DeLFI - e-Learning Fachtagung Informatik

Permanent URI for this communityhttps://dl.gi.de/handle/20.500.12116/21008

Authors with most Documents  

Schroeder, Ulrik
66
Lucke, Ulrike
43
Zender, Raphael
23
Pinkwart, Niels
21
Striewe, Michael
20

Browse

Author: search.filters.author.Pinkwart, Niels

Search Results

1 - 10 of 21
  • Conference Paper
    Auto-generated language learning online courses using generative AI models like ChatGPT
    (Gesellschaft für Informatik e.V., 2023) Rüdian, Sylvio; Pinkwart, Niels; Röpke, René; Schroeder, Ulrik
    Generating online courses is always a trade-off between possibilities, technical limitations, and quality. State-of-the-art generative models can assist teachers in the creation process. However, generating learning materials is highly complex. Hence, teachers mainly create them manually. In this paper, learning content for a concrete micro-learning template is generated focusing on the field of language teaching. It intends that learners can find correct responses by logical thinking. Teachers provide a topic as input. Then, the approach asks for the required information using GPT3.5 with instructional prompts and combines responses to form a language learning unit. The quality of the resulting learning content, focusing on correctness, and appropriateness, is evaluated and discussed to examine the practicability of the tool, and alternatives are given.
  • Conference Paper
    Show me the numbers! - Student-facing Interventions in Adaptive Learning Environments for German Spelling
    (Gesellschaft für Informatik e.V., 2023) Rzepka, Nathalie; Simbeck, Katharina; Müller, Hans-Georg; Bültemann, Marlene; Pinkwart, Niels; Röpke, René; Schroeder, Ulrik
    Our work presents the result of an experiment conducted on an online platform for the acquisition of German spelling skills. We compared the traditional online learning platform to three different adap-tive versions of the platform that implement machine learning-based student-facing interventions that show the personalized solution probability. We evaluate the different interventions with regards to the error rate, the number of early dropouts, and the users’ competency. Our results show that the number of mistakes decreased in comparison to the control group. Additionally, an increasing num-ber of dropouts was found. We did not find any significant effects on the users’ competency. We conclude that student-facing adaptive learning environments are effective in improving a person’s error rate and should be chosen wisely to have a motivating impact.
  • Conference Paper
    Towards a Creativity Support Tool for Facilitating Students’ Creative Thinking on Writing Tasks
    (Gesellschaft für Informatik e.V., 2023) Krishnaraja, Swathi; Wambsganss, Thiemo; Mejia, Paola; Pinkwart, Niels; Röpke, René; Schroeder, Ulrik
    Creative thinking is one of the key skills of human intelligence that leads to the generation of valuable and novel ideas. It is also considered essential for developing students' capabilities and their cognition. While recent advances in artificial intelligence and machine learning technologies have been shown to promote critical thinking, learner interfaces that support the 'creative thinking' of students are scarce. In this work, we present a design system for facilitating students’ creative writing abilities. We follow a learner-centered design methodology, and evaluate the design system functionally, visually, and for accessibility, with a group of twelve students as representative users. The results show that designing alongside the target audience helps to rapidly identify user needs, individual preferences, and diverse viewpoints, and shows that the designed system performs better in all tested aspects including learner satisfaction, ownership, and self-efficacy.
  • Conference Paper
    Adaptive Learning as a Service – A concept to extend digital learning platforms?
    (Gesellschaft für Informatik e.V., 2022) Rzepka, Nathalie; Simbeck, Katharina; Müller, Hans-Georg; Pinkwart, Niels; Henning, Peter A.; Striewe, Michael; Wölfel, Matthias
    Adaptive learning environments that adjust to the individual user are promising. Unfortunately, many digital learning environments are not yet adaptive and the transformation of legacy software to an adaptive learning environment is complex and costly. Our work introduces the concept of adaptive learning as a service and discusses potential benefits as well as challenges.
  • Conference Paper
    The relation of convergent thinking and trace data in an online course
    (Gesellschaft für Informatik e.V., 2021) Rüdian, Sylvio; Haase, Jennifer; Pinkwart, Niels; Kienle, Andrea; Harrer, Andreas; Haake, Joerg M.; Lingnau, Andreas
    Many prediction tasks can be done based on users’ trace data. In this paper, we explored convergent thinking as a personality-related attribute and its relation to features gathered in interactive and non-interactive tasks of an online course. This is an under-utilized attribute that could be used for adapting online courses according to the creativity level to enhance the motivation of learners. Therefore, we used the logfile data of a 60 minutes Moodle course with N=128 learners, combined with the Remote Associates Test (RAT). We explored the trace data and found a weak correlation between interactive tasks and the RAT score, which was the highest considering the overall dataset. We trained a Random Forest Regressor to predict convergent thinking based on the trace data and analyzed the feature importance. The result has shown that the interactive tasks have the highest importance in prediction, but the accuracy is very low. We discuss the potential for personalizing online courses and address further steps to improve the applicability.
  • Conference Paper
    Zirkus Empathico 2.0' A serious mobile game for empathy enhancement in children with Autism
    (Gesellschaft für Informatik e.V., 2020) Hassan, Ahmed; Pinkwart, Niels; Zender, Raphael; Ifenthaler, Dirk; Leonhardt, Thiemo; Schumacher, Clara
    The aim of the mobile app ‘Zirkus Empathico 2.0’ is to improve emotional empathy and social competencies in Pre-school children with autism spectrum disorder (ASD). The holistic idea of grounding is based on genuine results of empathy research. An examination of the app exposed its good usability and comprehensibility. The application ‘Zirkus Empathico 2.0’ is scheduled to be thoroughly investigated in a longitudinal clinical dissect in children aged five to ten.
  • Conference Paper
    LAYA will in die Schule – Eine Anforderungsanalyse für den inklusiven, kollaborativen Einsatz einer Lernsoftware in der Sekundarstufe
    (Gesellschaft für Informatik e.V., 2020) Claus, Sebastian; Pinkwart, Niels; Zender, Raphael; Ifenthaler, Dirk; Leonhardt, Thiemo; Schumacher, Clara
    LAYA (Learn as you are!) wird bisher im Kontext der Erwachsenenbildung eingesetzt. Ziel dieses Posters ist es die Anforderungsanalyse für einen inklusiven, kollaborativen Einsatz in der Sekundarschule mit ersten Erkenntnissen darzustellen. Dem Tagungsmotto „Educational Realities“ wird durch dem gewählten Participatory Design-Ansatz und seinem Bezug zur Grounded Theory Methodology besonders Rechnung getragen.
  • Conference Paper
    Is the context-based Word2Vec representation useful to determine Question Words for Generators?
    (Gesellschaft für Informatik e.V., 2020) Rüdian, Sylvio; Pinkwart, Niels; Zender, Raphael; Ifenthaler, Dirk; Leonhardt, Thiemo; Schumacher, Clara
    Question and answer generation approaches focus on the quality and correctness of generated questions for online courses but miss to use a good question word, which is a deficiency reported by many previous studies. In this experimental setup, we explored whether the word2vec representation, which is semantic-based, can be used to predict question words. We compare two pipelines of the prediction process and observed that splitting the problem into several subproblems performs similar to feeding a neural network with all the data. Although our approach is promising to take the context-based representation into account we can see that the success rate is still low but better than guessing.
  • Conference Paper
    Automatic Feedback for Open Writing Tasks: Is this text appropriate for this lecture?
    (Gesellschaft für Informatik e.V., 2020) Rüdian, Sylvio; Quandt, Joachim; Hahn, Kathrin; Pinkwart, Niels; Zender, Raphael; Ifenthaler, Dirk; Leonhardt, Thiemo; Schumacher, Clara
    Giving feedback for open writing tasks in online language learning courses is time-consuming and expensive, as it requires manpower. Existing tools can support tutors in various ways, e.g. by finding mistakes. However, whether a submission is appropriate to what was taught in the course section still has to be rated by experienced tutors. In this paper, we explore what kind of submission meta-data from texts of an online course can be extracted and used to predict tutor ratings. Our approach is generalizable, scalable and works with every online language course where the language is supported by the tools that we use. We applied a threshold-based approach and trained a neural network to compare the results. Both methods achieve an accuracy of 70% in 10-fold cross-validation. This approach also identifies “fake” submissions from automatic translators to enable more fine-granular feedback. It does not replace tutors, but instead provides them with a rating based on objective metrics and other submissions. This helps to standardize ratings on a scale, which could otherwise vary due to subjective evaluations.
  • Conference Paper
    Educational Text Summarizer: Which sentences are worth asking for?
    (Gesellschaft für Informatik e.V., 2020) Rüdian, Sylvio; Heuts, Alexander; Pinkwart, Niels; Zender, Raphael; Ifenthaler, Dirk; Leonhardt, Thiemo; Schumacher, Clara
    Many question generation approaches focus on the generation process itself, but they work with single sentences as input only. Although the state of the art of question generation’s results is quite good, it cannot be used practically as the selection which sentences are worth asking for in an educational setting is currently not possible in an automated way. This limits the ability to generate interactive course materials at scale. In this paper, we conduct a study where we compare teachers’ sentence selections of texts with 9 algorithms to find the most appropriate ones concerning reading comprehension. 30 teachers compared the “winner” algorithm, Edmundson with LexRank, which was found to be the optimal algorithm according to previous literature. The result shows that Edmundson outperforms LexRank.