Search for: All records

Given the increasing need for skilled workers in science, technology, engineering, and mathematics (STEM), there is a burgeoning interest to encourage young students to pursue a career in STEM fields. Middle school is an opportune time to guide students' interests towards STEM disciplines, as they begin to think about and plan for their career aspirations. Previous studies have shown that detectors of students' learning, affect, and engagement, measured from their interactions within an online tutoring system during middle school, are strongly predictive of their eventual choice to attend college and enroll in a STEM major (San Pedro et al., 2013; 2014). In this study, we extend prior work by examining how the constructs measured by these detectors relate to the decision to participate in a STEM career after college. Findings from this study suggest that subtle forms of disengagement (i.e., gaming the system, carelessness) are predictive and can potentially provide actionable information for teachers and counselors to apply early intervention in STEM learning. In general, this study sheds light on the relevant student factors that influence STEM participation years later, providing a more comprehensive understanding of student STEM trajectories. 

This special issue includes papers from some of the leading competitors in the ASSISTments Longitudinal Data Mining Competition 2017, as well as some research from non-competitors, using the same data set. In this competition, participants attempted to predict whether students would choose a career in a STEM field or not, making this prediction using a click-stream dataset from middle school students working on math assignments inside ASSISTments, an online tutoring platform. At the conclusion of the competition on December 3rd, 2017, there were 202 participants, 74 of whom submitted predictions at least once. In this special issue, some of the leading competitors present their results and what they have learned about the link between behavior in online learning and future STEM career development. 

Sensor-free affect detectors can detect student affect using their activities within intelligent tutoring systems or other online learning environments rather than using sensors. This technology has made affect detection more scalable and less invasive. However, existing detectors are either interpretable but less accurate (e.g., classical algorithms such as logistic regression) or more accurate but uninterpretable (e.g., neural networks). We investigate the use of a new type of neural networks that are monotonic after the first layer for affect detection that can strike a balance between accuracy and interpretability. Results on a real- world student affect dataset show that monotonic neural networks achieve comparable detection accuracy to their non-monotonic counterparts while offering some level of interpretability. 

There is a long history of research on the development of models to detect and study student behavior and affect. Developing computer-based models has allowed the study of learning constructs at fine levels of granularity and over long periods of time. For many years, these models were developed using features based on previous educational research from the raw log data. More recently, however, the application of deep learning models has often skipped this feature-engineering step by allowing the algorithm to learn features from the fine-grained raw log data. As many of these deep learning models have led to promising results, researchers have asked which situations may lead to machine-learned features performing better than expert-generated features. This work addresses this question by comparing the use of machine-learned and expert-engineered features for three previously-developed models of student affect, off-task behavior, and gaming the system. In addition, we propose a third feature-engineering method that combines expert features with machine learning to explore the strengths and weaknesses of these approaches to build detectors of student affect and unproductive behaviors. 

There is a long history of research on the development of models to detect and study student behavior and affect. Developing computer-based models has allowed the study of learning constructs at fine levels of granularity and over long periods of time. For many years, these models were developed using features based on previous educational research from the raw log data. More recently, however, the application of deep learning models has often skipped this feature engineering step by allowing the algorithm to learn features from the fine-grained raw log data. As many of these deep learning models have led to promising results, researchers have asked which situations may lead to machine-learned features performing better than expert-generated features. This work addresses this question by comparing the use of machine-learned and expert-engineered features for three previously-developed models of student affect, off-task behavior, and gaming the system. In addition, we propose a third feature-engineering method that combines expert features with machine learning to explore the strengths and weaknesses of these approaches to build detectors of student affect and unproductive behaviors. 

Student affect has been found to correlate with short- and long-term learning outcomes, including college attendance as well as interest and involvement in Science, Technology, Engineering, and Mathematics (STEM) careers. However, there still remain significant questions about the processes by which affect shifts and develops during the learning process. Much of this research can be split into affect dynamics, the study of the temporal transitions between affective states, and affective chronometry, the study of how an affect state emerges and dissipates over time. Thus far, these affective processes have been primarily studied using field observations, sensors, or student self-report measures; however, these approaches can be coarse, and obtaining finer grained data produces challenges to data fidelity. Recent developments in sensor-free detectors of student affect, utilizing only the data from student interactions with a computer based learning platform, open an opportunity to study affect dynamics and chronometry at moment-to-moment levels of granularity. This work presents a novel approach, applying sensor-free detectors to study these two prominent problems in affective research.