This study expands upon an existing model of students’ reading comprehension ability within an intelligent tutoring system. The current system evaluates students’ natural language input using a local student model. We examine the potential to expand this model by assessing the linguistic features of self-explanations aggregated across entire passages. We assessed the relationship between 126 students’ reading comprehension ability and the cohesion of their aggregated self-explanations with three linguistic features. Results indicated that the three cohesion indices accounted for variance in reading ability over and above the features used in the current algorithm. These results demonstrate that broadening the window of NLP analyses can strengthen student models within ITSs.

Recent research has extended tutor strategies to model not just interventions to offer information and activities, but also interventions to support learners’ wills and motivation. It is important to investigate new ways, intertwined with learners’ performance (successful completion of tasks) and judgement (self-report questionnaires), for evaluating tutor intervention strategies. One promising way is the use of physiological sensors. Within this paper, we study some motivational strategies that were implemented in a serious game called HeapMotiv to support learners’ performance and motivation. We build several hidden Markov models which use Keller’s ARCS model of motivation and electrophysiological data (heart rate HR, skin conductance SC and EEG) and are able to identify physiological patterns correlated with different motivational strategies.

In student modeling, the concept of "mastery learning" i.e. that a student continues to learn a skill till mastery is attained is important. Usually, mastery is defined in terms of most recent student performance. This is also the case with models such as Knowledge Tracing which estimate knowledge solely based on patterns of questions a student gets correct and the task usually is to predict immediate next action of the student. In retrospect however, it is not clear if this is a good definition of mastery since it is perhaps more useful to focus more on student retention over a longer period of time. This paper improves a recently introduced model by Wang and Beck that predicts long term student performance by clustering the students and generating multiple predictions by using a recently developed ensemble technique. Another contribution is that we introduce a novel clustering algorithm we call "Regularity Clustering" and show that it is superior in the task of predicting student retention over more popular techniques such as k-means and Spectral Clustering.

Research on individual differences indicates that students vary in how they interact with and perform while using intelligent tutoring systems (ITSs). However, less research has investigated how individual differences affect students’ interactions with game-based features. This study examines how learning outcomes and interactions with specific game-based features (off-task personalization vs. on-task mini games) within a game-based ITS, iSTART-ME, vary as a function of students’ performance orientation. The current study (n=40) is part of a larger study (n=126) conducted with high school students. The analyses in this study focus on those students assigned to iSTART-ME. Results indicate that students with higher levels of performance orientation perform better during training, progress further within the system, and interact less frequently with off-task game-based features. These results provide further evidence that individual differences play an important role in influencing students’ interactions and achievement within learning environments.

Many intelligent tutoring system (ITS) researchers are looking at ways to detect and to respond to student emotional states (for instance animated pedagogical agents that mirror student emotion). Such interventions are complicated to build, and do not take advantage of the potential for teachers to be part of the process. We present two studies that intervene when a student is having trouble by presenting the student with a YouTube video that is recorded by their own teacher and that delivers a motivational message to help them to persist with the learning session. We experimentally compared two different motivational interventions, which are both grounded in the literature on student affect and motivation. We also had a control condition that had no video. We found that when looking at students’ self-reports on the value of mathematics, we found a main effect of condition for the value-video. In Study 2 we examined whether these 60-second videos could impact homework completion rates and found that in fact homework completion rates were higher for students in the value-video condition. The present research is suggestive of a somewhat novel use of teacher-generated content that could easily be incorporated into other ITSs.

Introduction to the papers presented at the 2013 FLAIRS Conference Special Track on Intelligent Tutoring Systems

In this article, we study the notion of similarity within the context of cluster analysis. We begin by studying different distances commonly used for this task and highlight certain important properties that they might have, such as the use of data distribution or reduced sensitivity to the curse of dimensionality. Then we study inter- and intra-cluster similarities. We identify how the choices made can influence the nature of the clusters.

Finding useful patterns in stock market data requires tremendous analytical skills and effort. To help investors manage their portfolios, we developed a tool for clustering and visualizing stock market data using an unsupervised learning algorithm called Self-Organizing Map. Our tool is intended to assist users in identifying groups of stocks that have similar price movement patterns over a period of time. We performed a visual analysis by comparing the resulting visualization with Yahoo Finance charts. Overall, we found that the Self-Organizing Map algorithm can analyze and cluster the stock market data reasonably.

The impact of random choices is important to many ensemble classifiers algorithms, and the Random Forests is particularly sensible to pseudo-random number generation decisions.This paper proposes an extension to the classical Random Forests method that aims to reduce its sensibility to randomness.The benefits brought by such extension are illustrated by a large number of experiments over 32 different public data sets.

Mining sequential patterns on environment sensor data is a challenging task; the data can present noises and may also contain sparse patterns, which are difficult to be detected. The knowledge extracted from environment sensor data can be used to determine climate changes. However, there is a lack of methods that can handle this kind of database. In this paper, we propose a method to mine sequential patterns in sparse, incomplete and noisy sensor data. The proposed method, called Stretchy Time Windows (STW), allows the mining of sequential patterns that present time gaps between their events. We propose an algorithm to implement STW, called Miner of Stretchy Time Sequences (MSTS). The proposed algorithm works with sequences of any size and uses a balanced strategy to analyze the search space. Our experiments show that MSTS returns sequences that have a longer period of analysis than GSP a traditional frequent pattern mining algorithm. In fact, 5 times larger than GSP and higher number of patterns (2.3 times) when compared to previous methods.