Paneth, Lisa
E-Mail-Adresse
Geburtsdatum
Suchergebnisse
Beyond words: investigating non-verbal indicators of collaborative engagement in a virtual synchronous CSCL environment
In the future of higher education, student learning will become more virtual and group-oriented, and this new reality of academic learning comes with challenges. Positive social interactions in virtual synchronous student learning groups are not self-evident but need extra support. To successfully support positive social interactions, the underlying group processes, such as collaborative group engagement, need to be understood in detail, and the important question arises: How can collaborative group engagement be assessed in virtual group learning settings? A promising methodological approach is the observation of students’ non-verbal behavior, for example, in videoconferences. In an exploratory field study, we observed the non-verbal behavior of psychology students in small virtual synchronous learning groups solving a complex problem via videoconferencing. The groups were videorecorded to analyze possible relations between their non-verbal behaviors and to rate the quality of collaborative group engagement
Trend Monitoring & Erarbeitung fundierter Entscheidungsgrundlagen für die Entwicklung von FHNW Learning Spaces
A multi-method approach to capture quality of collaborative group engagement
Multi-method approaches are an emerging trend in CSCL research as they allow to paint a more comprehensive picture of complex group learning processes than using a single method. In this contribution, we combined measures from different data sources to capture the quality of collaborative group engagement (QCGE) in CSCL-groups: QCGE-self-assessments, QCGE-ratings of verbal group communication, and video recorded nonverbal group behaviors. Using different methods of analysis, we visualized, described, and analyzed the data and related the measures to each other. Here, we present results suggesting that measures from different data sources are interrelated: For instance, nonverbal behavior (like nodding the head) is related to high QCGE-ratings of verbal communications. Results are preliminary and show disparities, too. Yet, we conclude that the multi-method approach results in a more comprehensive understanding of QCGE. Feasibility and suitability of the multi-method approach are discussed and conclusions for future research are drawn.
Exploring nonverbal behavior and collaborative group engagement in online learning groups
In learning groups, nonverbal behavior provides important information about socio-emotional processes, emotional states, and social relationships (Burgoon & Dunbar, 2018), and is therefore of utmost interest for the study of learning processes and group engagement - especially in online scenarios, where certain social cues are missing (cf. Trepte & Reinecke, 2018). The explorative study presented here addressed nonverbal behaviors of students as an indicator for the quality of collaborative group engagement (Sinha et al., 2015) in online learning groups. N=7 student groups were tasked with solving a hidden profile assignment via Zoom video conference. A code system was developed to capture students’ gestures and facial expressions and to analyze and explore them in terms of collaborative group engagement. Data analysis is currently underway. Preliminary results indicate that the frequency of nonverbal behaviors differs between groups and also between different types of nonverbal behavior (e.g., smiling, or braced chin). As a next step, this study will explore what these findings tell us about the differences and the synchronicity of nonverbal behaviors in relation to collaborative group engagement and how they relate to students’ verbal communication. The results of this study will contribute to the development of a system for assessing quality of collaborative group engagement and serve as a basis for real-time feedback to foster collaborative group engagement.
A Multi-Method Approach to Capture Quality of Collaborative Group Engagement
Multi-method approaches are an emerging trend in CSCL research as they allow to paint a more comprehensive picture of complex group learning processes than using a single method. In this contribution, we combined measures from different data sources to capture the quality of collaborative group engagement (QCGE) in CSCL-groups: QCGE-self-assessments, QCGE-ratings of verbal group communication, and video recorded nonverbal group behaviors. Using different methods of analysis, we visualized, described, and analyzed the data and related the measures to each other. Here, we present results suggesting that measures from different data sources are interrelated: For instance, nonverbal behavior (like nodding the head) is related to high QCGE-ratings of verbal communications. Results are preliminary and show disparities, too. Yet, we conclude that the multi-method approach results in a more comprehensive understanding of QCGE. Feasibility and suitability of the multi-method approach are discussed and conclusions for future research are drawn.
Exploring linguistic indicators of social collaborative group engagement
This study takes a NLP approach to measuring social engagement in CSCL-learning groups. Specifically, we develop linguistic markers to capture aspects of social engagement, namely sentiment, responsiveness and uniformity of participation and compare them to human ratings of social engagement. We observed small to moderate links between NLP-markers and human ratings that varied in size and direction across the different groups. We discuss measurement and prediction of social collaborative group engagement using natural language processing.
Predicting engagement in computer-supported collaborative learning groups using natural language processing
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.