HOME‎ > ‎LAK19Tutorial‎ > ‎

BACKGROUND

Institute of Electrical and Electronics Engineers (IEEE) recently approved a standard committee (P2247.1 - Standard for the Classification of Adaptive Instructional Systems). This is a significant milestone for advanced personalized learning, which is identified by the National Academy of Engineering one of the grand challenges of the 21st century (http://www.engineeringchallenges.org/9127.aspx). Conversational Intelligent tutoring systems (C-ITS) is a class of AIS that are among the most studied and efficiently implemented in the last 20 years. This tutorial will bring you the most successful example C-ITS called AutoTutor (Graesser, Hu, & Person, 2001; Graesser et al., 2004; Nye, Graesser, & Hu, 2014; Nye, Graesser, Hu, & Cai, 2014; Person et al., 2000). AutoTutor holds conversations with the human in natural language. The authors of the proposed tutorial are among those who have development multiple versions of AutoTutor that teaches Critical Thinking (Wallace et al., 2009), Computer Literacy (Person, 2003), Physics (Graesser et al., 2003), Reading (Graesser et al., 2016), Electronics (Morgan et al., 2018), Chinese reading and mathematics learning (Liao, Kuo, & Pai, 2012).
AutoTutor applications are built with the guidance of human learning principles (A. C. Graesser, Halpern, & Hakel, 2008), such as Deep Questioning, to help students learn by holding deep reasoning conversations (Arthur C. Graesser & Person, 1994). AutoTutor converses with learners follow the Expectation-Misconception Tailored (EMT) dialog (Arthur C. Graesser et al., 2004). An AutoTutor conversation often starts with a main question about a certain topic. The goal of the conversation is to help students’ construct an acceptable answer (expected answers) to the main question. Instead of telling the students the answers, AutoTutor asks a sequence of questions (hints, prompts) that target specific concepts involved in the ideal answer to the main question. AutoTutor systems respond to students' natural language input, as well as other interactions, such as making a choice, arranging some objects in the learning environment, etc.
This tutorial focuses on the authoring of AutoTutor lessons and Data analysis process of Tutoring data:
1. Authoring of AutoTutor lessons include a) implementing discourse strategies in AutoTutor dialogues and trialogues, b) creating conversation elements (such as media elements); c) conversation rules, and d) using existing well-made authoring templates. 
2. Data analysis process of tutoring data include applying learning analytics methods, such as Bayesian Knowledge Tracing (BKT), Learning Factors Analysis (LFA), to leverage the sequences of observations from student-ITS interaction log files to continually update the estimate of student latent knowledge.

References

Graesser, A. C., Cai, Z., Baer, W. O., Olney, A. M., Hu, X., Reed, M., & Greenberg, D. (2016). Reading comprehension lessons in AutoTutor for the Center for the Study of Adult Literacy. Adaptive Educational Technologies for Literacy Instruction, 288–293.

Graesser, A. C., Halpern, D. F., & Hakel, M. (2008). 25 principles of learning. Task Force on Lifelong Learning at Work and at Home Washington, DC.

Graesser, A. C., Hu, X., & Person, N. K. (2001). Teaching with the help of talking heads. Proceedings of the 2001 IEEE International Conference on Advanced Learning Technologies, 460-461.

Graesser, A. C., Jackson, G. T., Matthews, E. C., Mitchell, H. H., Olney, A., Ventura, M., et al.  (2003). Why/AutoTutor: A test of learning gains from a physics tutor with natural language dialog. In R. Alterman & D. Hirsh (Eds.), Proceedings of the 25th Annual Conference of the Cognitive Science Society (pp. 1-5). Boston: Cognitive Science Society.

Graesser, A. C., Lu, S., Jackson, G. T., Mitchell, H. H., Ventura, M., Olney, A. M., et al. (2004). AutoTutor: A tutor with dialogue in natural language. Behavior Research Methods, Instruments, & Computers, 36, 180-193.

Graesser, A. C., & Person, N. K. (1994). Question asking during tutoring. American Educational Research Journal, 31, 104–137.

Liao, C.-H., Kuo, B.-C., & Pai, K.-C. (2012). Effectiveness of Automated Chinese Sentence Scoring with Latent Semantic Analysis. Turkish Online Journal of Educational Technology-TOJET, 11(2), 80–87.

Morgan, B., Hampton, A. J., Cai, Z., Tackett, A., Wang, L., Hu, X., & Graesser, A. C. (2018). Electronixtutor Integrates Multiple Learning Resources to Teach Electronics on the Web. In Proceedings of the Fifth Annual ACM Conference on Learning at Scale (pp. 33:1–33:2). New York, NY, USA: ACM.

Nye, B.D., Graesser, A.C., & Hu, X. (2014).  AutoTutor and family: A review of 17 years of natural language tutoring. International Journal of Artificial Intelligence in Education, 24(4), 427-469.

Nye, BD, Graesser, AC, Hu, X. (2014b). AutoTutor in the cloud: a service-oriented paradigm for an interoperable natural-language ITS. Journal of Advanced Distributed Learning Technology, 2(6), 35–48.

Person, N. K. (2003). AutoTutor improves deep learning of computer literacy: Is it the dialog or the talking head. Artificial Intelligence in Education: Shaping the Future of Learning through Intelligent Technologies, 97, 47.

Person, N. K., Craig, S., Price, P., Hu, X., Gholson, B., Graesser, A. C., & Tutoring Research Group. (2000). Incorporating human-like conversational behaviors in AutoTutor. Proceedings of the Agents 2000 Conference, 85-92.

Wallace, P., Graesser, A. C., Millis, K., Halpern, D., Cai, Z., Britt, M. A., Magliano, J., & Wiemer, K. (2009). Operation ARIES!: A computerized game for teaching scientific inquiry. In V. Dimitrova, R. Mizoguchi, B. Du Boulay, & A. C. Graesser (Eds.), Proceedings of 14th International Conference on Artificial Intelligence in Education. Building Learning Systems that Care: From Knowledge Representation to Affective Modelling (pp. 602-604). Amsterdam: IOS Press.