Kategorie: SPeL

Live Analytics for xMOOC students: a visualisation to support self-directed inquiry and collaboration

Philip Tubman, Phil Benachour, Murat Oztok

xMOOC platforms encourage a more independent study model that is in stark contrast to the more accepted socio‐constructivist approaches to learning [1]. They also produce academic engagement analytics, however these are only useful for teachers to make generalisations about course efficiency. This design based research project proposes a new tool which enables more learner centric, collaborative and self-directed inquiry-based learning. The ‘Comment Discovery Tool’ (CDT) is a visualisation of all user generated data (comments) on the course to support implicit conceptual scaffolding and personalised filtering. Comparative quantitative results from 35 courses, of which 9 contain the intervention, demonstrate that when the tool is included with little instruction conversation length, the number of unique participants is increased by a significant degree, and heuristic groupings associated with social interactions and based in IRF (initiation, response, feedback) [2] are also increased. Users who perceived the designed affordances also reported most benefit. Further iterative design based research phases will investigate how the tool can be integrated into courses within a learning design frame, and how it could be developed technically in order to create features which transform the MOOC experience; one suggestion is that the use of hashtags may act as a social glue for diverse learner communities and transform the nature of participation [3].

[1]      S. Bayne and J. Ross, ‘The pedagogy of the Massive Open Online Course: the UK view’, 2014.

[2]      N. Mercer, ‘Sociocultural discourse analysis: analysing classroom talk as a social mode of thinking’, J. Appl. Linguist. Prof. Pract., vol. 1, no. 2, pp. 137–168, 2007.

[3]      A. Bozkurt, S. Honeychurch, A. Caines, M. Bali, A. Koutropoulos, and D. Cormier, ‘Community tracking in a cMOOC and nomadic learner behavior identification on a connectivist Rhizomatic learning network’, Turk. Online J. Distance Educ., vol. 0, no. 0, Oct. 2016.

Curating educational resources for homework management: a support prototype

Andreea Isabela Bala, Stefania Carmen Dobre and Elvira Popescu

Learning content curation plays an important role given the increasing amount of educational resources available on the Web. The process implies searching, collecting, annotating, filtering, organizing and sharing relevant resources for a specific learning context. Our aim is to provide a support platform which allows both teachers and students to become content curators, leveraging various levels of expertise. More specifically, we propose a system dedicated to homework management, called EdReHo, which allows the collection and sharing of educational resources needed to understand and solve assignments. When teachers create an assignment in EdReHo, they can recommend also a set of resources relevant for that topic, which are aimed to supplement the mandatory course material. The students can also add useful resources and share them with peers, becoming more actively involved in the process and benefitting from the „learning by searching“ approach. The paper describes the EdReHo system prototype in terms of concept, features and implementation and illustrates its main functionalities.

Reconstructing Scanned Documents for Full-text Indexing to Empower Digital Library Services

Melania Nitu, Mihai Dascalu, Maria-Iuliana Dascalu, Teodor-Mihai Cotet and Silvia Tomescu

The digital era raises new challenges for traditional library services in which information has to be delivered and supported by technology-enhanced systems. The increasing need for rapid access to information requires librarians to re-evaluate the way they develop, manage and deliver resources, as well as services. However, most information extraction systems are not designed to work with PDF files generated after Optical Character Recognition, and several problems are encountered while trying to properly restructure the recognized text, for example: disruption of paragraphs, improper page breaks, or loss of content structure. This paper introduces a pre-processing pipeline designed to support university libraries to adequately index old document collections. The extracted text is indexed into Elasticsearch which facilitates the search for relevant documents, based on keywords. The information extraction system is designed to assist librarians in the digitization process by enabling a systematic review of documents, which leads to more accurate representations of the indexed files.

A web-based platform for building PBL competences among students

Hans Hüttel, Dorina Gnaur, Thomas Ryberg and Jette Egelund Holgaard

Problem-based learning (PBL) is at the heart of all degree programmes at Aalborg University and is most often project-organized. Experience shows that it is a challenge to develop the competences necessary for students to carry out PBL and requires systematic reflection of the part of students. The PBL Exchange/stud platform is a web-based platform intended for sharing student reflections and experience concering problem-based learning. In this paper we describe PBL Exchange/stud and our experience with introducing it in guided interventions in degree programmes at Aalborg University. The main challenge faced with PBL Exchange/stud turned out to be that of building a stable community of student users.

Semantic Recommendations and Topic Modeling based on the Chronology of Romanian Literary Life

Laurențiu-Marian Neagu, Teodor-Mihai Cotet, Mihai Dascalu, Stefan Trausan-Matu, Lucian Chisu, Eugen Simion

As part of the Romanian Academy’s effort aimed at underlining the importance of events centered on national authors and writings across time, the Chronology of Romanian Literary Life (also referred to as CVLR) is a centralized text repository which contains all important literature-related events that occurred after World War II. The current work presents an approach to capture topics’ evolution across time and helps learners by recommending events from the chronology on a given topic, based on a subset of 24 years of the CVLR. Our method combines techniques from information retrieval, topic modeling using LDA (Latent Dirichlet Allocation), and recommender systems to improve e-learning centered on Romanian literature. The most frequent topics in each year are ranked in order to identify and visualize the main interests in literature across time periods. Recommendations are performed in order to facilitate the exploration of the chronology, as it is currently indexed only by event dates.

Distributed student team work in challenge-based Innovation and Entrepreneurship (I&E) course

Galena Pisoni, Javier Segovia, Milena Stoycheva and Maurizio Marchese

Challenge-based learning is proposed as an alternative to traditional learning in training engineering graduates with the skills for the future. It puts equal emphasis on academic learning and on competences that students need more for their jobs. Challenge-based leaning is the learning in which students learn through understanding and resolution of a real-world challenge. In this paper we show how such challengebased course can be implemented in a cross-university setting in which students work on challenges provided by companies: the Universities that implemented the course are University of Trento, UNITN, Italy and Universidad Politcnica de Madrid, UPM, Spain and in it students form and work in teams composed of students coming from both of the locations. Both of the locations delivered the course at the same time. The positive feedback from the students shows the importance of such new multi method to train students adequately for remote team-work and training them with skills for 21st century, especially in the era of digital transformation. In addition, our paper draws important leanings on how to set such cross-university teams as well as important future research directions.

An educational model for integrating game-based and problem-based learning in data-driven flipped classrooms

Muriel Algayres, Evangelia Triantafyllou

Active learning has been employed in higher education, as a way to engage students more efficiently and encourage the development of 21st century skills. The flipped classroom (FC) in particular has known a remarkable development. The FC is defined as a teaching method where “events that have traditionally taken place inside the classroom now take place outside and vice versa”. The FC takes place into three stages: pre-class, in-class and post-class, all of which have used various technological tools and online environments. There is still, however, some lacks in research and development around the FC. Research into combining the FC with other active learning methods such as Problem-Based Learning (PBL) or Game-Based Learning (GBL) is a recent field of study. Furthermore, any endeavor into combining the FC and other methodologies or expanding the FC has been limited to one of its three stages, usually either for pre-class preparation or for in-class activities. Similarly, use of technology and learning analytics had so far been mostly limited to out-of-class periods. Therefore, we consider that there is potential in building a new theoretical model to enhance the FC methodology by incorporating problem-based learning and learning analytics in the full learning process, and to develop the new FC model as an adaptive, data-driven, personalized experience. This paper will therefore present the new pedagogical model, its structure, and the technological tools that will support its development.