An automated analysis of topic distributions and features approach to promoting group performance, collaborative knowledge building and socially shared regulation in online collaborative learning
{"title":"An automated analysis of topic distributions and features approach to promoting group performance, collaborative knowledge building and socially shared regulation in online collaborative learning","authors":"Lanqin Zheng, Lu Zhong, Yunchao Fan","doi":"10.14742/ajet.7995","DOIUrl":null,"url":null,"abstract":"Online collaborative learning has been widely used in the field of education. However, unrelated or off-topic information is often included in online collaborative learning. Furthermore, the content of online discussion is often too shallow or narrow. To achieve productive collaborative learning, this study proposed and validated an automated analysis of topic distributions and features (AATDF) approach. In total, 189 college students in China participated in this study and were assigned to one of two experimental groups or a control group. Experimental Group 1 participated in online collaborative learning with the AATDF approach. Experimental Group 2 participated in online collaborative learning with the automated analysis of topic distributions (AATD) approach. The control group participated in traditional online collaborative learning without any specified approach. The results indicate that the AATDF approach can significantly promote group performance, collaborative knowledge building and socially shared regulation compared with the AATD and traditional online collaborative learning approaches. The results and implications are also discussed in depth. The main contribution of this study is that the AATDF approach can improve learning performance and bring online collaborative learning onto new ground. Implications for practice: The AATDF approach is very useful and effective for promoting group performance, collaborative knowledge building and socially shared regulation. Teachers and practitioners can provide personalised interventions and optimise collaborative learning design based on the analysis results of topic distributions and features. Developers can adopt deep neural network models to develop intelligent online","PeriodicalId":47812,"journal":{"name":"Australasian Journal of Educational Technology","volume":"33 1","pages":"0"},"PeriodicalIF":3.3000,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Australasian Journal of Educational Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14742/ajet.7995","RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}
引用次数: 0
Abstract
Online collaborative learning has been widely used in the field of education. However, unrelated or off-topic information is often included in online collaborative learning. Furthermore, the content of online discussion is often too shallow or narrow. To achieve productive collaborative learning, this study proposed and validated an automated analysis of topic distributions and features (AATDF) approach. In total, 189 college students in China participated in this study and were assigned to one of two experimental groups or a control group. Experimental Group 1 participated in online collaborative learning with the AATDF approach. Experimental Group 2 participated in online collaborative learning with the automated analysis of topic distributions (AATD) approach. The control group participated in traditional online collaborative learning without any specified approach. The results indicate that the AATDF approach can significantly promote group performance, collaborative knowledge building and socially shared regulation compared with the AATD and traditional online collaborative learning approaches. The results and implications are also discussed in depth. The main contribution of this study is that the AATDF approach can improve learning performance and bring online collaborative learning onto new ground. Implications for practice: The AATDF approach is very useful and effective for promoting group performance, collaborative knowledge building and socially shared regulation. Teachers and practitioners can provide personalised interventions and optimise collaborative learning design based on the analysis results of topic distributions and features. Developers can adopt deep neural network models to develop intelligent online