Logo des Repositoriums

Auflistung nach Schlagwort "learning analytics"

1 - 10 von 14
  • Konferenzbeitrag
    Automated feedback on teamwork in programming courses
    (20. Fachtagung Bildungstechnologien (DELFI), 2022) Karl,Maximilian; Zender, Raphael
    In programming courses students might work asynchronous in a team to solve tasks from the tutor. A version control system (VCS) is commonly used by programming teams and the currently most popular VCS is Git. GitHub and GitLab are tools which are based on Git and supply additional features for teams to support their teamwork. This poster shows characteristics of collaborative teams and how they are reflected in GitHub and GitLab issue history. A learning analytics algorithm can analyse the issue history of GitHub or GitLab to distinguish teams by their teamwork and give an individual feedback for each team and team member. The feedback should encourage the team members to work more collaborative and use different features of GitHub or GitLab. The goal of the poster is to illustrate the possibilities of an automated feedback to enhance the teamwork of student teams which are using a VCS for their coding tasks.
  • Konferenzbeitrag
    Data Leakage Through Click Data in Virtual Learning Environments
    (20. Fachtagung Bildungstechnologien (DELFI), 2022) Hartmann, Johanna; Heuer, Hendrik; Breiter, Andreas
    Unsupervised machine learning techniques are increasingly used to cluster students based on their activity in virtual learning environments. It is commonly assumed that clusters formed by click data merely represent the actions of users and do not allow inferring personal information about individual users. Based on an analysis of 18,660 students and 5.56 million data points from the Open University Learning Analytics Dataset, we show that clusters trained on "raw" click data are highly correlated with personal information like student success, course specifics, and student demographics. Our analysis demonstrates that these clusters allow conclusions about demographic variables like the previous education and the affluence of the residential area. Our investigation shows that apparently, objective click data can leak private attributes. The paper discusses the implications of this for the design of virtual learning environments, especially considering the legal requirements posed by the principle of data minimization of the EU GDPR.
  • Konferenzbeitrag
    A Decision Tree Approach for the Classification of Mistakes of Students Learning SQL, a case study about SELECT statements
    (DELFI 2020 – Die 18. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V., 2020) Faeskorn-Woyke, Heide; Bertelsmeier, Birgit; Strohschein, Jan
    TH Köln provides a web-based e-learning platform edb4, where novices can do their first steps in SQL. The goal of this paper is to build a decision tree (manually) that classifies the novice's errors. To do so we logged data containing tasks, solutions, and wrong statements over seven months and got a table with 7533 rows as a training set. Each leaf node of the decision tree is a class of errors of similar type and generates an error message with feedback to help the user to solve the task. Interesting and surprising are the mistakes that SQL novices make. The result improves the first steps of learning SQL in a simple and personalized way and gives the teachers hints to improve their learning outputs.
  • Konferenzbeitrag
    Interaction of reading and assessment behavior
    (20. Fachtagung Bildungstechnologien (DELFI), 2022) Menze, Dennis; Seidel, Niels; Kasakowskij, Regina
    Reading and assessment are elementary activities for knowledge acquisition in online learning. Assessments represented as quizzes can help learners to identify gaps in their knowledge and understanding, which they can then overcome by reading the corresponding text-based course material. Reversely, quizzes can be used to evaluate reading comprehension. In this paper, we examine the interactions between reading and quiz activities using scroll and log data from an online undergraduate course (N=142). By analyzing processes and sequential patterns in user sessions, we identified six session clusters for characteristic reading and quiz patterns potentially relevant for adaptive learning support. Using these session clusters, we further clustered students by their reading and quiz behavior over six time periods within the semester. The results hypothesize a personalization for seven groups of learners characterized by their temporal activity and predominant quiz and reading behavior.
  • Textdokument
    Learning Analytics in Academic Writing Instruction – Opportunities Provided by Thesis Writer (TW)
    (Bildungsräume 2017, 2017) Rapp, Christian; Ott, Jakob
    No thesis - no graduation. Academic writing poses manifold challenges to students, instructors and institutions. Consequently, the question arose to what extent academic writing instruction can be supported electronically. With Thesis Writer (TW), a domain-specific, technology-supported learning environment for scaffolding academic writing, combined with an online editor optimised for producing academic text was implemented. Recently, a tracking function was also implemented that allows for fine-grained studying of user interaction with the system, and therefore also their writing and learning processes. In the demonstration, the researchers will present the data types collected, the tracking technology, and the learning analytics opportunities that TW provides.
  • Konferenz-Abstract
    Learning analytics in the age of AI: Will we see the promised learning revolution?
    (21. Fachtagung Bildungstechnologien (DELFI), 2023) Poquet, Oleksandra
    Current advances in generative AI represent a paradigm shift for educational technology. Affordances of generative AI change our perceptions of what can be possible, prompting to re-evaluate research questions, interventions, and applications in the field of educational technology. Against this backdrop, what should the focus on using data to inform teaching and learning look like? Learning analytics, an applied domain centred on data about learners, their processes, and learning artefacts, has gained traction over the last decade. The talk will take a historical perspective to position learning analytics within existing educational technology paradigms and discuss it within the context of AI, highlighting the adjacent possible for the future development.
  • Konferenzbeitrag
    Learning with ALeA: Tailored experiences through annotated course material
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Kruse, Theresa; Berges, Marc; Betzendahl, Jonas; Kohlhase, Michael; Lohr, Dominic; Müller, Dennis
    We present ALeA, an adaptive learning assistant for university courses. The intelligent tutoring system (ITS) provides services for both learners and instructors, based on semantically annotated course material. The system can generate learning tools like flashcards, guided tours, and quizzes, which can be tailored to individual learning progress. Currently, the system is only available for courses from the field of computer science, like artificial intelligence. We plan to expand it for further courses from different fields.
  • Textdokument
    Mediengestaltung und -einbettung in Moodle zur Vorbereitung von Learning Analytics auf Modulebene
    (Bildungsräume 2017, 2017) Leuchter,  Sandro
    keiner
  • Konferenzbeitrag
    Prototyping a Virtual Tutor with Modular Teaching Styles
    (21. Fachtagung Bildungstechnologien (DELFI), 2023) Linxen, Andrea; Opel, Simone; Ebbing, Stephanie; Beecks, Christian
    Digitization and artificial intelligence (AI) have entered education in several different ways. While the current development of large language models enables students to access vast knowledge, virtual tutors offer a more tailored approach and better support for time-independent and individualized learning. As several AI systems have become more common in higher education, we developed a concept to implement a virtual tutor with different teaching styles, using the conversational AI plat-form Rasa. This tutor teaches students basic Exploratory Data Analysis in linear, free, and modular learning phases. In the future, we will conduct comprehensive studies to determine the ability of the virtual tutor to support successful learning.
  • Konferenzbeitrag
    Scalable Interventions in Higher Education: An AI-Supported Feedback Tool to ASSIST Self-Reflection
    (Workshops der 21. Fachtagung Bildungstechnologien (DELFI), 2023) Rumert, Luis; Berens, Johannes; Gößl, Thomas; Henao, Leandro; Salamon, Moritz; Schneider, Kerstin
    ASSIST is an intelligent feedback portal for smartphones that helps students monitor their academic progress and predict their likelihood of success. It allows students to reflect on their current situation and explore individualized study scenarios.