Investigating Collaboration as a Process with Theory-driven Learning Analytics

Kent, Carmel; Cukurova, Mutlu

doi:10.18608/jla.2020.71.5

Cited by 24 publications

(22 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CSCL is a complex knowledge construction process based on social interaction (Saqr et al., 2020). However, most studies in the area have focused exclusively on learning outcomes rather than considering collaborative learning processes (Kent & Cukurova, 2020).…”

Section: Introductionmentioning

confidence: 99%

Effects of a learning analytics‐based real‐time feedback approach on knowledge elaboration, knowledge convergence, interactive relationships and group performance in CSCL

Zheng

Niu

Zhong

2021

Brit J Educational Tech

View full text Add to dashboard Cite

Learning analytics (LA) has been widely adopted in research on education. However, most studies in the area have conducted LA after computer‐supported collaborative learning (CSCL) activities rather than during CSCL. To address this problem, this study proposed a LA‐based real‐time feedback approach based on a deep neural network model to improve CSCL performance. In total, 72 university students participated in the study and were randomly assigned to an experimental or control group. The students in the experimental group learned with the LA‐based real‐time feedback approach, whereas the students in the control group learned with the conventional online collaborative learning approach. To analyse the data, both quantitative and qualitative methods were adopted. The results indicated that the LA‐based real‐time feedback approach significantly promoted knowledge convergence, knowledge elaboration, interactive relationships and group performance. The interview results also confirmed the effectiveness of the proposed approach. What is already known regarding this topic Learning analytics (LA) has been widely used in education. Most studies in the area have presented LA results only after collaborative learning and have lacked real‐time analysis and feedback. What this paper adds A LA‐based real‐time feedback approach was proposed and validated in the computer‐supported collaborative learning (CSCL) context. The experimental results indicated that the LA‐based real‐time feedback approach significantly promoted knowledge elaboration, knowledge convergence, interactive relationships and group performance. Implications for practice and/or policy To shed light on progress in CSCL, real‐time LA are recommended. Deep neural network models, such as bidirectional encoder representations from transformers, can be adopted to automatically analyse online discussion transcripts. Real‐time feedback based on LA results can promote CSCL performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Effects of a learning analytics‐based real‐time feedback approach on knowledge elaboration, knowledge convergence, interactive relationships and group performance in CSCL

Zheng

Niu

Zhong

2021

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…Although previous studies have demonstrated the potential of LA for transforming education, there has been little attention paid to the design and implementation of IS with LA capabilities [26]. As a result, the study attempts to propose essential guidelines and a unified framework in hope of that educational IS researchers can unite the forces with the learning scientists and other research communities to push the LA agenda forward This conceptual study responds to the recent calls to perform theory-based LA research [10,19] and to support the application of learning analytics in higher education [18,24]. The framework proposed in this paper is easy to follow to design a theory-based learning analytics information system.…”

Section: Discussionmentioning

confidence: 98%

A Framework for Designing Learning Analytics Information Systems

Nguyen¹,

Wandabwa²,

Rasco³

et al. 2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Learning analytics offers new opportunities in higher education, yet the design and development of educational data analytics are facing several challenges. There is a paucity of research and guidance supporting researchers and developers when it comes to designing, developing, and implementing learning analytics information systems in higher education. Hence, this study proposes a comprehensive conceptual framework for designing learning analytics information systems incorporating both computational and educational aspects. The framework provides systematic support for learning analytics researchers and designers. It is constructed based on the process and critical dimensions of learning analytics and instructional systems design. By applying the framework to analyze a previously published study, we provide a better understanding of its key qualities. Furthermore, the application of the framework to design a new learning analytics information system provides forward engineering support.

show abstract

“…Hence, the instructors participating in our study might have been concerned about their students' socio‐emotional state and collaboration and thus showed more interested in such data, and intention to make informed decisions based on data related to social and emotional aspects of online learning. Notably, information about collaboration and emotions could be detected from students' interactions with the online learning environment; hence, this may serve instructors in their decision‐making process (Baker et al., 2012; Calvo & D’Mello, 2010; Herder et al., 2018; Kent & Cukurova, 2020).…”

Section: Discussionmentioning

confidence: 99%

From data to actions: Instructors' decision making based on learners' data in online emergency remote teaching

Usher

Hershkovitz

Forkosh‐Baruch

2021

Brit J Educational Tech

View full text Add to dashboard Cite

The outbreak of the COVID‐19 pandemic has changed education dramatically, with the sudden shift from face‐to‐face to emergency remote teaching. Online learning environments may facilitate data‐driven instructional process; yet, our understanding regarding data‐driven decisions is still limited. This quantitative study examined types of learners' data that higher education instructors have access to, are interested in, and decisions they would consider making upon exposure to, while comparing emergency remote teaching with traditional teaching. Data were collected via an online questionnaire distributed among higher education instructors during the first COVID‐19 outbreak (N = 195, affiliated with 108 different academic institutions in 35 countries). Instructors were requested to refer to a face‐to‐face course that was shifted under these emergency circumstances to online teaching. Findings indicated a broader access to learners' data while teaching the course face‐to‐face and a slightly greater interest in learners' data while teaching the course in an emergency remote teaching mode. These complimentary findings depict a situation in which instructors lack face‐to‐face cues about their students without accessing alternative sources of data. Moreover, when teaching online versus face‐to‐face, instructors showed more interest and higher intention to make decisions based on data about learners' collaborative learning and social and emotional support, which highlights instructors' interest in aspects of learning that are less visible during online teaching. What is already known about this topic Evidence regarding the vital role of the instructor in online courses. Online learning environments collect digital traces of learners. Learners' data may assist in the improvement of teaching by implementing data‐driven decision making. Evidence that the COVID‐19 pandemic revealed a major liability in preparation and training for online teaching. The understanding of instructors' perspectives regarding the process of data‐driven decisions, especially in times of ERT, is still limited. What this paper adds We highlight instructors' perceived access to, interest in, and willingness to make decisions based on learners' data. We take a within‐subject approach for determining instructors' perceptions of learners' data during ERT compared with face‐to‐face teaching. We bring evidence to instructors' lesser access to (despite learners' digital traces), and greater interest in, learners' data during ERT. We bring evidence to instructors' higher inclination towards making data‐driven decisions during ERT, due to lack of F2F evidence. We bring evidence to a strong correlation between instructors' interest in learners' data and willingness to make data‐driven decisions. Implications for practice and/or policy Instructors should be trained for socio‐emotional support for students in times of ERT. Higher education institutions should collect data on learners' socio‐emotional status in times of ERT. Policies of data collect...

show abstract

Investigating Collaboration as a Process with Theory-driven Learning Analytics

Cited by 24 publications

References 53 publications

Effects of a learning analytics‐based real‐time feedback approach on knowledge elaboration, knowledge convergence, interactive relationships and group performance in CSCL

Effects of a learning analytics‐based real‐time feedback approach on knowledge elaboration, knowledge convergence, interactive relationships and group performance in CSCL

A Framework for Designing Learning Analytics Information Systems

From data to actions: Instructors' decision making based on learners' data in online emergency remote teaching

Contact Info

Product

Resources

About