Exploring effective dialogue act sequences in one-on-one computer science tutoring dialogues

Authors:
Lin Chen;Barbara Di Eugenio;Davide Fossati;Stellan Ohlsson;David Cosejo
Affiliations:
U. of Illinois at Chicago;U. of Illinois at Chicago;Carnegie Mellon U. in Qatar;U. of Illinois at Chicago;U. of Illinois at Chicago
Venue:
IUNLPBEA '11 Proceedings of the 6th Workshop on Innovative Use of NLP for Building Educational Applications
Year:
2011

Citing 10
Cited 1

The kappa statistic: a second look

Computational Linguistics
Correlations between dialogue acts and learning in spoken tutoring dialogues

Natural Language Engineering
The Cambridge Handbook of Computational Psychology

The Cambridge Handbook of Computational Psychology
Dialogue Modes in Expert Tutoring

ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
Inter-coder agreement for computational linguistics

Computational Linguistics
Beyond the code-and-count analysis of tutoring dialogues

Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
Supporting Computer Science Curriculum: Exploring and Learning Linked Lists with iList

IEEE Transactions on Learning Technologies
A Lucene and maximum entropy model based hedge detection system

CoNLL '10: Shared Task Proceedings of the Fourteenth Conference on Computational Natural Language Learning --- Shared Task
Generating proactive feedback to help students stay on track

ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part II
Characterizing the effectiveness of tutorial dialogue with hidden markov models

ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part I

Learner characteristics and dialogue: recognising effective and student-adaptive tutorial strategies

International Journal of Learning Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an empirical study of one-on-one human tutoring dialogues in the domain of Computer Science data structures. We are interested in discovering effective tutoring strategies, that we frame as discovering which Dialogue Act (DA) sequences correlate with learning. We employ multiple linear regression, to discover the strongest models that explain why students learn during one-on-one tutoring. Importantly, we define "flexible" DA sequence, in which extraneous DAs can easily be discounted. Our experiments reveal several cognitively plausible DA sequences which significantly correlate with learning outcomes.