Many teachers have come to rely on the affordances that computer-based learning platforms offer in regard to aiding in student assessment, supplementing instruction, and providing immediate feedback and help to students as they work through assigned content. Similarly, researchers commonly utilize the large datasets of clickstream logs describing students' interactions with the platform to study learning. For the teachers that use this information to monitor student progress, as well as for researchers, this data provides limited insights into the learning process; this is particularly the case as it pertains to observing and understanding the effort that students are applying to their work. From the perspective of teachers, it is important for them to know which students are attending to and using computer-provided aid and which are taking advantage of the system to complete work without effectively learning the material. In this paper, we conduct a series of analyses based on response time decomposition (RTD) to explore student help-seeking behavior in the context of on-demand hints within a computer-based learning platform with particular focus on examining which students appear to be exhibiting effort to learn while engaging with the system. Our findings are then leveraged to examine how our measure of student effort correlates with later student performance measures.

Despite the abundance of data generated from students' activities in virtual learning environments, the use of supervised machine learning in learning analytics is limited by the availability of labeled data, which can be difficult to collect for complex educational constructs. In a previous study, a subfield of machine learning called Active Learning (AL) was explored to improve the data labeling efficiency. AL trains a model and uses it, in parallel, to choose the next data sample to get labeled from a human expert. Due to the complexity of educational constructs and data, AL has suffered from the cold-start problem where the model does not have access to sufficient data yet to choose the best next sample to learn from. In this paper, we explore the use of past data to warm start the AL training process. We also critically examine the implications of differing contexts (urbanicity) in which the past data was collected. To this end, we use authentic affect labels collected through human observations in middle school mathematics classrooms to simulate the development of AL-based detectors of engaged concentration. We experiment with two AL methods (uncertainty sampling, L-MMSE) and random sampling for data selection. Our results suggest that using past data to warm start AL training could be effective for some methods based on the target population's urbanicity. We provide recommendations on the data selection method and the quantity of past data to use when warm starting AL training in the urban and suburban schools.

New ways to identify students in need of assistance are imperative to the evolution of online tutoring platforms. Currently implemented models to identify struggling students use costly and tedious classroom observation paired with student's platform usage, and are often suitable for only a subset of students. With the recent influx of new students to online tutoring platforms due to COVID-19, a simple method to quickly identify struggling students could help facilitate effective remote learning. To this end, we created an anomaly detection algorithm that models the normal behavior of students during remote learning and recognizes when students deviate from this behavior. We demonstrated how anomalous behavior revealed which students needed additional assistance and predicted student learning outcomes.

It has been shown in multiple studies that expert-created on-demand assistance, such as hint messages, improves student learning in online learning environments. However, there are also evident that certain types of assistance may be detrimental to student learning. In addition, creating and maintaining on-demand assistance are hard and time-consuming. In 2017-2018 academic year, 132,738 distinct problems were assigned inside ASSISTments, but only 38,194 of those problems had on-demand assistance. In order to take on-demand assistance to scale, we needed a system that is able to gather new on-demand assistance and allows us to test and measure its effectiveness. Thus, we designed and deployed TeacherASSIST inside ASSISTments. TeacherASSIST allowed teachers to create on-demand assistance for any problems as they assigned those problems to their students. TeacherASSIST then redistributed on-demand assistance by one teacher to students outside of their classrooms. We found that teachers inside ASSISTments had created 40,292 new instances of assistance for 25,957 different problems in three years. There were 14 teachers who created more than 1,000 instances of on-demand assistance. We also conducted two large-scale randomized controlled experiments to investigate how on-demand assistance created by one teacher affected students outside of their classes. Students who received on-demand assistance for one problem resulted in significant statistical improvement on the next problem performance. The students' improvement in this experiment confirmed our hypothesis that crowd-sourced on-demand assistance was sufficient in quality to improve student learning, allowing us to take on-demand assistance to scale. [This paper was published in: "L@S '20, August 12-14, 2020, Virtual Event, USA," ACM, 2020, pp. 115-124.]

The use of computer-based systems in classrooms has provided teachers with new opportunities in delivering content to students, supplementing instruction, and assessing student knowledge and comprehension. Among the largest benefits of these systems is their ability to provide students with feedback on their work and also report student performance and progress to their teacher. While computer-based systems can automatically assess student answers to a range of question types, a limitation faced by many systems is in regard to open-ended problems. Many systems are either unable to provide support for open-ended problems, relying on the teacher to grade them manually, or avoid such question types entirely. Due to recent advancements in natural language processing methods, the automation of essay grading has made notable strides. However, much of this research has pertained to domains outside of mathematics, where the use of open-ended problems can be used by teachers to assess students' understanding of mathematical concepts beyond what is possible on other types of problems. This research explores the viability and challenges of developing automated graders of open-ended student responses in mathematics. We further explore how the scale of available data impacts model performance. Focusing on content delivered through the ASSISTments online learning platform, we present a set of analyses pertaining to the development and evaluation of models to predict teacher-assigned grades for student open responses.

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.

We examine the use of computer-based learning in the classroom and the effect of immediate feedback on student performance. Since it is well known in educational research that it is possible to observe a Matthew Effect in which the rich get richer, we wanted to see if feedback was useful for low prior knowledge students, as defined by students whose pretest score was at or below the median. In this counterbalanced randomized controlled trial, 243 tenth and eleventh grade mathematics students were exposed to one of two conditions, as we measured their learning from: 1) immediate feedback (where the computer told them correctness and they could also ask for hints) or 2) practice only (where they received feedback only after taking a posttest). Results suggest that immediate feedback from computer-based learning tasks benefit both high and low prior knowledge students, with low prior knowledge students exhibiting greater gains. The implications of these findings support further investigation into the use of computer-based learning tasks that provide immediate feedback.

Persistence is a crucial trait for learners. However, a common issue in mastery learning is that persistence is not always productive, a construct termed wheel-spinning. In this paper, we extend on prior work to develop wheel-spinning detectors in the ASSISTments learning system that distinguish between non-persistence, productive persistence and wheel-spinning. To understand how quickly we can detect each state, we use data from different numbers of practice opportunities and compare model performance across student-problem set pairs. We identify that a model constructed using data from the first nine practice opportunities outperforms models using less practice data. However, it is possible to differentiate students who will eventually wheel-spin from learners who will persist productively using data from only the first three opportunities. Wheel-spinning can be differentiated from non-persistence from the first five opportunities, and non-persistence can be differentiated from productive persistence from the first seven opportunities. These results show that early differentiation between wheel-spinning and productive persistence is feasible. These detectors relied upon hint requests, the correctness of prior opportunities, and the amount of practice and time on the skill. Identifying predictive features offer insights into the impact of in-system behaviors on wheel-spinning and guide the system design.

Assessment in the context of foreign language learning can be difficult and time-consuming for instructors. Distinctive from other domains, language learning often requires teachers to assess each student's ability to speak the language, making this process even more time-consuming in large classrooms which are particularly common in post-secondary settings; considering that language instructors often assess students through assignments requiring recorded audio, a lack of tools to support such teachers makes providing individual feedback even more challenging. In this work, we seek to explore the development of tools to automatically assess audio responses within a college-level Chinese language-learning course. We build a model designed to grade student audio assignments with the purpose of incorporating such a model into tools focused on helping both teachers and students in real classrooms. Building upon our prior work which explored features extracted from audio, the goal of this work is to explore additional features derived from tone and speech recognition models to help assess students on two outcomes commonly observed in language learning classes: fluency and accuracy of speech. In addition to the exploration of features, this work explores the application of Siamese deep learning models for this assessment task. We find that models utilizing tonal features exhibit higher predictive performance of student fluency while text-based features derived from speech recognition models exhibit higher predictive performance of student accuracy of speech.

Randomized controlled trials (RCTs) admit unconfounded design-based inference--randomization largely justifies the assumptions underlying statistical effect estimates--but often have limited sample sizes. However, researchers may have access to big observational data on covariates and outcomes from RCT non-participants. For example, data from A/B tests conducted within an educational technology platform exist alongside historical observational data drawn from student logs. We outline a design-based approach to using such observational data for variance reduction in RCTs. First, we use the observational data to train a machine learning algorithm predicting potential outcomes using covariates, and use that algorithm to generate predictions for RCT participants. Then, we use those predictions, perhaps alongside other covariates, to adjust causal effect estimates with a flexible, design-based covariate-adjustment routine. In this way there is no danger of biases from the observational data leaking into the experimental estimates, which are guaranteed to be exactly unbiased regardless of whether the machine learning models are "correct" in any sense or whether the observational samples closely resemble RCT samples. We demonstrate the method in analyzing 33 randomized A/B tests, and show that it decreases standard errors relative to other estimators, sometimes substantially. [This is the online version of an article published in "Journal of Causal Inference." Additional funding was provided by the U.S. Department of Education's Graduate Assistance in Areas of National Need (GAANN) program.]