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

Abstract

AutoTutor is a natural language tutoring system that has produced learning gains across multiple domains (e.g., computer literacy, physics, critical thinking). In this paper, we review the development, key research findings, and systems that have evolved from AutoTutor. First, the rationale for developing AutoTutor is outlined and the advantages of natural language tutoring are presented. Next, we review three central themes in AutoTutor's development: human-inspired tutoring strategies, pedagogical agents, and technologies that support natural-language tutoring. Research on early versions of AutoTutor documented the impact on deep learning by co-constructed explanations, feedback, conversational scaffolding, and subject matter content. Systems that evolved from AutoTutor added additional components that have been evaluated with respect to learning and motivation. The latter findings include the effectiveness of deep reasoning questions for tutoring multiple domains, of adapting to the affect of low-knowledge learners, of content over surface features such as voices and persona of animated agents, and of alternative tutoring strategies such as collaborative lecturing and vicarious tutoring demonstrations. The paper also considers advances in pedagogical agent roles (such as trialogs) and in tutoring technologies, such semantic processing and tutoring delivery platforms. This paper summarizes and integrates significant findings produced by studies using AutoTutor and related systems.

Evaluating LSA sensibility to disclosure in learners' interactions

“…Semantic analysis is important to a number of applications such as question answering systems [13] and Intelligent Tutoring Systems [4]. For instance, [1] conducted automatic semantic analysis to support informal social learning by enabling visual exploration of the semantic spaces of usergenerated content.…”

“…For instance, [1] conducted automatic semantic analysis to support informal social learning by enabling visual exploration of the semantic spaces of usergenerated content. Alternatively, [3] used a probabilistic semantic model to analyse and visualize the collaborative writing process by extracting the semantic topics associated to its evolution, while [4] and [5] have used LSA to evaluate learners' contributions and compose peers' feedback respectively. LSA is one of these techniques used for analysing relationships between a set of documents and the terms they contain, by producing a set of latent concepts related to the documents and terms.…”

“…In the literature, there are a number of semantic analysis techniques that have been used in learning environment to support collaborative activities [3], to evaluate learners' contributions [4], and to protect learners' privacy [5]. Regarding the latter work, a semantic representation of peers' textual interactions was built, using Latent Semantic Analysis (LSA), in order to discard negative and self-disclosing feedback by varying the semantic space parameters.…”

Feedback Design in Multimodal Dialogue Systems

“…While there is experience in education with systems e.g. using written language for interaction (Nye, Graesser & Hu, 2014) and motion sensors (Triantafyllou, Timcenko, & Triantafyllidis, 2014), there is limited experience in using other or more modalities at the same time to support interaction for learning. The increasing computable power and miniaturization, however, opens up numerous new application scenarios in education; for example, using sensors to provide input about learners, between learners or between learner(s) and the environment they explore.…”

Work in Progress: Intelligent Tutoring Systems in Computer Science and Software Engineering Education

“…We found that systems combining ITS with pedagogical tutors, which first appeared about 17 years ago, continue to be improved and evaluated by researchers in CS/SE education. 12,13,19,20 The accumulated evidence indicates that pedagogical agents are associated with small, positive effects on learning, 21 but that the content of instructional messages is far more important than whether the messages are presented by an anthropomorphic figure. cognitively organize, and appropriately attend to the information ITS provide. For example, ITS that provide many types of messages or notifications may be able to improve pedagogical utility by assigning each broad category of message to a different pedagogical agent.…”