Representation and prediction of student navigational pathways, typically based on neural network (NN) methods, have seen their potential of improving instruction and learning under insufficient human knowledge about learner behavior. However, they are prominently studied in MOOCs and less probed within more institutionalized higher education scenarios. This work extends such research to the context of online college courses. Comparing student navigational sequences through course pages to documents in natural language processing, we apply a skip-gram model to learn vector embedding of course pages, and visualize the learnt vectors to understand the extent to which students' learning pathways align with pre-designed course structure. We find that students who get different letter grades in the end exhibit different levels of adherence to designed sequence. Next, we fit the embedded sequences into a long short-term memory architecture and test its ability to predict next page that a student visits given her prior sequence. The highest accuracy reaches 50.8% and largely outperforms the frequency-based baseline of 41.3%. These results show that neural network methods have the potential to help instructors understand students' learning behaviors and facilitate automated instructional support.

With the nationwide emphasis on improving outcomes for STEM undergraduates, it is important that we not only focus on modifying classroom instruction, but also provide students with the tools to maximize their independent learning time. There has been considerable work in laboratory settings examining two beneficial practices for enhancing learning: spacing and self-testing. In the current study, we examine biology students' study practices, particularly in the context of these two behaviors. We specifically investigate whether a light-touch study skills intervention focused on encouraging spacing and self-testing practices impacted their utilization. Based on pre- and post-course surveys, we found that students report utilizing both beneficial and ineffective study practices and confirm that usage of spacing and self-testing correlates with a higher course grade. We also found that students in the section of the course which received the study skills intervention were more likely to report continued use or adoption of spacing and self-testing compared to students in control sections without the intervention. Surprisingly, we found that underrepresented minorities (URMs) under-utilize self-testing, and that our intervention helped to partially ameliorate this gap. Additionally, we found that URMs who reported self-testing earned similar course grades compared to non-URMs who also self-tested, but that there was a much larger drop in performance for URMs who did not self-test relative to non-URMs who also did not selftest. Overall, we would encourage instructors to dedicate class time towards discussing the merits of beneficial study practices, especially for students that have historically underperformed in STEM disciplines.

Massive Open Online Courses (MOOCs) have the potential to democratize education by providing learners with access to high-quality free online courses. However, evidence supporting this democratization across countries is limited. We explored the question of MOOC democratization by conducting cross-national comparisons of gender differences in the enrollment in and completion of science, technology, engineering, and mathematics (STEM) MOOCs. We found that while females were less likely than males to enroll in STEM MOOCs, they were equally likely to complete them. Further, a higher probability to enroll in STEM MOOCs and smaller gender gaps in STEM MOOC enrollment and completion were found in less gender-equal and less economically developed countries.

Previous research has found that early engagement in MOOCs (e.g., watching lectures, contributing to discussion forums, and submitting assignments) can be used to predict course completion and course grade, which may help instructors and administrators to identify at-risk participants and to target interventions. However, most of these analyses have only focused on the average relationships between engagement and achievement, which may mask important heterogeneity among participant subgroups in MOOCs. This study examines how the relationship between engagement and achievement may vary across the four common behaviorally identified participant subgroups (disengagers, auditors, quiz-takers, and all-rounders) in three MOOC courses offered on the Coursera platform. For each of these subgroups, we used measures of behavioral and cognitive engagement from the first half of the ten-week courses to predict two outcomes: course grade and overall lecture coverage. Results indicate that the same engagement measure may be oppositely associated with achievement for different subgroups and that some engagement measures predict achievement for one subgroup but not another. These findings provide insight into both the benefits and the complexity of studying patterns of engagement from behavioral data and provide suggestions on the improvement of identification of at-risk participants in MOOCs.

Conducted in two sections of an introductory chemistry course, the current study assesses the impact of a partially flipped course compared to traditional lectures on student academic performance, motivation, and perceptions. Although the partially flipped course had little impact on student final exam performance in the current course, it had an overall positive effect on student grades in a subsequent course with presence of interaction effect favoring students with lower high school GPA. By implication, the partially flipped course structure has the potential to bridge the achievement gap over time. Similarly, flipped instruction had an overall positive effect on end-of-quarter student motivation, and academically weaker students showed relatively higher motivation increases. Treatment students rated the flipped course much more positively regarding instructional clarity, instructor quality, and course quality. Compared to the student reflections received in our previous study, negative comments were much less in scope and severity in the current study, owing to a gentler approach for introducing flipped instruction. The gentler approach might allow student to adapt to the format over time. Additionally, greater accountability due to increased assignments of the pre-class work contributed to higher student preparation and improved perceptions.

Distance learning is expanding rapidly in universities. While theoretical and qualitative literature stress the critical role of effective interpersonal interactions in motivating students and facilitating learning in online environments, quantitative evidence on the benefits of increased interpersonal interactions on student learning outcomes is limited. This study examines the effect of providing a voluntary in-person meeting time in a physical classroom and increasing instructor email activity in a fully online precalculus course at a public university. We examine student final exam score and course grade as outcome variables. Student selection into courses was minimal since students only had access to one treatment condition at a time. We further used a propensity score matching strategy to address demographic variations in student characteristics across cohorts. Our results indicate that the increased interpersonal interaction opportunities increased final exam scores by 0.22 standard deviations and improved passing rates by 19 percentage points. Rosenbaum's sensitivity analysis indicates that it is unlikely that these results are due to omitted variable bias.

Student clickstream data can provide valuable insights about student activities in an online learning environment and how these activities inform their learning outcomes. However, given the noisy and complex nature of this data, an ongoing challenge involves devising statistical techniques that capture clear and meaningful aspects of students' click patterns. In this paper, we utilize statistical change detection techniques to investigate students' online behaviors. Using clickstream data from two large university courses, one face-to-face and one online, we illustrate how this methodology can be used to detect when students change their previewing and reviewing behavior, and how these changes can be related to other aspects of students' activity and performance.

This study assessed the impact of flipped instruction on students' out-of-class study time, exam performance, preference, motivation, and perceptions in two sections of a large undergraduate chemistry course. Flipped instruction caused a shift in student workload without appreciably changing the overall study time. The treatment impact on student performance gradually diminished over time, showing a small but statistically significant effect with the final exam. No marked interaction was identified, indicating that flipped instruction benefited students of diverse backgrounds uniformly. Students in the flipped section showed mixed feelings with about one fifth of them displaying polarized attitudes. Open-ended student survey responses revealed non-compliance with pre-class studying as a serious implementation issue: By slowing down the overall pace of the class, it negatively affected students with different study behaviors and characteristics in ways that partly explained the small, diminishing treatment effect and absence of marked interaction. (C) 2016 Elsevier Ltd. All rights reserved.