The cognitive benefits of microlearning, combined with the behavioural potential of nudging, provided a ground base for our research and development of a mobile application that could facilitate the creation and re-usage of microactivities as a means to promote active participation, motivation and engagement. While still in the initial development and design phases, we tested a prototype of the application from the usability and adoption point of view and achieved promising results. The feedback from eleven university teachers was mainly positive, with a good usability score and encouraging input on usefulness. However, our results suggest several areas for improvement, especially in the teachers' understanding of how to use and retrieve resources that suit their specific needs.

Selecting an appropriate graduation project and supervisor is an important step for BSc and MSc students; a good compatibility between the student and the teacher, in terms of personality and supervisory style, contributes to enhanced achievement, engagement and well-being. Nevertheless, few approaches have been proposed in the literature to use these compatibility factors for providing student-teacher matching recommendations. In this context, we propose a system called Smart Project Allocation (SPA) which facilitates the supervisor selection process by providing personalized suggestions based on comprehensive student and teacher models (including personality, supervisory style and topics of interest). In addition, the platform provides a mechanism for automatic project allocation, which dynamically assigns projects to students in a more efficient, fair and transparent manner than the traditional manual approach.

By offering courses and resources, learning platforms on the Web have been attracting lots of participants, and the interactions with these systems have generated a vast amount of learning-related data. Their collection, processing and analysis have promoted a significant growth of learning analytics and have opened up new opportunities for supporting and assessing educational experiences. To provide all the stakeholders involved in the educational process with a timely guidance, being able to understand student's behavior and enable models which provide data-driven decisions pertaining to the learning domain is a primary property of online platforms, aiming at maximizing learning outcomes. In this workshop, we focus on collecting new contributions in this emerging area and on providing a common ground for researchers and practitioners (Website: https://mirkomarras.github.io/l2d-wsdm2021).

Peer assessment is a valuable approach in education, which can increase students' engagement and foster critical thinking and reflection. In this paper we investigate the potential of peer assessment for project-based learning settings, by means of a comparative case study. More specifically, we analyze and compare the outcomes and experiences of the students in two similar scenarios: one course where the peer assessment activity is compulsory and one course where it is optional. A dedicated peer assessment platform, called LearnEval, is used in both cases, which supports the teacher in configuring and monitoring the process and the students in reviewing peers' work and visualizing their activity and personal scores. We provide a description of the project settings and compare the unfolding and results of the two studies; we analyze the involvement and reviewing skills of the students, as well as their subjective appraisal of the learning experience. Our study adds to the body of literature on peer assessment, while the lessons learned can prove useful for the practitioners in devising and refining their instructional scenarios.

Peer assessment is widely used in educational settings as an alternative evaluation approach. It brings various benefits to the students, increasing engagement and interactivity and fostering critical thinking and reflection. Several platforms for managing the peer review process have been proposed in the literature, but most of them are confined to a particular domain or course and have various limitations related to reliability, reviewer allocation, reputation and training of reviewers or instructor support. In an attempt to address these challenges, we propose an innovative general-purpose peer assessment platform, called LearnEval. In this paper we focus on the student module part of the system, describing its functionalities, pedagogical rationale and implementation details.

Community of Inquiry (CoI) model is a framework with socio-constructivist roots, which describes an online learning community on three interdependent components: cognitive presence, social presence and teaching presence. Content analysis is widely used to examine transcripts of computer mediated conversations between students in a community of inquiry. However, there are no dedicated support tools for this process (apart from generic commercial software for qualitative data analysis). Therefore, in this paper we propose a content analysis tool specifically built for CoI, called CollAnnotator. The system provides several important features such as: comprehensive annotation functionality, support for multiple categories per unit of analysis, support for multiple coders and the negotiation process, detailed statistics and reports with graphical visualizations, all in an intuitive and easy-to-use interface. The paper describes the tool rationale, functionalities and some implementation details.

Social media tools are increasingly popular in Computer Supported Collaborative Learning and the analysis of students' contributions on these tools is an emerging research direction. Previous studies have mainly focused on examining quantitative behavior indicators on social media tools. In contrast, the approach proposed in this paper relies on the actual content analysis of each student's contributions in a learning environment. More specifically, in this study, textual complexity analysis is applied to investigate how student's writing style on social media tools can be used to predict their academic performance and their learning style. Multiple textual complexity indices are used for analyzing the blog and microblog posts of 27 students engaged in a project-based learning activity. The preliminary results of this pilot study are encouraging, with several indexes predictive of student grades and/or learning styles.

Investigating learning performance predictors is an important part of the educational process. Active participation or engagement is one such predictor, which has been widely analyzed in traditional learning settings, but less in the emerging social-media based learning environments. This paper explores the relationship between students' active participation on three social media tools (wiki, blog, microblogging tool) and their academic performance, in the context of a project-based learning scenario. Two cohorts, with a total of 119 students, are included in the study. Multiple linear regression is used to build easily interpretable models, which explain the final grade in terms of social media activity. Results indicate that engagement with social media tools is a good predictor of the student performance. More specifically, the models show that several features have an influence on the grade, such as: the frequency of blog posts, the average length of the tweets, the number of wiki page revisions, the average number of revisions for each distinct wiki page, the number of blog comments, the number of wiki file uploads.

Wikis are social media tools which allow users to easily create and edit pages collaboratively, enabling the co-construction of content. Due to their potential to facilitate cooperative and collaborative learning, they have started to be used in educational settings, with generally positive results. This paper reports on the successful experience of using a wiki as a support tool for a project-based learning scenario, in Computer Science education. The main assets of the study consist in its relatively large scale (215 students over a period of 4 years) and the assessment of data coming from two sources: students' activity on the wiki (collected by a dedicated tracking tool) and students' perceptions regarding the use of wiki (collected by means of opinion surveys). Some lessons learned and potential solutions for further boosting student engagement and promoting collaboration in wiki-supported learning are also included in the paper.

Analyzing student performance indicators has been a long-standing research direction, nowadays demanding for new multidimensional approaches tailored to the recent advent of Web 2.0 in education. This paper investigates two such potential learning performance indicators: i) students' active involvement with the Web 2.0 tools and ii) students' learning styles. By using Principal Component Analysis (PCA) we were able to identify a subset of student activities that are relevant to build up an orthogonal space of representation and those activities that may support prediction of learner success (measured as final grades). On the other hand, no significant correlations were found between the Felder-Silverman learning styles and students' performance in our case study.

With the recent introduction of social software in education, there is a need for support applications that will help teachers monitor students' activity on these Web 2.0 tools. In this paper we present such an approach for learner tracking and visualization in an integrated social learning environment called eMUSE. The platform collects learner actions from each of the disparate Web 2.0 tools (by means of APIs or RSS feeds), stores them in a local database for further processing and presents them to the instructor in suggestive graphical formats.

This paper presents the design, development and testing of an e-assessment system, focusing on the practical part of the Medical School training. It also discusses several important aspects that need to be taken into consideration when creating an e-learning application for the medical domain. For example, the application must accustom the student with certain procedure protocols, it must be available to as many scholars as possible and it must be appealing in order for the students to exercise a greater amount of time. The results indicate that case-bcase-based virtual patient systemsased virtual patient systems can help prepare experts in the medical field with low costs and without allowing patients to be treated by still-training doctors.

Analyzing the behavior of learners in an educational system is the first step towards an implicit method for learning style diagnosis. To this end we performed an experimental study (reported in this paper) involving 75 students, whose interaction with WELSA educational system was monitored and analyzed. The investigation emphasized statistically significant relations between learning preferences and 30 of the behavioral patterns exhibited by the students. Discussions and interpretations of the obtained results are also provided in the paper.

This paper analyzes the behavior of students in an educational hypermedia system, with the goal of identifying correlations between patterns of behavior and studentspsila learning style. Data from an exploratory study are presented and discussed: 22 students interact with an educational hypermedia system called WELSA, having all their actions monitored and logged by the system. Behavioral patterns are subsequently determined based on these actions and a subset of them are graphically sketched in this note.

Accommodating learning styles in adaptive educational systems represents an important step towards providing individualized instruction. The paper summarizes the main results reported in the literature, as well as the main criticisms of the current approaches. Thus, most of the adaptive educational systems to date are based on a single learning style model and the diagnosis is done explicitly, by means of a psychological questionnaire. The lack of an integrative, comprehensive learning style model and the questionable validity and reliability of the measuring instruments are two important problems of this approach. In this context, we advocate the use of a unified learning style model, which exhibits the following properties: i) it integrates the most relevant characteristics from several models in the literature; ii) it includes e-learning specific aspects (technology related preferences); iii) it is stored as a set of learning characteristics, not as a stereotyping model. Moreover, the student diagnosis is to be done implicitly, based on analyzing her/his interactions with the system.