelligence (AI) and machine learning technologies to automatically mine latent patterns from educational data holds great potential to inform teaching and learning practices. However, the current AI technology mostly works as "black box"-only the inputs and the corresponding outputs are available, which largely impedes researchers from gaining access to explainable feedback. This interdisciplinary work presents an explainable AI prototype with visualized explanations as feedback for computer-supported collaborative learning (CSCL). This research study seeks to provide interpretable insights with machine learning technologies for multimodal learning analytics (MMLA) by introducing two different explanatory machine learning-based models (neural network and Bayesian network) in different manners (end-to-end learning and probabilistic analysis) and for the same goal-provide explainable and actionable feedback. The prototype is applied to the real-world collaborative learning scenario with data-driven learning based on sensor-data from multiple modalities which can assess collaborative learning processes and render explanatory real-time feedback.@en

This paper presents a ubiquitous and mobile MOOC platform to foster lifelong learning. Harnessing the technological affordances of WeChat (a mobile social media app), learners accessed micro-learning activities and received personal learning analysis report on their mobile phones. Premised on activity theory, the mobile MOOC design model spans across five dimensions of intelligent distribution: learning objective analysis, learner persona analysis, platform improvement based on learning analytics, m-learn tool selection and m-learn interactive environment where the latter forms the core of individual and collaborative learning. To investigate learning effectiveness, we analysed the survey data of 117 Shanghai kindergarten, primary and secondary teachers in one mini-lecture. Findings showed that learning satisfaction and learning achievement are highly correlated with the learnability of the learning environment. The integration of a multidimensional activity and multi-scenario model showed great potential to successfully accommodate the complexity and diversity of mobile MOOC learning activities in a ubiquitous-learning environment.

@en

Recent discourse and research studies on mobile learning showed increasing awareness of the complexity of mobile learning in the digital age. Notwithstanding mobile devices, Web 2.0 and Web 3.0 technologies have greatly empowered learners and educators to overcome the constraints of conventional education, such as time, space, location and to learn on the move. However, balancing technological dependency and learner autonomy remains an area of contention in designing meaningful mobile learning activities. Hence, this interactive and participatory workshop aims to bring together researchers and practitioners working on this issue to share their experience and to engage in facilitated activities and discussions on designing mobile learning activities that effectively balance learners’ agency with mobile technology. Additionally, this workshop also provides a platform for unsolved challenges and future research directions on smart technology and smart learning spaces in the context of mobile learning, laying the groundwork for joint research efforts.

@en

This article examined the role of environmental interaction in interdisciplinary thinking and the use of different knowledge resource types. The case study was conducted with two classes (N = 40) of 8th-grade students, ages 13 to 14. The outdoor trail aimed to help students synthesize history, geography, and science knowledge. Two groups’ discourse from each class was audio-­recorded and transcribed for content analysis. We coded the discourse to examine: (i) the use of different knowledge resource types (i.e., contextual resource, new conceptual resource, prior knowledge resource); (ii) the relationship among these knowledge resource types; and (iii) evidences of interdisciplinary thinking. Findings showed that contextual resources enhanced students’ capacity to develop new conceptual resources and to activate prior knowledge resources. Further, about 80% of students’ discourse demonstrated interdisciplinary connections of two subjects.

@en

This paper investigates the effect of anonymity in online peer review on feedback types (directive, non-directive, higher-order concern, lower-order concern) and students' revisions (processed, partly processed and not processed) in second-language writing. Participants were 114 Dutch second-year university students. They were assigned to two experimental conditions: anonymous and non-anonymous. Results showed that students in the anonymous condition provided significantly more feedback on higher-order concerns and offered significantly different types of feedback than students in the non-anonymous condition. As for revision, overall findings showed that assessees in the anonymous condition did not process more feedback (i.e., the adoption rate) than their non-identified peers, however, assessees in the anonymous condition processed significantly more directive higher-order feedback and scored significantly higher final grades for the writing module than their non-anonymous peers. These results might imply that anonymity could enable learners to provide unreservedly more higher-order concerns feedback type. On the self-same note, the adoption and revision of these higher-order feedback items was instrumental in the improved writing performance of students in the anonymous condition.

@en