Computer‐supported collaborative learning (CSCL) has been an effective pedagogy in the field of education. However, productive collaborative learning often does not occur spontaneously, and learners often have difficulties with collaborative knowledge building and socially shared regulation. To address this research gap, this study proposes an automatic knowledge graph construction approach based on deep neural network models. In total, 63 groups comprising 189 college students participated in this study and were assigned to three conditions, namely, the automatic activated and unactivated knowledge graph (AAUKG) condition, the automated activated knowledge graph (AAKG) condition, and the traditional online collaborative learning (TOCL) condition. The findings revealed that the AAUKG approach had more significant and positive impacts on collaborative knowledge building, group performance, social interaction, and socially shared regulation than the AAKG and TOCL approaches. This study provides substantial evidence of utilising both automatically activated and unactivated knowledge graphs to improve collaborative learning performance.
What is already known about this topic
Knowledge graphs have been widely used in many fields for searches, recommendations, analytics, and automation.
Researchers have explored how to construct knowledge graphs. However, few studies have automatically constructed knowledge graphs in the CSCL context.
What this paper adds
An automatic knowledge graph construction approach is proposed and validated in the CSCL context.
The findings indicate that the AAUKG approach has more significant and positive impacts on collaborative knowledge building, group performance, social interaction, and socially shared regulation than the AAKG and TOCL approaches.
Implications for practice and/or policy
The AAUKG approach is an effective method for improving knowledge building and group performance in the CSCL context.
Researchers and practitioners are encouraged to consider how knowledge graphs can be applied to facilitate collaborative learning efficiently.
Alcohol dependence (AD) is characterized by compulsive alcohol consumption, which involves behavioral impairments such as aggression. Members of fibroblast growth factor (FGF) 19 superfamily, including FGF19, FGF21, and FGF23, are major endocrine mediators that play an important role in alcohol metabolism and alcohol related disorders. The objective of the present study is to explore the possible associations among the interaction of single nucleotide polymorphisms (SNPs) of the FGF 19 superfamily, AD occurrence, and aggression in patients with AD. A total of 956 subjects were enrolled in this study, including 482 AD patients and 474 healthy controls (HCs). Michigan alcoholism screening test (MAST) was used to measure the level of AD, a Chinese version of the Buss–Perry Aggression Questionnaire was used to evaluate the aggressive behavior of subjects, and MassARRAY@ system was used to genotype rs948992 of FGF19, rs11665841 and rs11665896 of FGF21, rs7955866 and rs11063118 of FGF23. The results showed that AD patients presented a significantly higher level of aggression compared to HCs, and MAST scores were significantly positively associated Buss–Perry aggression scores (r = 0.402, p < 0.001) in AD patients. The interaction of FGF19 rs948992 TC × FGF21 rs11665896 GG presented the high-risk genotype combination predicting the high level of AD. In addition, the interaction of FGF19 rs948992 TC × FGF21 rs11665896 TG × FGF23 rs11063118 TT presented the high-risk genotype combination predicting the high level of aggression in AD patients. Our results added evidence linking the combination of rs948992 TC × rs11665896 TG × rs11063118 TT to aggressive behavior in AD patients and pointed out the potential usefulness of the SNPs of FGF19 superfamily as a predictor for the aggression in AD patients.
Online collaborative learning (OCL) has been a mainstream pedagogy in the field of higher education. However, learners often produce off-topic information and engage less during online collaborative learning compared to other approaches. In addition, learners often cannot converge in knowledge, and they often do not know how to coregulate with peers. To cope with these problems, this study proposed an immediate analysis of interaction topics (IAIT) approach through deep learning technologies. The purpose of this study is to examine the effects of the IAIT approach on group performance, knowledge convergence, coregulation, and cognitive engagement in online collaborative learning. In total, 60 undergraduate students participated in this quasi-experimental study. They were assigned to either the experimental or the control groups. The students in the experimental groups conducted online collaborative learning with the IAIT approach, and the students in the control groups conducted online collaborative learning only without any particular approach. The whole study lasted for three months. Both qualitative and quantitative methods were adopted to analyze data. The results indicated that the IAIT approach significantly promoted group performance, knowledge convergence, coregulated behaviors, and cognitive engagement. The IAIT approach did not increase learners’ cognitive load. The results, together with the implications for teachers, practitioners and researchers, are also discussed in depth.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.