scholarly journals Predicting Student Performance and Deficiency in Mastering Knowledge Points in MOOCs Using Multi-Task Learning

Entropy ◽  
2019 ◽  
Vol 21 (12) ◽  
pp. 1216 ◽  
Author(s):  
Shaojie Qu ◽  
Kan Li ◽  
Bo Wu ◽  
Xuri Zhang ◽  
Kaihao Zhu
Keyword(s):  
Student Performance ◽  
Short Term Memory ◽  
Online Courses ◽  
Recall Rate ◽  
Learning Material ◽  
Online Behavior ◽  
Overall Performance ◽  
Predicting Student Performance ◽  
And Performance ◽  
Using Data

Massive open online courses (MOOCs), which have been deemed a revolutionary teaching mode, are increasingly being used in higher education. However, there remain deficiencies in understanding the relationship between online behavior of students and their performance, and in verifying how well a student comprehends learning material. Therefore, we propose a method for predicting student performance and mastery of knowledge points in MOOCs based on assignment-related online behavior; this allows for those providing academic support to intervene and improve learning outcomes of students facing difficulties. The proposed method was developed while using data from 1528 participants in a C Programming course, from which we extracted assignment-related features. We first applied a multi-task multi-layer long short-term memory-based student performance predicting method with cross-entropy as the loss function to predict students’ overall performance and mastery of each knowledge point. Our method incorporates the attention mechanism, which might better reflect students’ learning behavior and performance. Our method achieves an accuracy of 92.52% for predicting students’ performance and a recall rate of 94.68%. Students’ actions, such as submission times and plagiarism, were related to their performance in the MOOC, and the results demonstrate that our method predicts the overall performance and knowledge points that students cannot master well.

scholarly journals Tracking Student Performance Tool for Predicting Students EBPP in Online Courses

2021 ◽  
Vol 16 (23) ◽  
pp. 140-157
Author(s):  
Iman Rashid Al-Kindi ◽  
Zuhoor Al-Khanjari
Keyword(s):  
Online Learning ◽  
Student Engagement ◽  
Student Performance ◽  
Learning Environments ◽  
Online Courses ◽  
Online Learning Environments ◽  
Specific Focus ◽  
Overall Performance ◽  
And Performance ◽  
Improving Student Performance

Our motivation in this paper is to predict student Engagement (E), Behavior (B), Personality (P) and Performance (P) via designing a Tracking Student Perfor-mance Tool (TSPT) that obtained data directly from Moodle logs of any selected courses. The proposed tool follows the predictive EBP model that focuses mainly on student's EBP and Performance where the instructor could use it to monitor the overall performance of his/her students during the course. The results of test-ing the tool show that the developed tool gives the same as manual results analy-sis. Analyzing Moodle log of any course using such a tool is supposed to help with the implementation of similar courses and helpful for the instructor in re-designing it in a way that is more beneficial to the students. This paper sheds light on the importance of studying student's EBPP and provides interesting possibili-ties for improving student performance with a specific focus on designing online learning environments or contexts.

scholarly journals Specialization and Performance: Evidence from NCAA 4 × 400 m Relay Times

Economies ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 96
Author(s):  
Candon Johnson ◽  
Robert Schultz ◽  
Joshua C. Hall
Keyword(s):  
Performance Measure ◽  
Division I ◽  
Division Iii ◽  
Overall Performance ◽  
The Difference ◽  
And Performance ◽  
Using Data ◽  
The Impact ◽  
Better Than

This paper investigates the impact of having open 400 meter (400 m) runners on NCAA relay teams. Using data from 2012–2016 containing the top 100 4 × 400 m in each NCAA Division relay times for each year, it is found that more 400 m specialists lead to an increase in the overall performance of the team, measured by a decrease in relay times. The effect is examined across Division I–III NCAA track teams. The results are consistent across each division. We view this as a test of the role of specialization on performance. Using runners who specialize in 400 m races should increase overall team performance as long as specialization does not lead to an inefficient allocation of team human capital. An additional performance measure is used examining the difference between projected and actual relay times. Divisions I and II are found to perform better than projected with an increase in 400 m runners, but there is no effect found in Division III.

scholarly journals Analysis of Time-on-Task, Behavior Experiences, and Performance in Two Online Courses with Different Authentic Learning Tasks

2017 ◽  
Vol 18 (2) ◽  
Author(s):  
Sanghoon Park
Keyword(s):  
Student Performance ◽  
Online Courses ◽  
Learning Activities ◽  
Time On Task ◽  
Design Development ◽  
Behavioral Interactions ◽  
Learning Tasks ◽  
And Performance ◽  
Authentic Discussion ◽  
Interactions With Peers

<p class="3">This paper reports the findings of a comparative analysis of online learner behavioral interactions, time-on-task, attendance, and performance at different points throughout a semester (beginning, during, and end) based on two online courses: one course offering authentic discussion-based learning activities and the other course offering authentic design/development-based learning activities. Web log data were collected to determine the number of learner behavioral interactions with the Moodle learning management system (LMS), the number of behavioral interactions with peers, the time-on-task for weekly tasks, and the recorded attendance. Student performance on weekly tasks was also collected from the course data. Behavioral interactions with the Moodle LMS included resource viewing activities and uploading/downloading file activities. Behavioral interactions with peers included discussion postings, discussion responses, and discussion viewing activities. A series of Mann-Whitney tests were conducted to compare the two types of behavioral interactions between the two courses. Additionally, each student's behavioral interactions were visually presented to show the pattern of their interactions. The results indicated that, at the beginning of the semester, students who were involved in authentic design/development-based learning activities showed a significantly higher number of behavioral interactions with the Moodle LMS than did students involved in authentic discussion-based learning activities. However, in the middle of the semester, students engaged in authentic discussion-based learning activities showed a significantly higher number of behavioral interactions with peers than did students involved in authentic design/development-based learning activities. Additionally, students who were given authentic design/development-based learning activities received higher performance scores both during the semester and at the end of the semester and they showed overall higher performance scores than students who were given authentic discussion-based learning activities. No differences were found between the two groups with respect to time-on-task or attendance.</p>

scholarly journals Gender, Math Confidence, and Grit: Relationships with Quantitative Skills and Performance in an Undergraduate Biology Course

2017 ◽  
Vol 16 (3) ◽  
pp. ar47 ◽  
Author(s):  
K. M. Flanagan ◽  
J. Einarson
Keyword(s):  
Student Performance ◽  
Gender Gap ◽  
Positive Impact ◽  
Skills Assessment ◽  
Final Grade ◽  
Undergraduate Biology ◽  
Quantitative Skills ◽  
Overall Performance ◽  
And Performance ◽  
Positive Effect

In a world filled with big data, mathematical models, and statistics, the development of strong quantitative skills is becoming increasingly critical for modern biologists. Teachers in this field must understand how students acquire quantitative skills and explore barriers experienced by students when developing these skills. In this study, we examine the interrelationships among gender, grit, and math confidence for student performance on a pre–post quantitative skills assessment and overall performance in an undergraduate biology course. Here, we show that females significantly underperformed relative to males on a quantitative skills assessment at the start of term. However, females showed significantly higher gains over the semester, such that the gender gap in performance was nearly eliminated by the end of the semester. Math confidence plays an important role in the performance on both the pre and post quantitative skills assessments and overall performance in the course. The effect of grit on student performance, however, is mediated by a student’s math confidence; as math confidence increases, the positive effect of grit decreases. Consequently, the positive impact of a student’s grittiness is observed most strongly for those students with low math confidence. We also found grit to be positively associated with the midterm score and the final grade in the course. Given the relationships established in this study among gender, grit, and math confidence, we provide “instructor actions” from the literature that can be applied in the classroom to promote the development of quantitative skills in light of our findings.

Using Learning Analytics to Improve Engagement, Learning, and Design of Massive Open Online Courses

2019 ◽  
pp. 76-107
Author(s):  
David Santandreu Calonge ◽  
Karina M. Riggs ◽  
Mariam Aman Shah ◽  
Tim A. Cavanagh
Keyword(s):  
Student Performance ◽  
Curriculum Design ◽  
Learning Analytics ◽  
Online Courses ◽  
Academic Research ◽  
Massive Open Online Courses ◽  
Massive Open Online ◽  
Design Decisions ◽  
Effective Interventions ◽  
Using Data

Academic research in the past decade has indicated that using data and analyzing learning in curriculum design decisions can lead to improved student performance and student success. As learning in many instances has evolved into the flexible format online, anywhere at any time, learning analytics could potentially provide impactful insights into student engagement in massive open online courses (MOOCs). These may contribute to early identification of “at risk” participants and provide MOOC facilitators, educators, and learning designers with insights on how to provide effective interventions to ensure participants meet the course learning outcomes and encourage retention and completion of a MOOC. This chapter uses the essential human biology MOOC within the Australian AdelaideX initiative to implement learning analytics to investigate and compare demographics of participants, patterns of navigation including participation and engagement for passers and non-passers in two iterations of the MOOC, one instructor-led, and second self-paced.

Improving Teaching Effectiveness Using Distance Education Tools

2011 ◽  
pp. 102-120 ◽  
Author(s):  
Murali Shanker ◽  
Michael Y Hu
Keyword(s):  
Distance Education ◽  
Student Satisfaction ◽  
Student Learning ◽  
Student Performance ◽  
Teaching Effectiveness ◽  
Learning Objectives ◽  
Learning Material ◽  
Student Learning Objectives ◽  
Using Data ◽  
High Level

Distance education is now an integral part of offering courses in many institutions. With increasing access to the internet, the importance of distance education will only grow. But, to date, the specific benefits that distance education brings to student learning objectives remain unclear. We first propose a framework that links student performance and satisfaction to the learning environment and course delivery. Next, we empirically evaluate our framework using data from a Business Statistics course that we offer in the traditional classroom setting and as a distance-education course. Our results show that while a well-designed distance-education course can lead to a high level of student satisfaction, classroom-based students achieve even higher satisfaction if they are also given access to online learning material. This indicates that material for an effective distance-education course can also be used to supplement in-class teaching to increase satisfaction with student learning objectives.

scholarly journals Predicting Student Performance by Using Data Mining Methods for Classification

2013 ◽  
Vol 13 (1) ◽  
pp. 61-72 ◽  
Author(s):  
Dorina Kabakchieva
Keyword(s):  
Data Mining ◽  
Decision Making ◽  
Student Performance ◽  
High Potential ◽  
University Management ◽  
Mining Methods ◽  
Predicting Student Performance ◽  
Using Data ◽  
Initial Results ◽  
Support Decision Making

Abstract Data mining methods are often implemented at advanced universities today for analyzing available data and extracting information and knowledge to support decision-making. This paper presents the initial results from a data mining research project implemented at a Bulgarian university, aimed at revealing the high potential of data mining applications for university management.

scholarly journals ANALYSIS OF STUDENTS PERFORMANCE IN RELATION TO THE RESULTS OF STATE UNIFIED EXAM: THE CASE OF RUSSIAN UNIVERSITY

2021 ◽  
Vol 19 (01) ◽  
pp. 170-179
Author(s):  
Anna Svirina ◽  
Aleksey Lopatin ◽  
Jelena Titko
Keyword(s):  
Student Performance ◽  
Statistical Evaluation ◽  
University Research ◽  
Assessment Tools ◽  
First Semester ◽  
Predicting Student Performance ◽  
And Performance ◽  
Education Performance ◽  
The University ◽  
Practical Implications

Purpose – Considering the limited number of studies covering the topic, the goal is to check the existence of the correlation between the results of Russia’s Unified State Exam and performance at the university. Research methodology – the article uses quantitate analysis (regression) of the student performance on a sample of 4664 students. To provide statistical evaluation, the authors use SPSS Statistics software. Findings – the research suggests, that results of unified state exam and individual students scores, awarded by the university under restrictions, are non-efficient in terms of predicting student performance. On the opposite, students’ performance during their first semester is a good predictor for the whole period of academic studies. As existing results of testing such hypotheses are inconsistent, the research provides value to the field of educational research. Research limitations – data for research refer to only Kazan National Research Technical University named after A. N. Tupolev (KNRTU-KAI). Practical implications – the research clearly indicate, that the universities cannot rely solely on the unified state exam during admission; they are to use different assessment tools to ensure future academic performance and lower dropouts rate. Originality/Value – There is a gap in the investigation the link between secondary education and higher education performance.

Implementation of Dual Decision Support System for Students and Teachers using Data Analytics in Online Exam

2021 ◽  
Vol 9 (VII) ◽  
pp. 2979-2982
Author(s):  
Kalyani V. Deshmukh
Keyword(s):  
Online Learning ◽  
Decision Support ◽  
Decision Support System ◽  
Student Performance ◽  
Support System ◽  
Data Analytics ◽  
Learning System ◽  
Improve Student Performance ◽  
And Performance ◽  
Using Data

Online Learning platforms are increasing day by day, and most of the people prefer online learning as this platform is very convenient and affordable. In online learning education, learning content designing plays very important role to improve student performance. Therefore in this project we proposed a data analytics based model to analyze student’s exam solving and content accessing behaviors which will help teachers to improve content quality. Student’s behavior analysis will also help to find out questions difficulty levels as well as student’s grade and performance. We proposed a decision support system in online learning system for tutors/teachers which will help them to improve their learning quality. Along with this the tutors will be able to view student’s performance online using Graphical User Interface. In this system, we proposed a personal questions ordering module for students depending upon their historical question solving patterns.

Sign in / Sign up

Export Citation Format

Share Document