With the rapid emergence of K-12 online learning platforms, a new era of education has been opened up. It is crucial to have a dropout warning framework to preemptively identify K-12 students who are at risk of dropping out of the online courses. Prior researchers have focused on predicting dropout in Massive Open Online Courses (MOOCs), which often deliver higher education, i.e., graduate level courses at top institutions. However, few studies have focused on developing a machine learning approach for students in K-12 online courses. In this paper, we develop a machine learning framework to conduct accurate at-risk student identification specialized in K-12 multimodal online environments. Our approach considers both online and offline factors around K-12 students and aims at solving the challenges of (1) multiple modalities, i.e., K-12 online environments involve interactions from different modalities such as video, voice, etc; (2) length variability, i.e., students with different lengths of learning history; (3) time sensitivity, i.e., the dropout likelihood is changing with time; and (4) data imbalance, i.e., only less than 20\% of K-12 students will choose to drop out the class. We conduct a wide range of offline and online experiments to demonstrate the effectiveness of our approach. In our offline experiments, we show that our method improves the dropout prediction performance when compared to state-of-the-art baselines on a real-world educational dataset. In our online experiments, we test our approach on a third-party K-12 online tutoring platform for two months and the results show that more than 70\% of dropout students are detected by the system.
Improving prediction of students' performance in intelligent tutoring systems using attribute selection and ensembles of different multimodal data sources
Pontifical Catholic University of Ecuador（厄瓜多尔天主教大学）；University of Oviedo（奥维耶多大学）；University of Central Florida（中佛罗里达大学）；University of Córdoba（科尔多瓦大学）
Online distance learning is highly learner-centred, requiring different skills and competences from learners, as well as alternative approaches for instructional design, student support, and provision of resources. Learner autonomy and self-regulated learning (SRL) in online learning settings are considered key success factors that predict student performance. SRL comprises processes of planning, monitoring, action and reflection according to Zimmerman. And typically focuses on three key features of learners: (1) use of SRL strategies, (2) responsiveness to self-oriented feedback about learnin…
Learning management systems (LMSs) have become essential in higher education and play an important role in helping educational institutions to promote student success. Traditionally, LMSs have been used by postsecondary institutions in administration, reporting, and delivery of educational content. In this paper, we present an additional use of LMS by using its data logs to perform data-analytics and identify academically at-risk students. The data-driven insights would allow educational institutions and educators to develop and implement pedagogical interventions targeting academically at-ris…
Instructors and students alike are often focused on the grade in programming assignments as a key measure of how well a student is mastering the material and whether a student is struggling. This can be, however, misleading. Especially when students have access to auto-graders, their grades may be heavily skewed. In this paper, we analyze student assignment submission data collected from a functional programming course taught at McGill university incorporating a wide range of features. In addition to the grade, we consider activity time data, time spent, and the number of static errors. This a…
Automatic analysis of teacher and student interactions could be very important to improve the quality of teaching and student engagement. However, despite some recent progress in utilizing multimodal data for teaching and learning analytics, a thorough analysis of a rich multimodal dataset coming for a complex real learning environment has yet to be done. To bridge this gap, we present a large-scale MUlti-modal Teaching and Learning Analytics (MUTLA) dataset. This dataset includes time-synchronized multimodal data records of students (learning logs, videos, EEG brainwaves) as they work in vari…
Blended courses have become the norm in post-secondary education. Universities use large-scale learning management systems to manage class content. Instructors deliver readings, lectures, and office hours online; students use intelligent tutors, web forums, and online submission systems; and classes communicate via web forums. These online tools allow students to form new social networks or bring social relationships online. They also allow us to collect data on students' social relationships. In this paper we report on our research on community formation in blended courses based on online for…
Growth mindset interventions foster students' beliefs that their abilities can grow through effort and appropriate strategies. However, not every student benefits from such interventions - yet research identifying which student factors support growth mindset interventions is sparse. In this study, we utilized machine learning methods to predict growth mindset effectiveness in a nationwide experiment in the U.S. with over 10,000 students. These methods enable analysis of arbitrarily-complex interactions between combinations of student-level predictor variables and intervention outcome, defined …
Harvard University（哈佛大学）；University of Maryland（马里兰大学）；Stanford University（斯坦福大学）
Responsive teaching is a highly effective strategy that promotes student learning. In math classrooms, teachers might "funnel" students towards a normative answer or "focus" students to reflect on their own thinking, deepening their understanding of math concepts. When teachers focus, they treat students' contributions as resources for collective sensemaking, and thereby significantly improve students' achievement and confidence in mathematics. We propose the task of computationally detecting funneling and focusing questions in classroom discourse. We do so by creating and releasing an annotat…
The COVID-19 pandemic has thrown natural life out of gear across the globe. Strict measures are deployed to curb the spread of the virus that is causing it, and the most effective of them have been social isolation. This has led to wide-spread gloom and depression across society but more so among the young and the elderly. There are currently more than 200 million college students in 186 countries worldwide, affected due to the pandemic. The mode of education has changed suddenly, with the rapid adaptation of e-learning, whereby teaching is undertaken remotely and on digital platforms. This st…
How effective are VLMs in assisting humans in inferring the quality of mental models from Multimodal short answers?
Department of Computer Science and Engineering, IIT Bombay（印度理工学院班加罗尔分校计算机科学与工程系）；Center for Educational Technology, IIT Bombay（印度理工学院班加罗尔分校教育技术中心）；School of Management, Mahindra University（马恒达大学管理学院）
A Predictive Model using Machine Learning Algorithm in Identifying Students Probability on Passing Semestral Course
Lyceum of the Philippines University – Cavite（菲律宾大学莱西姆大学卡维特分校）；University of the East（东方大学）；Gokongwei College of Engineering, De La Salle University（德拉萨勒大学戈孔韦工程学院）
Whenever students use any drilling system the question arises how much of their learning is meaningful learning vs memorisation through repetition or rote learning. Although both types of learning have their place in an educational system it is important to be able to distinguish between these two approaches to learning and identify options which can dislodge students from rote learning and motivate them towards meaningful learning. The tutor-web is an online drilling system. The design aim of the system is learning rather than evaluation. This is done by presenting students with multiple-choi…
Predictive models for identifying at-risk students early can help teaching staff direct resources to better support them, but there is a growing concern about the fairness of algorithmic systems in education. Predictive models may inadvertently introduce bias in who receives support and thereby exacerbate existing inequities. We examine this issue by building a predictive model of student success based on university administrative records. We find that the model exhibits gender and racial bias in two out of three fairness measures considered. We then apply post-hoc adjustments to improve model…
Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing
Shandong University of Finance and Economics（山东财经大学）；Hong Kong Polytechnic University（香港理工大学）；Shandong University（山东大学）；Shandong Jianzhu University（山东建筑大学）
Which CS1 Students Will Fail? Identifying Digital Markers from Learning Analytics in Computer Systems and Architecture Using Weighted Academic Momentum and Interaction Logs
University of Zambia（赞比亚大学）；DataLab Research Group, University of Zambia（赞比亚大学数据实验室研究组）
