2024-03-20, Jeitziner, Loris Tizian, Paneth, Lisa, Rack, Oliver, Zahn, Carmen, Wulff, Dirk

Collaborative group engagement is a key factor of success in learning groups. This work explores the development of an innovative natural language processing method for predicting collaborative group engagement. To this end, we identified linguistic markers based on an established observation-based scheme for rating collaborative group engagement, such as, semantic similarity to task instructions, verbal mimicry, sentiment, and use of jargon. We evaluated the predictive power of the linguistic markers on the data of an observational study in which 38 learning groups were instructed to perform a collaborative learning task. Overall, the data consisted of 2588 expert ratings on collaborative group engagement. We relied on machine learning to the predict collaborative group engagement ratings using informative subsets of linguistic markers. The results showed above-baseline predictive accuracy for all four dimensions of collaborative group engagement. Moreover, the analysis of feature importance points to quantity of utterances, responsiveness and uniformity of participation as the most important markers for collaborative group engagement. By harnessing natural language processing, this work extends traditional qualitative analysis and delivers nuanced quantitative metrics suitable for capturing the complexity and dynamics of contemporary Computer Supported Collaborative Learning (CSCL) environments. Thereby, it contributes to the evolving landscape of CSCL research and demonstrates the potential of novel analytic techniques to support and enrich qualitative analysis in multiple domains.

2023-01-20, Paneth, Lisa, Rack, Oliver, Zahn, Carmen

2022-06, Jeitziner, Loris Tizian, Roos, Anna-Lena, Ruf, Alessia, Zahn, Carmen

The pandemic has forced higher education to shift from onsite to online environments. This novel situation may increase students’ exam stress and induce new stressors. In the present study, we identified stressors in online exams by conducting an exploratory factor analysis of a novel questionnaire. The analysis revealed five factors that categorize students’ experience of stress. Preliminary descriptive results suggest that possible system failures and social pressures cause the highest stress for students.

2021, Ruf, Alessia, Jäger, Joscha, Niederhauser, Mario, Zahn, Carmen, Opwis, Klaus, Wichmann, Astrid, Hoppe, H. Ulrich, Rummel, Nikol

Logible is a highly sensitive web-based interactive tool that automatically detects behavior sequences from raw log files. It further analyzes and visualizes sequences and allows for comparisons of behavior data between different experimental conditions without the use of other software. Logible was developed based on an iterative, exploratory, and rule-based method devised to find meaningful sequences from 92 data sets of students who learned individually or collaboratively with an enhanced video-based environment. The tool is customizable and thus enables researchers to investigate learning behavior with various kinds of sequentially logged interaction data (from web-based video environments, online learning platforms etc.).

2023-12-31, Jeitziner, Loris Tizian, Frick, Andrea, Paneth, Lisa, Zahn, Carmen

2022-11-17, Schwaninger, Adrian, Sterchi, Yanik, Wäfler, Toni, Renggli, Philipp, Rack, Oliver, Bleisch, Susanne, Paneth, Lisa, Jeitziner, Loris Tizian, Gasparik, Matus, Zahn, Carmen

2021-01-28, Zahn, Carmen, Paneth, Lisa

2023-06, Roos, Anna-Lena, Jeitziner, Loris Tizian, Zahn, Carmen

2022-07-22, Rack, Oliver, Paneth, Lisa, Jeitziner, Loris Tizian, Zahn, Carmen

In an explorative field study, we investigated nonverbal behavior and collaborative group engagement (QCGE) in online learning groups. Participants in small groups performed a hidden profile task. Results suggests differences within and between groups in their nonverbal behavior. We expect that nonverbal behaviors relate to QCGE in online learning groups.

2021, Ruf, Alessia, Leisner, David, Zahn, Carmen, Opwis, Klaus, Hmelo-Silver, Cindy, de Wever, Bram, Oshima, Jun

Enhanced video-based learning environments provide new tools (e.g., hyperlinks) – along with the well-known basic video control tools (e.g., play, pause, rewind) – that afford learners‘ enhanced interaction with videos. With these tools, learners can actively transform existing videos into their own hypervideo structures by adding hyperlinks and own materials. Unlike research on basic control tools that has revealed positive impacts on learning, research on enhanced tools is still rare and conflicting. It is thus open, whether the tools support generative interested learning or put too much extrinsic cognitive load onto learners. In the present study, we investigated the effects of video annotation and hyperlinking tools on learning success and cognitive load by analyzing tool-related interaction behavior data of 141 university students. Results indicated that the frequent use of enhanced video tools positively predicted learning success and a decrease in cognitive load. Implications of these results are discussed.