23 February 2022 in School Psychology Review
Social and emotional learning (SEL) has been increasingly emphasized in educational research and practice for promoting children’s wellbeing. Perhaps the most well-known SEL framework is the model provided by the Collaborative for Academic, Social, and Emotional Learning (CASEL). This framework has become the dominant framework informing state SEL standards, which guide educators’ SEL related practice. Yet, the content of these standards has not been formally examined for alignment with the CASEL framework. The purpose of this exploratory study was to evaluate the content of CASEL-based state standards to explore how the CASEL framework is translated into school-based practice and to understand what SEL skills are valued by states. Using text mining and network analysis, we identified SEL standard content that was consistent across nine states and examined relationships within and across CASEL domains. Implications of these findings for research and practice are discussed. Impact Statement Social and emotional learning (SEL) practices have grown in prominence and utility in schools across grade levels. The CASEL framework is commonly used to inform SEL intervention, assessment, and, more recently, state standards. We evaluated the content of SEL state standards created using the CASEL framework to explore how states have implemented CASEL’s model. We describe how states’ interpretations of CASEL domains may inform further scientific grounding of SEL-focused research, policy, and practice.
28 October 2021 in Interactive Learning Environments
Participating in online communities has significant benefits to students learning in terms of students’ motivation, persistence, and learning outcomes. However, maintaining and supporting online learning communities is very challenging and requires tremendous work. Automatic support is desirable in this situation. The purpose of this work is to explore the use of deep learning algorithms for automatic text generation in providing emotional and community support for a massive online learning community, Scratch. Particularly, state-of-art deep learning language models GPT-2 and recurrent neural network (RNN) are trained using two million comments from the online learning community. We then conduct both a readability test and human evaluation on the automatically generated results for offering support to the online students. The results show that the GPT-2 language model can provide timely and human-written like replies in a style genuine to the data set and context for offering related support.
8 June 2022 in Journal of Educational Computing Research
Social-media-based teacher learning networks have the affordance to grant flexibility of time and space for teachers’ professional learning, support the development and sustainability of social networking, and meet their just-in-time needs for exchanging knowledge, negotiating meaning and accessing resources. However, most existing research on teacher online learning networks relies on qualitative methods and self-report data. There is a lack of study using quantitative methods to study large networks, especially using authentic data from social media. This work adds to the literature through mining teacher informal online learning networks using authentic data retrieved from Twitter. Specifically, we collected around half a million tweets and developed a network with the data. Then, various social network analysis techniques were utilized to explore the network structure and characteristics, participants’ behavioral patterns and how individuals connected with each other. We found that members of massive teacher informal online learning networks tended to communicate more with others of similar characteristics forming homogeneous communities, while hub participants connected many small communities which are significantly from one another, and hence, are the key to degree heterogeneity in a large network.
1 August 2021 in IEEE Transactions on Learning Technologies
Predictive modeling in online education is a popular topic in learning analytics research and practice. This study proposes a novel predictive modeling method to improve model transferability over time within the same course and across different courses. The research gaps addressed are limited evidence showing whether a predictive model built on historical data retrospectively can be directly applied to a future offering of the same course or to another different course; lacking interpretable data mining models to improve model transferability over time and across courses. Three datasets from two distinct online courses with one course offered two times over two years were applied using direct transferring of the predictive model and the proposed Bayesian updating technique for model transfer. The results showed that the direct transferring of predictive model to the subsequent offering of the course and to a totally different course did not work effectively. By contrast, the proposed Bayesian updating provided a robust and interpretable approach with improved model transferability results for both situations. This Bayesian updating model can be continuously updated with new collected data rather than building prediction model from scratch every time, which can serve as a new methodological framework to carry experience and knowledge from past and other courses forward to new courses.
22 February 2024 in Journal of Computer Assisted Learning
Background: Social annotation has emerged as a promising educational technology that fosters collaborative reading and discussion of digital resources among learners. While the positive impact of social annotation on students' learning process and performance is widely acknowledged, students' behavioural patterns in social annotation are underexplored.Objectives: This study investigated patterns in students' use of annotation and response behaviours in social annotation activities. We also explored how students' performance in the behavioural, cognitive, emotional, and social dimensions varied based on their behavioural patterns.Methods: We recruited 93 undergraduates who were enrolled in an elective course at a large North American University. Students were tasked with collaboratively annotating the class readings uploaded to Perusall, a social annotation platform, over 7 weeks. We used metaclustering to determine the optimal number of clusters pertaining to student behaviours. We compared the differences among clusters across multiple performance dimensions.Results and Conclusions: Two distinct clusters were identified and defined as initiators and responders. We found that responders had significantly longer active reading time and exhibited greater social annotation effort compared to initiators. However, initiators received more peer acknowledgement, as evidenced by higher upvotes. No significant difference was found in cognitive insight between initiators and responders, but responders demonstrated significantly higher cognitive discrepancy. Additionally, there were no significant differences in positive and negative tones between initiators and responders; however, responders displayed higher levels of prosocial behaviours than initiators. This study has significant practical implications regarding promoting students' collaborative learning experience in social annotation.