Early prediction of student difficulty during longduration learning activities allows a tutoring system to intervene by providing needed support, such as a hint, or by alerting an instructor. To be e effective, these predictions must come early and be highly accurate, but such predictions are difficult for openended programming problems. In this work, Recent Temporal Patterns (RTPs) are used in conjunction with Support Vector Machine and Logistic Regression to build robust yet interpretable models for early predictions. We performed two tasks: to predict student success and difficulty during one, openended novice programming task of drawing a squareshaped spiral. We comparedmore »
What Time is It? Student Modeling Needs to Know.
Abstract: Modeling student learning processes is highly complex since it is influenced by many factors such as motivation and learning habits. The high volume of features and tools provided by computerbased learning environments confounds the task of tracking student knowledge even further. Deep Learning models such as LongShort Term Memory (LSTMs) and classic Markovian models such as Bayesian Knowledge Tracing (BKT) have been successfully applied for student modeling. However, much of this prior work is designed to handle sequences of events with discrete timesteps, rather than considering the continuous aspect of time. Given that time elapsed between successive elements in a student’s trajectory can vary from seconds to days, we applied a Timeaware LSTM (TLSTM) to model the dynamics of student knowledge state in continuous time. We investigate the effectiveness of TLSTM on two domains with very different characteristics. One involves an openended programming environment where students can selfpace their progress and TLSTM is compared against LSTM, Recent Temporal Pattern Mining, and the classic Logistic Regression (LR) on the early prediction of student success; the other involves a classic tutordriven intelligent tutoring system where the tutor scaffolds the student learning step by step and TLSTM is compared with LSTM, LR, more »
 Award ID(s):
 1651909
 Publication Date:
 NSFPAR ID:
 10214148
 Journal Name:
 In Proceedings of the 13th International Conference on Educational Data Mining (EDM) 2020
 Page Range or eLocationID:
 pp 171182
 Sponsoring Org:
 National Science Foundation
More Like this


Bayesian Knowledge Tracing (BKT) is a commonly used approach for student modeling, and Long Short Term Memory (LSTM) is a versatile model that can be applied to a wide range of tasks, such as language translation. In this work, we directly compared three models: BKT, its variant InterventionBKT (IBKT), and LSTM, on two types of student modeling tasks: posttest scores prediction and learning gains prediction. Additionally, while previous work on student learning has often used skill/knowledge components identified by domain experts, we incorporated an automatic skill discovery method (SK), which includes a nonparametric prior over the exerciseskill assignments, to allmore »

Determining when and whether to provide personalized support is a wellknown challenge called the assistance dilemma. A core problem in solving the assistance dilemma is the need to discover when students are unproductive so that the tutor can intervene. Such a task is particularly challenging for openended domains, even those that are wellstructured with defined principles and goals. We present a set of datadriven methods to classify, predict, and prevent unproductive problemsolving steps in the wellstructured openended domain of logic. This approach leverages and extends the Hint Factory, a set of methods that leverages prior student solution attempts to buildmore »

Deep neural network models, especially Long Short Term Memory (LSTM), have shown great success in analyzing Electronic Health Records (EHRs) due to their ability to capture temporal dependencies in time series data. When applying the deep learning models to EHRs, we are generally confronted with two major challenges: high rate of missingness and time irregularity. Motivated by the original PACIFIER framework which utilized matrix decomposition for data imputation, we applied and further extended it by including three components: forecasting future events, a timeaware mechanism, and a subgroup basis approach. We evaluated the proposed framework with realworld EHRs which consists ofmore »

We conducted a study to see if using Bayesian Knowledge Tracing (BKT) models would save time and problems in programming tutors. We used legacy data collected by two programming tutors to compute BKT models for every concept covered by each tutor. The novelty of our model was that slip and guess parameters were computed for every problem presented by each tutor. Next, we used crossvalidation to evaluate whether the resulting BKT model would have reduced the number of practice problems solved and time spent by the students represented in the legacy data. We found that in 64.23% of the concepts,more »