Massive Open Online Courses (MOOC) are seen as a next step in distance online learning. In the MOOC vision, large numbers of students can access the course content over the Internet and complete courses at their own pace while interacting with their peers and instructors online. Despite the initial enthusiasm about MOOCs, large number of students were observed dropping out of the online courses. In this paper, we pinpoint the reasons behind the high student dropout rate and discuss how the interaction capabilities of MOOCs contributed towards the low completion rate.
Understanding Self-Regulated Learning Behavior Among High and Low Dropout Risk Students During CS1: Combining Trace Logs, Dropout Prediction and Self-Reports
Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models
School of Information, Renmin University of China（中国人民大学信息学院）；Institute of Education, Tsinghua University（清华大学教育学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Language Technology Institute, Carnegie Mellon University（卡内基梅隆大学语言技术学院）
Early identification of college dropouts can provide tremendous value for improving student success and institutional effectiveness, and predictive analytics are increasingly used for this purpose. However, ethical concerns have emerged about whether including protected attributes in the prediction models discriminates against underrepresented student groups and exacerbates existing inequities. We examine this issue in the context of a large U.S. research university with both residential and fully online degree-seeking students. Based on comprehensive institutional records for this entire stud…
Through the analysis of cultural, socioeconomic and academic performance aspects it is possible to map the profile of the students and their motivations to drop out. This article aims to create a computational tool for data visualization that allows drawing the profile of students to support educational institutions managers in the definition of dropout avoidance policies. We present a method to treat data collected by higher education institutions over the years, analyze them to understand the dropout and provide that information to the university and the general public. Eight questions were …
Each year, roughly 30% of first-year students at US baccalaureate institutions do not return for their second year and over $9 billion is spent educating these students. Yet, little quantitative research has analyzed the causes and possible remedies for student attrition. Here, we describe initial efforts to model student dropout using the largest known dataset on higher education attrition, which tracks over 32,500 students' demographics and transcript records at one of the nation's largest public universities. Our results highlight several early indicators of student attrition and show that …
One of the long term goals of any college or university is increasing the student retention. The negative impact of student dropout are clear to students, parents, universities and society. The positive effect of decreasing student attrition is also self-evident including higher chance of having a better career and higher standard of life for college graduate. In view of these reasons, directors in higher education feel increasingly pressurized to outline and implement strategies to increase student retention. In this paper, we provide a detailed analysis of the student attrition problem and u…
The accurate estimation of students' grades in future courses is important as it can inform the selection of next term's courses and create personalized degree pathways to facilitate successful and timely graduation. This paper presents future-course grade predictions methods based on sparse linear models and low-rank matrix factorizations that are specific to each course or student-course tuple. These methods identify the predictive subsets of prior courses on a course-by-course basis and better address problems associated with the not-missing-at-random nature of the student-course historical…
Student dropout prediction is an indispensable for numerous intelligent systems to measure the education system and success rate of any university as well as throughout the university in the world. Therefore, it becomes essential to develop efficient methods for prediction of the students at risk of dropping out, enabling the adoption of proactive process to minimize the situation. Thus, this research work propose a prototype machine learning tool which can automatically recognize whether the student will continue their study or drop their study using classification technique based on decision…
This research is comparing learning environments to students dropout intentions. While using statistics I looked at data and the correlations between two articles to see how the two studies looked side to side. Learning environments and dropout intentions can both have vary effects on students. They can both determine if a student does well, or bad in school especially math.
This paper provides an overview of students behavior analysis on a learning management system (LMS), Blackboard (Bb) Learn for a core data communications course of the Undergraduate IT program in the Information Sciences and Technology (IST) Department at George Mason University (GMU). This study is an attempt to understand the navigational behavior of students on Blackboard Learn which can be further attributed to the overall performance of the students. In total, 160 undergraduate students participated in the study. Vast amount of students activities data across all four sections of the cour…
Online tools provide unique access to research students' study habits and problem-solving behavior. In MOOCs, this online data can be used to inform instructors and to provide automatic guidance to students. However, these techniques may not apply in blended courses with face to face and online components. We report on a study of integrated user-system interaction logs from 3 computer science courses using four online systems: LMS, forum, version control, and homework system. Our results show that students rarely work across platforms in a single session, and that final class performance can b…
This article is about the author's experience with developing and teaching an introductory electrical engineering course for students of Faculty (department) of Information Technology of a Russian university. The curriculum of this department conforms to typical computer science curricula of US engineering schools with a noticeable omission of comparable electrical engineering courses. When developing the course, I did my best to pay attention to learning preferences of the department's student body. I also hoped to contribute to a degree to meeting labor market demands for developers of elect…
Students' satisfaction plays a vital role in success of an educational institute. Hence, many educational institutes continuously improve their service to produce a supportive learning environment to satisfy the student need. For this reason, educational institutions collect student satisfaction data to make decision about institutional quality, but till now it cannot be determined because student satisfaction is a complex matter which is influenced by variety of characteristics of students and institutions. There are many studies have been performed to inspect student satisfaction in the form…
In order to obtain reliable accuracy estimates for automatic MOOC dropout predictors, it is important to train and test them in a manner consistent with how they will be used in practice. Yet most prior research on MOOC dropout prediction has measured test accuracy on the same course used for training the classifier, which can lead to overly optimistic accuracy estimates. In order to understand better how accuracy is affected by the training+testing regime, we compared the accuracy of a standard dropout prediction architecture (clickstream features + logistic regression) across 4 different tra…
This Full Paper in the Research-To-Practice Category presents a long-term study about the effects of a student-centered course on communication and professional skills on students' thoughts, attitudes, and behavior. The course is offered at a European university as part of a computer science master's program. This paper shares the design and challenges of a longitudinal study that reaches ten years behind and employs a mixed-methods approach. Besides presenting and interpreting the findings, we shed light on which features tend to stay on students' minds and impact their way of being and actin…
We present a novel learning analytics approach, for analyzing the usage of resources in MOOCs. Our target stakeholders are the course designers who aim to evaluate their learning materials. In order to gain insight into the way educational resources are used, we view dropout behaviour in an atypical manner: Instead of using it as an indicator of failure, we use it as a mean to compute other features. For this purpose, we developed a prototype, called RUAF, that can be applied to the data format provided by FutureLearn. As a proof of concept, we perform a study by applying this tool to the inte…
Massive Open Online Courses (MOOCs) once offered the promise of accessibility and affordability. However, MOOCs typically lack expert feedback and social interaction, and have low student engagement and retention. Thus, alternative programs for online education have emerged including an online graduate program in computer science at a major public university in USA. This program is considered a success with over 9000 students now enrolled in the program. We adopt the perspective of cognitive science to answer the question why do only some online educational courses succeed? We measure learner …
Contribution: This study examined student effort and performance in an introductory programming course with respect to student-held implicit theories and self-efficacy. Background: Implicit theories and self-efficacy shed a light into understanding academic success, which must be considered when developing effective learning strategies for programming. Research Questions: Are implicit theories of intelligence and programming, and programming-efficacy related to each other and student success in programming? Is it possible to predict student course performance using a subset of these constructs…
We analyze learning data of an e-assessment platform for an introductory mathematical statistics course, more specifically the time of the day when students learn. We propose statistical models to predict students' success and to describe their behavior with a special focus on the following aspects. First, we find that learning during daytime and not at nighttime is a relevant variable for predicting success in final exams. Second, we observe that good and very good students tend to learn in the afternoon, while some students who failed our course were more likely to study at night but not suc…
This study attempted to develop fair, relevant, and content-valid assessment tools for capstone project courses. Toward this goal, new rating instruments based on the concept of rubrics were proposed. To ensure that the new instruments were valid and fair, several meetings with faculty and students of the computing science departments (i.e., Computer Science and Information Technology) were successively conducted. Eight faculty members and 10 students participated in the study. The final versions of the instruments were completed after a series of careful deliberations with faculty and student…
In higher educational institutes, many students have to struggle hard to complete different courses since there is no dedicated support offered to students who need special attention in the registered courses. Machine learning techniques can be utilized for students' grades prediction in different courses. Such techniques would help students to improve their performance based on predicted grades and would enable instructors to identify such individuals who might need assistance in the courses. In this paper, we use Collaborative Filtering (CF), Matrix Factorization (MF), and Restricted Boltzma…
Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsity and overfitting, recent sample-level contrastive learning helps to alleviate this issue. One major limitation of sample-level approaches is that they regard students' behavior interaction sequences as a bundle, so they often fail to encode temporal contexts and track their dynamic changes, making it hard to find optimal representations for knowledge tracing and dropout predic…
One of the leading university goals is to provide the students with the necessary skills for better functioning in their future studies. Gaining and developing skills, both technical and soft skills, are the critical building blocks for a successful career. The traditional teaching process, which includes delivering lectures and conducting exams, emphasizes the upliftment of technical knowledge rather than building self-esteem and enhancing skills development among students. Development of non-technical skills like self-esteem, life-long learning among students is vital for a successful career…
Riiid! AI Research（Riiid人工智能研究院）；Yale University（耶鲁大学）；University of Michigan（密歇根大学）
Student dropout prediction provides an opportunity to improve student engagement, which maximizes the overall effectiveness of learning experiences. However, researches on student dropout were mainly conducted on school dropout or course dropout, and study session dropout in a mobile learning environment has not been considered thoroughly. In this paper, we investigate the study session dropout prediction problem in a mobile learning environment. First, we define the concept of the study session, study session dropout and study session dropout prediction task in a mobile learning environment. …
Students' interactions with online tools can provide us with insights into their study and work habits. Prior research has shown that these habits, even as simple as the number of actions or the time spent on online platforms can distinguish between the higher performing students and low-performers. These habits are also often used to predict students' performance in classes. One key feature of these actions that is often overlooked is how and when the students transition between different online platforms. In this work, we study sequences of student transitions between online tools in blended…
University of Miami（迈阿密大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Given the variability in student learning it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence recommendations to students. First, a forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate. The algorithm accounts for prerequisite requirements (typically present in higher level education) and course availability. Second, using the tools of multi-armed bandits, an…
The identification and analysis of student satisfaction is a challenging issue. This is becoming increasingly important since a measure of student satisfaction is taken as an indication of how well a course has been taught. However, it remains a challenging problem as student satisfaction has various aspects. In this paper, we formulate the student satisfaction estimation as a prediction problem where we predict different levels of student satisfaction and infer the influential predictors related to course and instructor. We present five different aspects of student satisfaction in terms of 1)…
Paris-Saclay University（巴黎-萨克雷大学）；Instituto Nacional de Astrofísica, Óptica y Electrónica（国家天体物理、光学与电子学研究所）
Data-driven decision making is serving and transforming education. We approached the problem of predicting students' performance by using multiple data sources which came from online courses, including one we created. Experimental results show preliminary conclusions towards which data are to be considered for the task.
Millions of learners worldwide are now using intelligent tutoring systems (ITSs). At their core, ITSs rely on machine learning algorithms to track each user's changing performance level over time to provide personalized instruction. Crucially, student performance models are trained using interaction sequence data of previous learners to analyse data generated by future learners. This induces a cold-start problem when a new course is introduced for which no training data is available. Here, we consider transfer learning techniques as a way to provide accurate performance predictions for new cou…
The high level of attrition and low rate of certification in Massive Open Online Courses (MOOCs) has prompted a great deal of research. Prior researchers have focused on predicting dropout based upon behavioral features such as student confusion, click-stream patterns, and social interactions. However, few studies have focused on combining student logs with forum data. In this work, we use data from two different offerings of the same MOOC. We conduct a survival analysis to identify likely dropouts. We then examine two classes of features, social and behavioral, and apply a combination of mode…
Massive Open Online Course (MOOC) platforms incorporate large course catalogs from which individual students may register multiple courses. We performed a network-based analysis of student achievement, considering how course-course interactions may positively or negatively affect student success. Our dataset included 378,000 users and 1,000,000 unique registration events in France Universite Numerique (FUN), a national MOOC platform. We adapt reliability theory to model certificate completion rates with a Weibull survival function, following the intuition that students "survive" in a course fo…
The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas Tech University（德克萨斯理工大学）
This paper investigates how high school students approach computing through an introductory computer science course situated in the Logic Programming (LP) paradigm. This study shows how novice students operate within the LP paradigm while engaging in foundational computing concepts and skills, and presents a case for LP as a viable paradigm choice for introductory CS courses.
Educational software data promises unique insights into students' study behaviors and drivers of success. While much work has been dedicated to performance prediction in massive open online courses, it is unclear if the same methods can be applied to blended courses and a deeper understanding of student strategies is often missing. We use pattern mining and models borrowed from Natural Language Processing (NLP) to understand student interactions and extract frequent strategies from a blended college course. Fine-grained clickstream data is collected through Diderot, a non-commercial educationa…
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…
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 c…
Carnegie Mellon University（卡内基梅隆大学）；University of California, Berkeley（加州大学伯克利分校）
Course load analytics (CLA) inferred from LMS and enrollment features can offer a more accurate representation of course workload to students than credit hours and potentially aid in their course selection decisions. In this study, we produce and evaluate the first machine-learned predictions of student course load ratings and generalize our model to the full 10,000 course catalog of a large public university. We then retrospectively analyze longitudinal differences in the semester load of student course selections throughout their degree. CLA by semester shows that a student's first semester …
Beyond classical and contemporary models: a transformative AI framework for student dropout prediction in distance learning using RAG, Prompt engineering, and Cross-modal fusion
Online courses, as a pedagogical approach to teaching, boomed during this Coronavirus Disease 2019 pandemic era. Universities shifted from traditional face to face classes to online distance learning due to the cause of the pandemic. This study aimed to determine how effective an online course is in learning a programming course. The study utilized mixed method research applied through a validated survey questionnaire consisting of closed and open ended questions. Python programming was the course selected to undergo the study and underwent an evaluation to determine the students' responses. S…
University of Califonia, San Diego 9500 Gilman Dr San Diego California 92093-0404；University of Califonia, San Diego
We describe our experience teaching an intensive capstone course in which pairs of students build the hardware and software for a remote-controller quad-rotor aircraft (i.e., a quadcopter or "drone") from scratch in one 10-week quarter. The course covers printed circuit board (PCB) design and assembly, basic control theory and sensor fusion, and embedded systems programming. To reduce the workload on course staff and provide higher-quality feedback on student designs, we have implemented an automated PCB design checking tool/autograder. We describe the course content in detail, identify the ch…
University course ranking forums are a popular means of disseminating information about satisfaction with the quality of course content and instruction, especially with undergraduate students. A variety of policy decisions by university administrators, instructional designers and teaching staff affect how students perceive the efficacy of pedagogies employed in a given course, in class and online. While there is a large body of research on qualitative driving factors behind the use of academic rating sites, there is little investigation of the (potential) implicit student bias on said forums t…
The large-scale online management systems (e.g. Moodle), online web forums (e.g. Piazza), and online homework systems (e.g. WebAssign) have been widely used in the blended courses recently. Instructors can use these systems to deliver class content and materials. Students can communicate with the classmates, share the course materials, and discuss the course questions via the online forums. With the increased use of the online systems, a large amount of students' interaction data has been collected. This data can be used to analyze students' learning behaviors and predict students' learning ou…
