scholarly journals Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance

Algorithms ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 318
Author(s):  
Thao-Trang Huynh-Cam ◽  
Long-Sheng Chen ◽  
Huynh Le
Keyword(s):  
Random Forest ◽  
Performance Prediction ◽  
Prediction Models ◽  
Family Background ◽  
Educational Practice ◽  
Poor Performance ◽  
Learning Performance ◽  
First Year ◽  
First Year Students ◽  
Early Performance

First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These models cannot provide enough timely support for the poor performance students, caused by economic factors. Therefore, other variables are needed that allow us to reach prediction results earlier. This study attempts to use family background variables that can be obtained prior to the start of the semester to build learning performance prediction models of freshmen using random forest (RF), C5.0, CART, and multilayer perceptron (MLP) algorithms. The real sample of 2407 freshmen who enrolled in 12 departments of a Taiwan vocational university will be employed. The experimental results showed that CART outperforms C5.0, RF, and MLP algorithms. The most important features were mother’s occupations, department, father’s occupations, main source of living expenses, and admission status. The extracted knowledge rules are expected to be indicators for students’ early performance prediction so that strategic intervention can be planned before students begin the semester.

scholarly journals METHODOLOGY OF GROUP WORK ORGANISATION FOR STUDENT LEARNING PERFORMANCE IMPROVEMENT

2017 ◽  
Vol 2 ◽  
pp. 133 ◽  
Author(s):  
Nataly Prokofyeva ◽  
Marina Uhanova
Keyword(s):  
Student Learning ◽  
Group Work ◽  
Learning Performance ◽  
Basic Knowledge ◽  
First Year ◽  
Work Organisation ◽  
Student Group ◽  
First Year Students ◽  
Java Programming ◽  
Learning Programming

The article describes the methodology of learning programming for students of various engineering disciplines. The course "Algorithmization and Programming of Solutions" is taught to all first-year students of the Faculty of Computer Science and Information Technology in Riga Technical University and provides the basic knowledge of the principles of computational process algorithmization and software creation technology using Java programming language. There are 8 laboratory assignments in the course, where students have to develop a software programme and 2 group work assignments, where the student has to develop some algorithms to solve a given problem, write a programme, evaluate the speed of developed algorithms and prepare a presentation on the results of their research. The article describes the main principles of efficient student group work organisation that lets to increase their interest and motivate them to participate in the course in a responsible way. This paper is focused on research on how group work influences student learning performance.

Computer Assisted Learning For Enhancing Mastery Of Concepts In Science

2020 ◽  
Vol 2 (2) ◽  
pp. 134-142
Author(s):  
Sharon Anyango Onditi ◽  
Stephen Oloo Ajwang
Keyword(s):  
Teaching And Learning ◽  
Poor Performance ◽  
Target Population ◽  
Computer Assisted ◽  
First Year ◽  
Computer Assisted Learning ◽  
First Year Students ◽  
Post Test ◽  
Science Concepts ◽  
And Control

This study examined the effects of Computer Assisted Learning (CAL) on the mastery of Science concepts by learners in universities. Teaching and learning of Science concepts present learners with numerous challenges. Of critical concern is the negative perception by learners that Science based subjects are difficult, thus contributing to widespread poor performance by the learners in the national examinations and subsequently poor choice of the subject in the universities. Solomon Four Group experimental design was employed for the study. The target population comprised all first-year students taking science subjects in 8 universities in western Kenya. A sample size of 335 students was determined using Krejcie Morgan table (1970). The universities were divided into two forming experimental and control groups.  The study was carried out in 4 months spanning 16 weeks where pretest was administered after the first 8 weeks of conventional teaching and post-test administered after the next 8 weeks of treatment. Pretest and post-test Science Achievements Test (SAT) on two topics, digestive system and light and optics, were designed and administered by the respective lecturers, and scores recorded. Piloting was carried before the use of the instruments, and a reliability coefficient of 0.85 on SAT was recorded.  Data were analyzed using t-test one-way ANOVA. The study found that 171 students taught using CAL achieved significantly higher scores in SAT compared to164 students taught through conventional methods with a mean gain of 2.851. The study demonstrated that CAL enhanced active manipulation of content and promoted interaction with content, and gave reality to abstraction. The study may be significant to educationists, lecturers, researchers, and policy makers as it provides insight on the benefits of applying Computer Assisted Learning in Science Education. 

scholarly journals Academic Engagement and Intention to Drop Out: Levers for Sustainability in Higher Education

2018 ◽  
Vol 10 (12) ◽  
pp. 4637 ◽  
Author(s):  
Camelia Truta ◽  
Luminita Parv ◽  
Ioana Topala
Keyword(s):  
Higher Education ◽  
Academic Engagement ◽  
Family Background ◽  
Drop Out ◽  
Dropping Out ◽  
First Year ◽  
Students At Risk ◽  
First Year Students ◽  
Academic Context ◽  
Early Dropout

The present paper analyses the relevance of academic engagement in the process of students dropping out of school. Previous studies have consistently shown strong associations between engagement and students’ achievement outcomes. The increased attention given to academic engagement in recent years is also visible in the efforts of stakeholders in higher education to increase engagement and, consequently, to reduce dropout. The relationships between engagement and dropout rates are somewhat fuzzier, vigor, dedication, and absorption vary inconsistently in students at risk. Using a correlation research design, we tested several dimensions of academic engagement as predictors of early dropout intentions on a sample of first-year students (N = 1063). The results showed that psychological academic engagement of students is a significant predictor of early dropout intentions. Differences in academic engagement given by family background and academic context were also tested. The implications of the results are discussed in the light of possible interventions for increasing academic engagement of university students. Also, suggestions for including employers in academic engagement and dropout interventions are given.

scholarly journals Types of boredom and other learning activity emotions: A person-centred investigation of inter-individual data

2021 ◽  
Author(s):  
Dirk Tempelaar ◽  
Alexandra Corina Niculescu
Keyword(s):  
Latent Class ◽  
Educational Practice ◽  
Linear Ordering ◽  
Learning Activity ◽  
First Year ◽  
Cross Sectional ◽  
First Year Students ◽  
Discrete Learning ◽  
High Control ◽  
Level Of Analysis

AbstractWhether boredom is a unitary construct or if multiple types of boredom exist is a long-standing debate. Recent research has established the existence of boredom types based on frequency observations of boredom by experience sampling. This work tries to expand our understanding of boredom and replicate these previous findings by applying intensity observations of cross-sectional type for four discrete learning activity emotions: boredom, anxiety, hopelessness, and enjoyment. Latent class analysis based on activity emotion scores from 9863 first-year students of a business and economics program results in seven profiles. Five of these profiles allow a linear ordering from low to high control and value scores (the direct antecedents of emotions), low to high positive, and high to low negative emotions. Two profiles differ from this pattern: one ‘high boredom’ profile and one ‘low boredom’ profile. We next compare antecedent relationships of activity emotions at three different levels: inter-individual, inter-class or between classes, and intra-class or within classes. Some of these relationships are invariant for the choice of level of analysis, such as hopelessness. Other relationships, such as boredom, are highly variant: within-class relationships differ from inter-individual relationships. Indeed, our results confirm that boredom is not a unitary construct. The types of boredom found and their implications for educational practice are discussed and shared in this article.

Adopting Learning Analytics in a First-Year Veterinarian Professional Program: What We Could Know in Advance about Student Learning Progress

2021 ◽  
Vol 48 (6) ◽  
pp. 720-728
Author(s):  
Wenting Weng ◽  
Nicola L. Ritter ◽  
Karen Cornell ◽  
Molly Gonzales
Keyword(s):  
At Risk ◽  
Academic Success ◽  
Student Learning ◽  
Learning Analytics ◽  
Prediction Models ◽  
Early Stage ◽  
At Risk Students ◽  
Learning Performance ◽  
First Year ◽  
Actual Performance

Over the past decade, the field of education has seen stark changes in the way that data are collected and leveraged to support high-stakes decision-making. Utilizing big data as a meaningful lens to inform teaching and learning can increase academic success. Data-driven research has been conducted to understand student learning performance, such as predicting at-risk students at an early stage and recommending tailored interventions to support services. However, few studies in veterinary education have adopted Learning Analytics. This article examines the adoption of Learning Analytics by using the retrospective data from the first-year professional Doctor of Veterinary Medicine program. The article gives detailed examples of predicting six courses from week 0 (i.e., before the classes started) to week 14 in the semester of Spring 2018. The weekly models for each course showed the change of prediction results as well as the comparison between the prediction results and students’ actual performance. From the prediction models, at-risk students were successfully identified at the early stage, which would help inform instructors to pay more attention to them at this point.

scholarly journals Student Selection of Content Licenses in OER-enabled Pedagogy

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Katherine Williams ◽  
Eric Werth
Keyword(s):  
Intellectual Property ◽  
Property Rights ◽  
Intellectual Property Rights ◽  
Liberal Arts ◽  
Educational Practice ◽  
The United States ◽  
Educational Process ◽  
First Year ◽  
First Year Students ◽  
Creative Commons

Students acting as content creators is an emergent trend in the field of open educational practice. As more faculty turn towards the use of open pedagogy or OER-enabled Pedagogy, they must be prepared to address concerns related to intellectual property rights of student work. This article addresses student concerns related to intellectual property rights, specifically related to Creative Commons licensing as well as faculty awareness of use of Creative Commons licensing. Research was conducted at a small, liberal arts college in the Appalachian Region of the United States. All first-year students engaged in an OER-enabled Pedagogy project where they collaboratively created a reader for the First Year Studies seminar course. Following class, students and faculty were interviewed regarding how dynamics of intellectual property and Creative Commons licensing impacted the educational process. Results indicate students are open to sharing their works with credit, and value helping others. Faculty tend to be unfamiliar with Creative Commons licensing and must balance the desire to help students understand licensing and prescribing their own preferences when asked about licensing selection. 

Psychological Safety Development Drill As a Mean of Training First-Year Students for Educational Practice

2015 ◽  
Vol 4 (3) ◽  
pp. 45-48
Author(s):  
Столярова ◽  
E. Stolyarova
Keyword(s):  
Psychological Safety ◽  
Educational Practice ◽  
Safety Training ◽  
First Year ◽  
First Year Students

In article experimentally substantiates the efficiency of psychological safety training in education for training first-year students, future bachelors of psychology and pedagogy programs. It reveals prospective of the training that provide preparation for recognising and overcoming psychological dangers arising towards an individual himself or towards subjects of interaction during educational practice.

scholarly journals Oversampling technique in student performance classification from engineering course

2021 ◽  
Vol 11 (4) ◽  
pp. 3567
Author(s):  
Nachirat Rachburee ◽  
Wattana Punlumjeak
Keyword(s):  
Random Forest ◽  
Student Performance ◽  
Performance Prediction ◽  
Gradient Boosting ◽  
First Year ◽  
Engineering Student ◽  
Academic Planning ◽  
Minority Class ◽  
Class Prediction

<span>The first year of an engineering student was important to take proper academic planning. All subjects in the first year were essential for an engineering basis. Student performance prediction helped academics improve their performance better. Students checked performance by themselves. If they were aware that their performance are low, then they could make some improvement for their better performance. This research focused on combining the oversampling minority class data with various kinds of classifier models. Oversampling techniques were SMOTE, Borderline-SMOTE, SVMSMOTE, and ADASYN and four classifiers were applied using MLP, gradient boosting, AdaBoost and random forest in this research. The results represented that Borderline-SMOTE gave the best result for minority class prediction with several classifiers.</span>

scholarly journals Development of an interactive mathematics learning system based on a two-tier test diagnostic and guiding strategy

2016 ◽  
Author(s):  
Tzu-Chi Yang ◽  
Hseng-Tz Fu ◽  
Gwo-Jen Hwang ◽  
Stephen J. H. Yang
Keyword(s):  
Learning Strategies ◽  
Mathematics Learning ◽  
Learning System ◽  
Learning Performance ◽  
First Year ◽  
Science Students ◽  
Mathematical Skills ◽  
First Year Students ◽  
Effective Learning ◽  
Learning Mathematics

<p>Mathematical skills have been recognised as a core competence for engineering and science students. However, learning mathematics has been recognised as a difficult and challenging task for most students, in particular, calculus for first-year students in university. Consequently, the development of effective learning strategies and environments for mathematics courses has become an important issue. To this end, a mathematics learning system based on an instant diagnostic and guiding strategy is proposed to enhance students’ calculus learning outcomes. Moreover, an experiment has been conducted in a university calculus course to evaluate the effectiveness of the proposed method. The experimental results show that the proposed approach not only improved the students’ learning performance, but also improved their confidence in learning calculus. Further findings are also discussed.</p>

Sign in / Sign up

Export Citation Format

Share Document