作者机构：
[Liu, Qingtang; Zhang, Si] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.;[Wen, Yun] Nanyang Technol Univ, Natl Inst Educ, Singapore, Singapore.
通讯机构：
[Zhang, Si] C;Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.
关键词：
Collaborative learning;social knowledge construction behavior;teacher education;collective agency
摘要：
The potential of online collaborative learning has been recognized in teacher education, and the value student teachers’ collective agency in predict their sustainable professional develop has been discussed. However, there is limited understanding of how student teachers’ collaborative knowledge construction behaviors correlate with their collective agency. This study investigated one class of student teachers’ collaborative knowledge construction behavioral pattern in a multi-layered interaction activity, and further explained their correlation with the participants’ collective agency. A total of 50 third-year student teachers from a class of a university in central China participated in the study. The results suggested that in terms of the average density, both intragroup and intergroup interaction networks were high-density ones. However, the number of interactions within each group was uneven. The student teachers had different reciprocity in intragroup and intergroup discussions. Their social knowledge construction behavioral patterns showed different characteristics in different stages of the multi-layered interaction activity. The questionnaire survey and interview data further revealed that though the student teachers built up collaborative learning awareness to some extent, their collective agency still has space to be improved. The authors conclude with some insights into the online collaborative learning in sustainable teachers’ professional development.
摘要：
Lesson study (LS) is an effective means of improving teachers' facility with teaching design. This research designs a case study of online to offline (O2O) LS and explores the social interaction and behaviour patterns in the process of the LS. The participants included 29 chemistry teachers from 10 secondary schools and two educational technology experts from a university in western China, who participated in the O2O LS, with Chemistry Teaching Design based on Augmented Reality (AR): Molecules and Atoms as its topic. Through social network analysis (SNA) and lag sequence analysis (LSA), the findings of this case study indicate that: (1) in the LS process, the two co-hosts played their due roles well, while different teachers played strong guiding and controlling roles in different discussion phases, and (2) in different discussion phases, the behaviour sequence of teachers' knowledge construction presented different characteristics in that high-level knowledge construction took place among teachers in the later phases under the leadership of the host. This study will aid in the design and implementation of O2O LS and the description of interactive characteristics in teachers' collaborative learning so as to provide reference for using teacher training process data and improving teachers' professional abilities.
摘要：
Despite the continuous emphasis on emotion in multimedia learning, it was still unclear how pedagogical agent emotional cues might affect learning. In the present study, a between-subjects experiment was performed to examine the effects of a pedagogical agent with dual-channel emotional cues on learners' emotions, cognitive load, and knowledge transfer performance. Participants from a central Chinese university (age mean = 21.26, N = 66) were randomly divided into three groups. These groups received instructions from an affective pedagogical agent, a neutral pedagogical agent, or a neutral voice narration without pedagogical agent embodiment. Results showed that learners assigned the affective pedagogical agent reported a significantly higher emotional level than learners assigned the neutral pedagogical agent. Learners’ perceived task difficulty was not significantly different among groups while instructional efficiency was significantly higher for learners with the affective pedagogical agent. Moreover, learners assigned to the affective pedagogical agent performed significantly better on the knowledge transfer test than those assigned the neutral pedagogical agent or the neutral voice.
作者机构：
School of Information Technology in Education, South China Normal University, Guangzhou 510631, China;School of Educational Information Technology, Central China Normal University, Wuhan 430079, China;Authors to whom correspondence should be addressed.
关键词：
comma disambiguation;feature engineering;hyperparameter tuning;imbalanced learning;natural language understanding;random forests
摘要：
Natural language understanding technologies play an essential role in automatically solving math word problems. In the process of machine understanding Chinese math word problems, comma disambiguation, which is associated with a class imbalance binary learning problem, is addressed as a valuable instrument to transform the problem statement of math word problems into structured representation. Aiming to resolve this problem, we employed the synthetic minority oversampling technique (SMOTE) and random forests to comma classification after their hyperparameters were jointly optimized. We propose a strict measure to evaluate the performance of deployed comma classification models on comma disambiguation in math word problems. To verify the effectiveness of random forest classifiers with SMOTE on comma disambiguation, we conducted two-stage experiments on two datasets with a collection of evaluation measures. Experimental results showed that random forest classifiers were significantly superior to baseline methods in Chinese comma disambiguation. The SMOTE algorithm with optimized hyperparameter settings based on the categorical distribution of different datasets is preferable, instead of with its default values. For practitioners, we suggest that hyperparameters of a classification models be optimized again after parameter settings of SMOTE have been changed.
期刊：
Journal of Educational Computing Research,2021年59(7):1319-1342 ISSN：0735-6331
通讯作者：
Wu, Linjing;Liu, Qingtang
作者机构：
[Wu, Linjing; Liu, Qingtang; Li, Jing; Yang, Weiqing; He, Liming; Zhang, Yaosheng] Cent China Normal Univ, Sch Educ Informat Technol, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.;[Liu, Qingtang] Cent China Normal Univ, Hubei Res Ctr Educ Informationizat, Wuhan, Hubei, Peoples R China.;[Cheng, Yun] Huang Gang Normal Univ, Sch Educ, Huanggang, Hubei, Peoples R China.
通讯机构：
[Wu, LJ; Liu, QT] C;Cent China Normal Univ, Sch Educ Informat Technol, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
关键词：
collaborative knowledge building;knowledge contribution;information theory;amount of information;information gain
摘要：
The measurement of knowledge contribution in collaborative knowledge building is an important research topic in computer-supported collaborative learning. The information measures of knowledge contribution based on information theory are proposed in this study, which includes two measures: amount of information and information gain. Discourse data collected from a collaborative knowledge building activity were analyzed to validate these measures. The results showed that our information measures can complement the traditional behavioral. With the help of the two measures, community-level variation tendency and individual-level knowledge contribution characteristics could be analyzed in collaborative knowledge building activities. A log function was used to fit the community knowledge variation tendency to measure the convergence of knowledge building. Students were clustered into five types according to their behaviors and contributions in collaborative knowledge building. Both teachers and researchers can benefit from these two information measures by using them in practice.
期刊：
Technology, Knowledge and Learning,2020年25(4):811-833 ISSN：2211-1662
通讯作者：
Linjing Wu
作者机构：
[Linjing Wu; Qingtang Liu; Gang Mao; Jingxiu Huang] School of Educational Information Technology, Central China Normal University, Wuhan, China;[Wanlei Zhou] School of Information Technology, Deakin University, Melbourne, Australia;[Huan Huang] School of Education, South-Central University for Nationalities, Wuhan, China
通讯机构：
[Linjing Wu] S;School of Educational Information Technology, Central China Normal University, Wuhan, China
摘要：
A big challenge in educational resources construction is the intelligent and personalized resource recommendation for learners. This paper proposes a semantic recommendation framework of educational resources based on semantic web and pedagogics. In this framework, a domain ontology is constructed to describe the knowledge structure of the domain. All the resources and user portfolio are described with ontology technology and resource description framework to support semantic inference. Based on the semantic resource organization, we made a set of reasoning rules based on pedagogics. These rules are made from the synthesis of the type of the knowledge, the internal structure of knowledge and learner’s learning performance. A case study was implemented on the course “theory and practice of database”. In this case, learners are recommended different learning materials according to the different knowledge structure and different learning performance. Three typical learning modes are proposed to describe the personalized learning experience. This framework can be used as a guide for teachers and resource designers.
摘要：
This study analysed the instructors' teaching presence of three courses conducted by an instructor to explore the effects of the instructors' online teaching presence on students' interactions and collaborative knowledge constructions. Content analysis, social network analysis, and lag sequential analysis were used to explore the mechanism of teaching presence on students' interactions and collaborative knowledge construction. Results demonstrate that the design and organization, as well as facilitating discourse, can facilitate students' interaction, reduce the number of peripheral students, and facilitate students' collaborative knowledge construction, especially in the knowledge sharing, discovery, discussion, and application, whereas direct instruction has positive effects on teachers' centrality and negative effects on knowledge negotiation and testing. The result can give the instructors some guidance on online teaching practices.
作者：
Ni Zhang;Qingtang Liu;Jiaojiao Zhu;Qiyun Wang;Kui Xie
期刊：
Technology, Knowledge and Learning,2020年25(2):323-336 ISSN：2211-1662
通讯作者：
Zhang, N.
作者机构：
[Ni Zhang; Qingtang Liu; Jiaojiao Zhu] School of Educational Information Technology, Central China Normal University, Wuhan, China;[Qiyun Wang] National Institute of Education, Nanyang Technological University, 50 Nanyang Avenue, Singapore;[Kui Xie] Department of Educational Studies, The Ohio State University, Columbus, USA
通讯机构：
School of Educational Information Technology, Central China Normal University, 152 Luoyu Road, Wuhan, China
摘要：
Teacher workshops attract teachers with common goals; they wish to improve their teaching practices and subject and information technology knowledge. The asynchronous online discussion is the main activity in teacher workshops. An analytical model was developed in this study to examine the temporal characteristics of collaborative knowledge construction in teacher workshops. Specifically, 664 posts were analyzed from an asynchronous online discussion—involving 91 teachers—on the topic, “How to Make a Language Course Interesting?” The aim of this paper is to present the changes in knowledge construction levels and teachers’ social interactive characteristics resulting from participation in teacher workshops. From the findings of this study, advances in theory, methodology and pedagogical practice are indicated. The findings also indicate that knowledge construction levels and teachers’ social interactive characteristics change at different stages of discussions. Suggestions for improving the effects of online teacher workshops are provided.
摘要：
Metacognition is important in self-regulated learning and understanding its epistemic network can improve teaching and learning. We collected self-reported metacognition reflections on collaborative learning activities from 87 college students to analyze how students' metacognitive patterns differ by performance level and discipline type. We used an epistemic network analysis to identify these differences, and the results indicated that description of goals appeared most in self-reported reflections. There are variations in metacognitive patterns between different groups. High-score students had stronger connections around actions, while low-score students had stronger connections between metacognitive knowledge and context. The natural science students focused more on metacognitive knowledge and actions, while the humanities science students focused more on metacognitive experience and context. This implies that teachers should provide clear explanations about the collaborative learning goal, and a group strategy that takes both performance and discipline types into consideration could address the variation in metacognitive patterns.
