同理心模擬之情感支持系統對合作學習之成效測試

Emulating Empathy in Emotional Support System to Test Performance on Collaborative Learning

王冠云(Guan-Yun Wang)

指導教授 ： 黃囇莉

共同指導教授 ： 岳修平(Hsiu-Ping Yueh)

國立臺灣大學/理學院/心理學研究所/碩士(2020年)

https://doi.org/10.6342/NTU202001980

摘要

本研究測試一個能模擬人類同理心的機器人，作為科技輔助教學的工具之一，機器人具備了「物理存在感」這項特點，再加上具備聲音與表情，使之可能得以模擬人類的同理心並且介入合作學習的任務之中。本研究之實驗情境為一個語言解題任務，實驗參與者共有45人，男生21人、女生24人，參與者皆為學生，且每三人為一組，隨機分派到三種實驗條件：高同理心組、低同理心組、控制組。本研究要了解學生如何被給予情感支持、如何感受到指導方的同理心，進而提升自己的學習，學習成效方面分為認知表現（解題時間、解題正確率）以及情感表現（機器人友情、心智知覺、基本同理心）。在本研究的研究結果中，發現了在控制組的實驗條件之下，實驗參與者的解題正確率最高，且對於機器人的心靈知覺亦較高。當機器人介入合作學習的小組討論時，確實可以讓學習者對於機器人投以更多的社交行為，並且促進討論。此外，本研究結果顯示了使用者對於科技仍然較期待一個「客觀而聰明」的機器作為輔助工具。在具有挑戰性的學習情境中，科技模擬而出的同理心，可能影響了學習。

關鍵字

同理心 ； 人機互動 ； 科技輔助教學 ； 合作學習 ； 情感支持

並列摘要

This study tests a robot which can emulate human’s empathy. As a technology-enhanced system in education, robot, which has “physical presence” with voice and facial expression, is more possible to emulate empathy than other information communication tools. This study used a linguistic puzzle task as our experimental scenario. Totally 45 participants including 21 males and 24 females joined the experiment, and 3 students a group would be randomly assigned to 3 conditions: high empathy group, low empathy group and control group. This study examined the learning performance of both cognitive (solving time, solving accuracy) and affective (friendship with robot, mind perception of robot, basic empathy). The results showed that in neutral group, the participants had higher accuracy and mind perception of robot. When robot intervened into collaborative learning group, the learners engaged more social interaction behavior and the robot facilitate their discussion. Besides, the users expected a “objective and clever” robot as a supportive tool. In this kind of challenging learning scenario, emulating empathy might reduce the performance of learning.

並列關鍵字

empathy ； human-robot-interaction (HRI) ； technology-enhance learning ； collaborative learning ； emotional support

參考文獻

Abubshait, A., Wiese, E. (2017). You look human, but act like a machine: Agent appearance and behavior modulate different aspects of human–robot Interaction. Frontiers in Psychology, 8. Retrieved from: https://www.frontiersin.org/articles/10.3389/fpsyg.2017.01393/full

Alves-Oliveira, P., Janarthanam, S., Candeias, A., Deshmukh, A., Ribeiro, T., Hastie, H., . . . Aylett, R. (2014, 25-29 Aug. 2014). Towards dialogue dimensions for a robotic tutor in collaborative learning scenarios. Paper presented at the The 23rd IEEE International Symposium on Robot and Human Interactive Communication, Edinburgh, UK.

Amaro, R. (2016). Teaching computational linguistics. Paper presented at the Proceedings of II World Congress on Computer Science, Engineering and Technology Education, Castelo Branco, Portugal.

Belpaeme, T., Kennedy, J., Ramachandran, A., Scassellati, B., Tanaka, F. (2018). Social robots for education: A review. Science Robotics, 3(21). Retrieved from: https://robotics.sciencemag.org/content/3/21/eaat5954

Breazeal, C. (2004). Social interactions in HRI: the robot view. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 34(2), 181-186.