Learning in computer-mediated setting represents a complex, multidimensional process. This complexity calls for a comprehensive analytical approach that would allow for understanding of various dimensions of learner generated discourse and the structure of the underlying social interactions. Current research, however, primarily focuses on manual or, more recently, supervised methods for discourse analysis. Moreover, discourse and social structures are typically analyzed separately without the use of computational methods that can offer a holistic perspective. This paper proposes an approach that addresses these two challenges, first, by using an unsupervised machine learning approach to extract speech acts as representations of knowledge construction processes and finds transition probabilities between speech acts across different messages, and second, by integrating the use of discovered speech acts to explain the formation of social ties and predicting course outcomes. We extracted six categories of speech acts from messages exchanged in discussion forums of two MOOCs and each category corresponded to knowledge construction processes from well-established theoretical models. We further showed how measures derived from discourse analysis explained the ways how social ties were created that framed emerging social networks. Multiple regression models showed that the combined use of measures derived from discourse analysis and social ties predicted learning outcomes.

@en

Student engagement is often considered an overarching construct in educational research and practice. Though frequently employed in the learning analytics literature, engagement has been subjected to a variety of interpretations and there is little consensus regarding the very definition of the construct. This raises grave concerns with regards to construct validity: namely, do these varied metrics measure the same thing? To address such concerns, this paper proposes, quantifies, and validates a model of engagement which is both grounded in the theoretical literature and described by common metrics drawn from the field of learning analytics. To identify a latent variable structure in our data we used exploratory factor analysis and validated the derived model on a separate sub-sample of our data using confirmatory factor analysis. To analyze the associations between our latent variables and student outcomes, a structural equation model was fitted, and the validity of this model across different course settings was assessed using MIMIC modeling. Across different domains, the broad consistency of our model with the theoretical literature suggest a mechanism that may be used to inform both interventions and course design.

@en

In this paper, the transition from teaching on-campus to an online audience consisting of working professionals in an Aerospace Engineering context is described. The differences in the learner’s needs and the transition in teaching methods and style that is required from teaching staff is discussed. This is illustrated by two case studies: for Smart Structures and for Air Safety Investigation. Recommendations on how universities can contribute to Life Long Learning are given.@en

In the Interaction Equivalency Theorem (IET), Anderson proposed that students are likely to achieve different levels of satisfaction depending on the interaction intensity inside a course (student-student, student-content, or student-teacher interaction). Although higher interaction intensity could lead to a more satisfying learning experience, this may not be as cost- or time effective as less interactive learning sequences. However, the research done so far about the IET has not validated this thesis statement. Therefore, we aim to define a methodological research approach which would allow us to identify different types of interaction and its intensity inside Massive Open Online Courses (MOOCs), in order to confirm Anderson’s thesis. As MOOCs are by definition massive, i.e. many people enrol in them, they provide an opportunity for exploration of hypotheses that can prove to be more challenging to research in other environments, such as the IET. Furthermore, as virtually all student behaviour is recorded, measuring different types of interaction is easier and can be much more systematic, as the same approach can then be applied across myriads of online courses. Since it is challenging to determine what can be considered a high, medium or low level of interaction, we also aim to define an approach that will allow us to do that.@en

This paper explores the confidence starting first-year engineering students have in being successful in the first study year and which study-related behaviour they believe to be important to this end. Additionally, this paper studies which feedback these students would like to receive and compares it with the experiences of second-year students regarding feedback. To this end, two questionnaires were executed: one within three European higher education institutes with freshman engineering students and one with second-year engineering students in one institute. The results show that starting first-year engineering students are confident regarding their study success. This confidence is, however, higher than the observed first-year students’ success. Not surprisingly, the students have good intentions and believe that most academic activities are important for student success. When students look back on their first year, their beliefs in the importance of these activities have strongly decreased, especially for preparing classes and following communication through email and the virtual learning environment. First-year students expect feedback regarding their academic performance and engagement. They expect that this feedback primarily focuses on the impact of their future study pathway rather than on comparison to peer students. Second-year students indicate that the amount of feedback they receive could be improved, but agree with the first-year students that comparative feedback is less important. @en

Online education can be used as a catalyst for gaining knowledge on learning and learning processes due to its generation of massive corpora of data on student behaviour. This knowledge can then be utilized to improve the quality of education. Since 2013 the Delft University of Technology (TU Delft) Massive Open Online Courses (MOOC) programme has created and run over forty MOOCs, gaining more than one million enrolled students in the process. As TU Delft’s MOOC programme developed and expanded over time, an organisational structure was created in which educational processes and research activities were aligned and integrated. Through this integrated organisational structure, data is collected and analysed, which has resulted in a substantial number of evaluation reports, analyses, and academic papers. TU Delft has benefited from the insights from this combined output and has adapted to the findings both in online and on-campus course design. This way TU Delft’s MOOC programme provides a valuable environment for innovating educational design experience and developing new educational delivery strategies that can also be used to improve on-campus education.@en