Comparing Linguistic Features for Modeling Learning in Computer Tutoring

Authors:
Kate Forbes-Riley;Diane Litman;Amruta Purandare;Mihai Rotaru;Joel Tetreault
Affiliations:
University of Pittsburgh, Pittsburgh, PA, 15260, USA;University of Pittsburgh, Pittsburgh, PA, 15260, USA;University of Pittsburgh, Pittsburgh, PA, 15260, USA;University of Pittsburgh, Pittsburgh, PA, 15260, USA;University of Pittsburgh, Pittsburgh, PA, 15260, USA
Venue:
Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
Year:
2007

Citing 10
Cited 8

The Architecture of Why2-Atlas: A Coach for Qualitative Physics Essay Writing

ITS '02 Proceedings of the 6th International Conference on Intelligent Tutoring Systems
PARADISE: a framework for evaluating spoken dialogue agents

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
The role of initiative in tutorial dialogue

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Correlations between dialogue acts and learning in spoken tutoring dialogues

Natural Language Engineering
The PARADISE Evaluation Framework: Issues and Findings

Computational Linguistics
Modelling user satisfaction and student learning in a spoken dialogue tutoring system with generic, tutoring, and user affect parameters

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Comparing the utility of state features in spoken dialogue using reinforcement learning

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Going Beyond the Problem Given: How Human Tutors Use Post-Solution Discussions to Support Transfer

International Journal of Artificial Intelligence in Education - "Caring for the Learner" in honour of John Self
Natural Language Generation for Intelligent Tutoring Systems: a case study

Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
Exploiting discourse structure for spoken dialogue performance analysis

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing

Semantic Cohesion and Learning

ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
Student Note-Taking in Narrative-Centered Learning Environments: Individual Differences and Learning Effects

ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
Dialog Convergence and Learning

Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies

User Modeling and User-Adapted Interaction
Inducing effective pedagogical strategies using learning context features

UMAP'10 Proceedings of the 18th international conference on User Modeling, Adaptation, and Personalization
Do micro-level tutorial decisions matter: applying reinforcement learning to induce pedagogical tutorial tactics

ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part I
An evaluation of pedagogical tutorial tactics for a natural language tutoring system: a reinforcement learning approach

International Journal of Artificial Intelligence in Education - Special issue on Best of ITS 2010
Evaluating language understanding accuracy with respect to objective outcomes in a dialogue system

EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We compare the relative utility of different automatically computable linguistic feature sets for modeling student learning in computer dialogue tutoring. We use the PARADISE framework (multiple linear regression) to build a learning model from each of 6 linguistic feature sets: 1) surface features, 2) semantic features, 3) pragmatic features, 4) discourse structure features, 5) local dialogue context features, and 6) all feature sets combined. We hypothesize that although more sophisticated linguistic features are harder to obtain, they will yield stronger learning models. We train and test our models on 3 different train/test dataset pairs derived from our 3 spoken dialogue tutoring system corpora. Our results show that more sophisticated linguistic features usually perform better than either a baseline model containing only pretest score or a model containing only surface features, and that semantic features generalize better than other linguistic feature sets.