Evaluation of an LLM-Powered Student Agent for Teacher Training

被引:2
作者
Bhowmik, Saptarshi [1 ]
West, Luke [1 ]
Barrett, Alex [1 ]
Zhang, Nuodi [1 ]
Dai, Chih-Pu [2 ]
Sokolikj, Zlatko [1 ]
Southerland, Sherry [1 ]
Yuan, Xin [1 ]
Ke, Fengfeng [1 ]
机构
[1] Florida State Univ, Tallahassee, FL 32306 USA
[2] Univ Hawaii Manoa, Honolulu, HI 96822 USA
来源
TECHNOLOGY ENHANCED LEARNING FOR INCLUSIVE AND EQUITABLE QUALITY EDUCATION, PT II, EC-TEL 2024 | 2024年 / 15160卷
关键词
Teaching simulation; Teacher education; Large Language Model; Sentiment Analysis; Cognitive-affective states; Virtual Student Agent;
D O I
10.1007/978-3-031-72312-4_7
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
As technology continues to advance, there is a growing interest in exploring the potential of generative agents and large language model (LLM)-powered virtual students to revolutionize the field of education. In this work, we present Evelyn AI, a LLM-powered virtual student conversation agent that we developed for pre-service teacher training in a virtual environment. Students powered by Evelyn AI exhibit varying baseline conceptual understanding levels, dynamic cognitive-affective states, and short-term memory. These features enable personalized, adaptive training and promote a more engaging and immersive learning experience for pre-service teachers. We describe the design and implementation of Evelyn AI, and report results of alpha testing to assess the utility of Evelyn AI for pre-service teacher training.
引用
收藏
页码:68 / 74
页数:7
相关论文
共 12 条
[1]   Teacher Coaching in a Simulated Environment [J].
Cohen, Julie ;
Wong, Vivian ;
Krishnamachari, Anandita ;
Berlin, Rebekah .
EDUCATIONAL EVALUATION AND POLICY ANALYSIS, 2020, 42 (02) :208-231
[2]  
Connolly T., 2020, Games and Simulations in Teacher Education, P55
[3]  
D'Mello S., 2007, Monitoring affective trajectories during complex learning, P203
[4]  
Dai C-P., 2022, Comput Educ Artif Intell, V3, P100087, DOI [DOI 10.1016/J.CAEAI.2022.100087, 10.1016/j.caeai.2022.100087 10.1016/j.caeai.2022.100087, 10.1016/j.caeai.2022.100087]
[5]   From sentence to emotion: a real-time three-dimensional graphics metaphor of emotions extracted from text [J].
Gobron, Stephane ;
Ahn, Junghyun ;
Paltoglou, Georgios ;
Thelwall, Michael ;
Thalmann, Daniel .
VISUAL COMPUTER, 2010, 26 (6-8) :505-519
[6]   Tapping epistemological resources for learning physics [J].
Hammer, D ;
Elby, A .
JOURNAL OF THE LEARNING SCIENCES, 2003, 12 (01) :53-90
[7]  
Hovey K., 2018, Kappa Delta Pi Record, V54, P165, DOI [https://doi.org/10.1080/00228958.2018.1515544, DOI 10.1080/00228958.2018.1515544]
[8]   The mind and brain of short-term memory [J].
Jonides, John ;
Lewis, Richard L. ;
Nee, Derek Evan ;
Lustig, Cindy ;
Berman, Marc G. ;
Moore, Katherine Sledge .
ANNUAL REVIEW OF PSYCHOLOGY, 2008, 59 :193-224
[9]   Virtual reality simulation-based learning of teaching with alternative perspectives taking [J].
Ke, Fengfeng ;
Xu, Xinhao .
BRITISH JOURNAL OF EDUCATIONAL TECHNOLOGY, 2020, 51 (06) :2544-2557
[10]   Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [J].
Liu, Pengfei ;
Yuan, Weizhe ;
Fu, Jinlan ;
Jiang, Zhengbao ;
Hayashi, Hiroaki ;
Neubig, Graham .
ACM COMPUTING SURVEYS, 2023, 55 (09)