José P. González-Brenes

Classifying dialogue in high-dimensional space

The richness of multimodal dialogue makes the space of possible features required to describe it very large relative to the amount of training data. However, conventional classifier learners require large amounts of data to avoid overfitting, or do not generalize well to unseen examples. To learn dialogue classifiers using a rich feature set and fewer data points than features, we apply a recent technique, ℓ1-regularized logistic regression. We demonstrate this approach empirically on real data from Project LISTENs Reading Tutor, which displays a story on a computer screen and listens to a child read aloud. We train a classifier to predict task completion (i.e., whether the student will finish reading the story) with 71% accuracy on a balanced, unseen test set. To characterize differences in the behavior of children when they choose the story they read, we likewise train and test a classifier that with 73.6% accuracy infers who chose the story based on the ensuing dialogue. Both classifiers significantly outperform baselines and reveal relevant features of the dialogue.

Challenges of Using Observational Data to Determine the Importance of Example Usage

Educational interventions are often evaluated with randomized control trials, which can be very expensive to conduct. One of the promises of “Big Data” in education is to use non-experimental data to discover insights. We focus on studying the impact of example usage in a Java programming tutoring system using observational data. For this, we compare different formulations of a recently proposed generalized Knowledge Tracing framework called FAST. We discover that different formulations can have the same predictive performance; yet their coefficients may have opposite signs, which may lead researchers to contradictory conclusions. We discuss implications of using fully data-driven approaches to study non-experimental data.

Inferring Course Enrollment from Partial Data

We study how to infer students’ course enrollment information from incomplete data. We use data collected from a leading technology company and use a novel extension of Factorization Machines that we call Weighted Feat2Vec. Our empirical evaluation suggests that we improve on popular methods, while training time is reduced by half (when using the same implementation language, and hardware).