| 1. |
- Cukurova, Mutlu, et al.
(författare)
-
Modelling Collaborative Problem-solving Competence with Transparent Learning Analytics : Is Video Data Enough?
- 2020
-
Ingår i: LAK20. - New York, NY, USA : Association for Computing Machinery (ACM). ; , s. 270-275
-
Konferensbidrag (refereegranskat)abstract
- In this study, we describe the results of our research to model collaborative problem-solving (CPS) competence based on analytics generated from video data. We have collected similar to 500 mins video data from 15 groups of 3 students working to solve design problems collaboratively. Initially, with the help of OpenPose, we automatically generated frequency metrics such as the number of the face-in-the-screen; and distance metrics such as the distance between bodies. Based on these metrics, we built decision trees to predict students' listening, watching, making, and speaking behaviours as well as predicting the students' CPS competence. Our results provide useful decision rules mined from analytics of video data which can be used to inform teacher dashboards. Although, the accuracy and recall values of the models built are inferior to previous machine learning work that utilizes multimodal data, the transparent nature of the decision trees provides opportunities for explainable analytics for teachers and learners. This can lead to more agency of teachers and learners, therefore can lead to easier adoption. We conclude the paper with a discussion on the value and limitations of our approach.
|
|
| 2. |
- Ternblad, Eva Maria, et al.
(författare)
-
Far from success – Far from feedback acceptance? The influence of game performance on young students’ willingness to accept critical constructive feedback during play
- 2020
-
Ingår i: Artificial Intelligence in Education- 21st International Conference, AIED 2020, Proceedings, Part I. - Cham : Springer International Publishing. - 1611-3349 .- 0302-9743. - 9783030522360 ; 12163 LNAI, s. 537-548
-
Konferensbidrag (refereegranskat)abstract
- In a learning situation, feedback is of great importance in order to help a student to correct a possible misconception. However, previous research shows that many students tend to avoid feedback regarding failures, including critical constructive feedback (CCF) that is intended to support and guide them. This is especially true for lower-achieving students, who might perceive feedback as an ego-threat, and therefore protect themselves by neglecting it. However, it has been shown that such neglect can be suppressed by using teachable agents (TA’s). Another, but less studied factor that influences feedback acceptance is the degree or extent of failure when trying to solve a task. The present study explores if and how momentary performance levels influence middle school students’ willingness to accept CCF when playing an educational game in history – with or without a TA. On the basis of teacher assessments of the students’ general skills, data logs and analyses of sequential patterns, we concluded that the willingness to accept CCF differs between students, but also between conditions and situations. One major finding is that a TA supports the students to more readily embrace CCF, even if the effect is larger for lower-achieving students. Another finding is that indications of being far from succeeding, such as low success rates or repeated trials and revisions, have a negative impact on feedback acceptance, even if a TA mitigates some of this influence. The implications of these results are discussed in relation to meta-cognitive aspects of learning and to educational software design.
|
|
