When Does Disengagement Correlate with Learning in Spoken Dialog Computer Tutoring?

We examine correlations between dialogue behaviors and learning in tutoring, using two corpora of spoken tutoring dialogues: a human-human corpus and a human-computer corpus. To formalize the notion of dialogue behavior, we manually annotate our data using a tagset of student and tutor dialogue acts relative to the tutoring domain. A unigram analysis of our annotated data shows that student learning correlates both with the tutor's dialogue acts and with the student's dialogue acts. A bigram analysis shows that student learning also correlates with joint patterns of tutor and student dialogue acts. In particular, our human-computer results show that the presence of student utterances that display reasoning (whether correct or incorrect), as well as the presence of reasoning questions asked by the computer tutor, both positively correlate with learning. Our human-human results show that student introductions of a new concept into the dialogue positively correlates with learning, but student attempts at deeper reasoning (particularly when incorrect), and the human tutor's attempts to direct the dialogue, both negatively correlate with learning. These results suggest that while the use of dialogue act n-grams is a promising method for examining correlations between dialogue behavior and learning, specific findings can differ in human versus computer tutoring, with the latter better motivating adaptive strategies for implementation.

Download Full-text

Genetic variation interacts with experience to determine interindividual differences in learned song

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1713031115 ◽

2017 ◽

Vol 115 (2) ◽

pp. 421-426 ◽

Cited By ~ 17

Author(s):

David G. Mets ◽

Michael S. Brainard

Keyword(s):

Genetic Variation ◽

Vocal Learning ◽

Interindividual Variation ◽

Interindividual Differences ◽

Computer Tutoring ◽

Genetically Determined ◽

Genetic Contributions ◽

And Control ◽

Weak Influence

Learning reflects the influence of experience on genetically determined circuitry, but little is known about how experience and genetics interact to determine complex learned phenotypes. Here, we used vocal learning in songbirds to study how experience and genetics contribute to interindividual differences in learned song. Previous work has established that such differences in song within a species depend on learning, but in principle some of these differences could also depend on genetic variation. We focused on song tempo, a learned and quantifiable feature that is controlled by central neural circuitry. To identify genetic contributions to tempo we computer-tutored juvenile Bengalese finches (Lonchura striata domestica) from different genetic backgrounds with synthetic songs in which tempo was systematically varied. Computer-tutored birds exhibited unexpectedly strong heritability for song tempo and comparatively weak influence of experience. We then tested whether heritability was fixed and independent of experience by providing a second group of birds with enriched instruction via live social tutoring. Live tutoring resulted in not only a significant increase in the influence of experience on tempo but also a dramatic decrease in the influence of genetics, indicating that enriched instruction could overcome genetic biases evident under computer tutoring. Our results reveal strong heritable genetic contributions to interindividual variation in song tempo but that the degree of heritability depends profoundly on the quality of instruction. They suggest that for more complex learned phenotypes, where it can be difficult to identify and control relevant experiential variables, heritability may similarly be contingent on the specifics of experience.

Download Full-text

Learning Problem-Solving Skills in Algebra

Journal of Educational Technology Systems ◽

10.2190/pe6f-2upe-g03r-xeuk ◽

1987 ◽

Vol 15 (3) ◽

pp. 303-324 ◽

Cited By ~ 16

Author(s):

David McArthur ◽

Cathleen Stasz ◽

John Y. Hotta

Keyword(s):

Problem Solving ◽

Learning Opportunities ◽

Learning Problem ◽

High Quality ◽

Problem Solving Skills ◽

Intelligent Tutors ◽

Computer Tutoring ◽

First Time ◽

Intelligent Tutor

In this article we describe aspects of our intelligent tutor for basic algebra. A main goal of the project is to develop a computer tutoring system whose skills and knowledge approximate those of a high-quality human tutor. We are particularly interested in exploring novel learning opportunities that can be made available to students for the first time by exploiting the reactive capabilities of such intelligent tutors. In this context, we focus here on the role of an algebra expert system embedded in the tutor. We discuss how it can be used to help students learn several nontraditional types of skill and knowledge in the context of algebra, including goal-directed reasoning skills, and debugging techniques.

Download Full-text

A Consistent Set of Oxidation Number Rules for Intelligent Computer Tutoring

Journal of Chemical Education ◽

10.1021/ed079p465 ◽

2002 ◽

Vol 79 (4) ◽

pp. 465 ◽

Cited By ~ 3

Author(s):

Dale A. Holder ◽

Benny G. Johnson ◽

Paul J. Karol

Keyword(s):

Oxidation Number ◽

Computer Tutoring ◽

Intelligent Computer

Download Full-text

The method of student's query analysis while intelligent computer tutoring in SQL

RADIOELECTRONIC AND COMPUTER SYSTEMS ◽

10.32620/reks.2021.2.07 ◽

2021 ◽

pp. 78-86

Author(s):

Andrey Chukhray ◽

Olena Havrylenko

Keyword(s):

General Scheme ◽

Computer Training ◽

Computer Programs ◽

Automatic Testing ◽

Syntactic Analysis ◽

Technical Diagnostics ◽

Analysis Methods ◽

Computer Tutoring ◽

Sql Query ◽

Intelligent Computer

Recently, IT specialties have become one of the most demanded specialties in the world labor market. Simultaneously the traditional teaching in conditions of mass production, even with a professional teacher, has a significant drawback – the fundamental impossibility of adapting to each student. Since the 60s of the twentieth century, researchers worldwide have been developing various computer-tutoring tools that have, less or more, adaptive functions. Nevertheless, the task of the perfect computer tutor development is still far from being solved. The article's research subject is the process of student requests analyzing during intelligent computer tutoring in SQL. The main goal is to develop a method for analyzing the student's SQL queries. The purposes: to form a general scheme and features of the method for analyzing student’s SQL queries based on the principles of technical diagnostics and methods of lexical, syntactic analysis of computer programs; to develop methods for parse tree construction; to create methods for comparing reference and real SQL queries according to their similarity rate; to demonstrate the function ability of the developed methods on specific examples. The methods used computer programs the automatic testing method, the computer programs lexical and syntactic analysis methods, the computer programs parsing trees construction methods, the objects diagnosing method based on comparison with a reference, the strings analysis methods, the method of q-grams. The following results were obtained: the student’s SQL queries analysis method was formed based on a system approach including automatic testing on real data, building query-parsing trees, comparison with a reference, and comprehensive determination of the queries similarity rate. The scientific novelty is the improvement of the method for the student's SQL query analysis during intelligent computer training in SQL query composition.

Download Full-text