Due to the increasing interest in integrating data into various instructional decisions, data science skills have become important to promote in Ed.D. students. Meanwhile, there is a similar increase in interest in improving communication skills among engineering students. The needs of these two communities open room for an exchange of skills and mentoring opportunities. Bi-directional, two-way mentoring emphasizes the reciprocal exchange of knowledge, skills, and experiences between mentors and mentees, transcending traditional hierarchical relationships. While these two communities could benefit from each other by helping their counterpart acquire or improve their respective skills, two elements must exist for bi-directional mentoring to be effective: commitment and recognition of each other's value. Therefore, in this research-to-practice WIP article, the researchers explore computer science students' perceptions of the importance of communication skills and the value they see in mentors helping them gain these skills. Mainly, we address the following research questions: RQ1: To what extent do computer science student value communication skills in their academic and future professional pursuits? RQ2: To what extent do computer science students value mentoring to learn and develop communication skills? RQ3: Is there a difference in the value that computer science students pose in learning and developing communication skills with and without mentoring? To answer these questions, we distributed a survey in two different classes at two different institutions in a southeastern region of the US in Spring 2024. In this WIP paper, the researchers present the results of the computer science students' values related to participating in a bi-directional mentoring program to learn communication skills. Overall, students value communication skills and know their critical role in their future. This is shown by high-scale scores obtained in mentoring for communications skills.

This research-to-practice WIP paper reports on a study that explores the comparison between two different exposures to microelectronics in engineering and computer science classrooms. Career choices for the semiconductor sectors are critical, as there is a current shortage of a trained workforce, with legislation such as the CHIPS Act supporting this need. Microelectronics have been introduced to the classrooms with the objective of more hands-on experience, using the best instructional practices. However, using microelectronics in the classroom may affect students' learning outcomes and their career choices. Therefore, in this paper we use Social Cognitive Career Theory (SCCT), to understand how exposure to microelectronics, and self-efficacy in computing tasks affects the interest of students in learning more about microelectronics. We found that longer exposure to microelectronics was correlated with a lower interest with microelectronics, potentially explained by the experiences of students with longer projects and troubleshooting. In addition, we found that most students felt comfortable solving computational problems, and that prior experience with microelectronics did not correlate with higher interest.

Traditional learning-based approaches to student modeling generalize poorly to underrepresented student groups due to biases in data availability. In this paper, we propose a methodology for predicting student performance from their online learning activities that optimizes inference accuracy over different demographic groups such as race and gender. Building upon recent foundations in federated learning, in our approach, personalized models for individual student subgroups are derived from a global model aggregated across all student models via meta-gradient updates that account for subgroup heterogeneity. To learn better representations of student activity, we augment our approach with a self-supervised behavioral pretraining methodology that leverages multiple modalities of student behavior (e.g., visits to lecture videos and participation on forums), and include a neural network attention mechanism in the model aggregation stage. Through experiments on three real-world datasets from online courses, we demonstrate that our approach obtains substantial improvements over existing student modeling baselines in predicting student learning outcomes for all subgroups. Visual analysis of the resulting student embeddings confirm that our personalization methodology indeed identifies different activity patterns within different subgroups, consistent with its stronger inference ability compared with the baselines.

We study the problem of predicting student knowledge acquisition in online courses from clickstream behavior. Motivated by the proliferation of eLearning lecture delivery, we specifically focus on student in-video activity in lectures videos, which consist of content and in-video quizzes. Our methodology for predicting in-video quiz performance is based on three key ideas we develop. First, we model students’ clicking behavior via time-series learning architectures operating on raw event data, rather than defining hand-crafted features as in existing approaches that may lose important information embedded within the click sequences. Second, we develop a self-supervised clickstream pre-training to learn informative representations of clickstream events that can initialize the prediction model effectively. Third, we propose a clustering guided meta-learning-based training that optimizes the prediction model to exploit clusters of frequent patterns in student clickstream sequences. Through experiments on three real-world datasets, we demonstrate that our method obtains substantial improvements over two base-line models in predicting students’ in-video quiz performance. Further, we validate the importance of the pre-training and meta-learning components of our framework through ablation studies. Finally, we show how our methodology reveals insights on video-watching behavior associated with knowledge acquisition for useful learning analytics.

Sketchtivity is a stylus-based intelligent tutoring system that can help instructors automatically provide feedback to their students, saving them the time and effort of providing personalized feedback themselves. The system uses a generic evaluation of perspective, direction, and accuracy to give students feedback on the quality of their sketches. If instructors want to personalize the metrics, the system would require them to provide multiple sets of samples. Therefore, instructors may use instructional team members such as teaching and graduate teaching assistants to provide feedback on the required samples. Compared to that of assistants, the feedback they produce might vary due to expertise and create noise in the training data. To address this problem, we implement a deep neural network that leverages learning to reweight algorithms. The data collected by the instructor from undergraduate and graduate-level rectilinear perspectives sketching is considered the validated sample. In this study, we analyzed the training size requirement for a Multi-Layer Perceptron (MLP) to accurately predict whether or not a stroke was a perspective stroke. We observed that the training data required to predict stroke accuracy is small. In addition, the performance of the algorithm in terms of accuracy was good even under extreme conditions such as having highly unbalanced data and having a small valid set of data. The results from the study support the use of these types of algorithms for future system personalizing to support scalable feedback systems in education.

This research WIP contributes to understanding the relationship between learning engagement in Learning Management System (LMS) and outcomes in an online course. In large engineering courses, it is challenging for instructors to identify who is engaging with course materials at a level necessary to be successful in terms of course outcomes. The purpose of this research WIP study is two-fold: (1) to develop metrics for quantifying learner engagement in online courses, and (2) to explore the relationship between engagement and student success. Our research question is: How does learning engagement relate to course outcomes? We modeled learner engagement on a course level using the following features: number of views per content object, total time spent in the platform, percentage of the course accessed by the learners, percentage of feedback read, and number of attempts per quiz. We used the data collected by the LMS in a large first-year engineering course. We obtained data in Fall 2020, the first semester that many traditional universities were forced mostly or entirely online. After calculating the proposed metrics, we used a linear mixed model to analyze the effect of engagement on learning outcomes. Our linear mixed model shows that all engagement metrics are positively related to the final grade. However, the results also indicate that the relationship between engagement and learning outcomes is not linear; more complex modeling is needed to further explore this relationship.

In this Research-to-Practice Full Paper, two different reflection prompts in the form of unstructured and structured reflections were implemented in an engineering course to guide students towards improved self-regulated learning behaviors, specifically accessing feedback on their assignments. The course setting for this study employed standards-based grading (SBG) which provides rich feedback on students' proficiency with the course learning objectives. Low student access to feedback, delivered through a learning management system (LMS), was seen as a considerable learning opportunity loss. Negative binomial regression models were used to investigate whether semester (2016 or 2017) and refection (presence or absence) had an impact on the (1) number of days students accessed the LMS gradebook or rubrics, (2) the number of times students accessed the gradebook to view grades, or (3) the number of times students accessed rubrics to view feedback. Semester, which relates to implementation changes in the SBG system, significantly increased students' number of days of access and number of gradebook and rubric accesses. Reflection, particularly structured reflection, significantly improved students' access to the rubrics. Pairing reflection with a well-developed SBG system has the potential to improve students' access to feedback.