1. |
- Gulz, Agneta, et al.
(författare)
-
Preschoolers’ Understanding of a Teachable Agent-Based Game in Early Mathematics as Reflected in their Gaze Behaviors – : an Experimental Study
- 2020
-
Ingår i: International Journal of Artificial Intelligence in Education. - : Springer Science and Business Media LLC. - 1560-4292 .- 1560-4306.
-
Tidskriftsartikel (refereegranskat)abstract
- This study investigated how preschool children processed and understood critical information in Magical Garden, a teachable agent-based play-&-learn game targeting early math. We analyzed 36 children’s (ages 4–6 years) real-time behavior during game-use to explore whether children: (i) processed the information meant to support number sense development; (ii) showed an understanding of the teachable agent as an entity with agency. An important methodological goal was to go beyond observable behavior and shed some light on how cognitive processing and understanding in children of such young age can be studied. First, the children played Magical Garden for three weeks to get acquainted with the game. Second, in an experimental part of the study, the children’s gaze behaviors were measured during 5 rounds of interaction with an experimental version of one of the sub-games. The analyses suggest that two of the gaze behaviors were positively correlated with the game performance measure, as hypothesized. Another result was that children looked at the teachable agent significantly more often when the teachable agent had been in charge of gameplay than when it had not. This can be interpreted as an indication that the children had an understanding of their teachable agent as an entity that, like themselves and unlike other dynamic visual elements in the game, made decisions based on own ‘knowledge’. In a broader context, the findings are important in showing the potential gains of combining log data with eye-tracking data for developing and refining AI algorithms for adaptive individual feedback and scaffolding.
|
|
2. |
- Lingonblad, Martin, et al.
(författare)
-
Virtual Blindness - A Choice Blindness Experiment with a Virtual Experimenter
- 2015
-
Ingår i: Intelligent Virtual Agents. - Cham : Springer International Publishing. - 0302-9743 .- 1611-3349. ; 9238, s. 442-451
-
Konferensbidrag (refereegranskat)abstract
- How are people facing a virtual agent affected by the vividness and graphical fidelity of the agent and its environment? A choice blindness (CB) experiment - measuring detection rate of hidden manipulations - was conducted presenting a high versus low immersion virtual environment. The hypothesis was that the lower quality virtual environment (low immersion) would increase the detection rate for the CB manipulations. 38 subjects participated in the experiment and were randomized into two groups (high and low immersion). Both conditions presented a virtual agent conducting the CB experiment. During the experiment, 16 pairs of portraits were shown two at a time for the participants who were then asked to choose which portrait they found most attractive. For eight of the pairs, participants were asked to justify their choice while in four cases their choice had been secretly switched to the portrait they had not chosen. If a participant stated that the chosen portrait had been switched, it was annotated as a concurrent detection. The results revealed an increase in detection and earlier detection rate for the low immersion implementation compared to the high immersion implementation. Future research may involve experiments with higher degree of both immersion and presence, using for example head mounted display systems.
|
|