Recent Advances in Conversational Intelligent Tutoring Systems

Abstract

We report recent advances in intelligent tutoring systems with conversational dialogue. We highlight progress in terms of macro and microadaptivity. Macroadaptivity refers to a system’s capability to select appropriate instructional tasks for the learner to work on. Microadaptivity refers to a system’s capability to adapt its scaffolding while the learner is working on a particular task. The advances in macro and microadaptivity that are presented here were made possible by the use of learning progressions, deeper dialogue and natural language processing techniques, and by the use of affect-enabled components. Learning progressions and deeper dialogue and natural language processing techniques are key features of DeepTutor, the first intelligent tutoring system based on learning progressions. These improvements extend the bandwidth of possibilities for tailoring instruction to each individual student which is needed for maximizing engagement and ultimately learning.

A Roadmap for Natural Language Processing Research in Information Systems

“…The rest 20 articles focused on real world NLP-related applications, though no prototypical tasks were explicitly represented. For example, Rus et al [44] reported advances in intelligent tutoring systems with conversational dialogue, where each system could employ many complex NLP related tasks but not explicitly stated.…”

AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring

“…DeepTutor integrates verbal contributions and problem-based assessment into the detection of learner states by using conversation and short multiple-choice tests to diagnose learning states (Rus et al 2013c). The system maps student statements and problem-solving activity to different states of understanding each concept.…”

“…AutoTutor and related systems in the family have tutored computer literacy (Graesser et al 2004a), conceptual physics (Graesser et al 2003a;Rus et al 2013c;VanLehn et al 2007), biology , critical thinking (Halpern et al 2012;Hu and Graesser 2004;Millis et al 2011), and other topics. AutoTutor approaches have also been extended to push the boundaries of the tutoring interaction, examining the impact of incorporating affect (AutoTutor-AS; D'Mello and Graesser 2012a), gaze focus (GazeTutor; D 'Mello et al 2012), metacognitive skills (MetaTutor; Azevedo et al 2010), and 3D simulations (AutoTutor-3D; Graesser et al 2005a).…”

Design and Evaluation of a Natural Language Tutor for Force and Motion

“…In order to better compare potential trade-offs between learning gains and training time, we define the efficiency of training for a particular student as the ratio of assessment score over total time spent during training (in minutes). The mean efficiency ratings (score/min) for each of the training methods were 8.44 for multiple choice format, 5.16 for natural language, and 5.52 for natural language without feedback. A oneway ANOVA showed that the difference between these efficiencies is significant (F(2,130) = 11.3, p < 0.001).…”

“…Physics education, in particular, has an impressive pedigree of development -including ANDES/ATLAS [1], the AutoTutor series [2,3], Cordillera [4], and most recently Deep Tutor [5]. These computer tutors, using various natural language methodologies and to significant levels of success, have tackled physics topics such as forces, kinematics, Newton's laws, and energy conservation.…”