The advancement in artificial intelligence (AI) and Machine learning (ML) have made it easier to foreknown feature happens from current and past trends. Once Self-efficacy and self-confidence are believed to be, an individual trait associated with academic brilliance. Using a hybridised Random Forest and Support Vector Machine (RFSVM) ML model we predicted students' academic performance in computer programming courses, based on their self-confidence, self-efficacy, positive thinking, focus, big goals, a motivating environment and demographic data. Benchmarking our RFSVM model against Decision Tree (DT) and K-Nearest Neighbour (K-NN) model, the RFSVM recorded and accuracy of 98% as against 95.45% for DT and 36.36% for K-NN. The error between actual values and predicted values of the RFSVM model was better (RMSE = 0.326401, MAE = 0.050909) and compared with the K-NN (RMSE = 2.671397, MAE = 1.954545) and DT models (RMSE = 0.426401, MAE = 0.090909). The results further revealed that students with a high level of self-confidence, self-efficacy and positive thinking performed well in computer programming courses.
Development of Aljabar Materials Based On React Strategy To Increase Material...AJHSSR Journal
e them is with developing algebra teaching materials based
on the REACT strategy to enhance students' metaphorical thinking ability. The research method uses research
and development type formative research. The subject of this study is class VII in one of junior high school in
Cianjur, Indonesia. Based on the results of research and discussion can be summed up some things as follows:
(1) teaching materials that have been compiled good quality although still need to be refined again. (2) The
students' metaphorical thinking ability through the use of the teaching materials is enhancing. (3) The student's
response to this teaching material is very positive.
KEYWORDS: React Strategy , Algebra, Teaching and Learning Materials, Metaphorical Thingking, Moral
Crisis
Learning Trajectory-Aligned Diagnostic Assessments for Early Algebra, Grades ...Basia Coulter
A learning trajectory connects what students bring to instruction, to a target concept, and delineates a set of landmarks and obstacles that students are likely to encounter as they move from naïve to sophisticated understandings.
Development of Aljabar Materials Based On React Strategy To Increase Material...AJHSSR Journal
e them is with developing algebra teaching materials based
on the REACT strategy to enhance students' metaphorical thinking ability. The research method uses research
and development type formative research. The subject of this study is class VII in one of junior high school in
Cianjur, Indonesia. Based on the results of research and discussion can be summed up some things as follows:
(1) teaching materials that have been compiled good quality although still need to be refined again. (2) The
students' metaphorical thinking ability through the use of the teaching materials is enhancing. (3) The student's
response to this teaching material is very positive.
KEYWORDS: React Strategy , Algebra, Teaching and Learning Materials, Metaphorical Thingking, Moral
Crisis
Learning Trajectory-Aligned Diagnostic Assessments for Early Algebra, Grades ...Basia Coulter
A learning trajectory connects what students bring to instruction, to a target concept, and delineates a set of landmarks and obstacles that students are likely to encounter as they move from naïve to sophisticated understandings.
Exploring General Science Questions of Secondary School Certificate (SSC) Exa...Md. Mehadi Rahman
Creative question is generally considered as a tool to measure students’ various levels of learning. The study focused on exploring the present situation of General Science test items/creative questions in Bangladesh. This descriptive study was conducted using a concurrent triangulation research design. To conduct this study both quantitative and qualitative data were collected. 16 test of General Science test items/creative question papers of 2015 or 2016 were selected purposively as sample from all educational boards. 48 students were selected conveniently for interview from those who had been passed the SSC examination of 2015 or 2016. For collecting data from these sources test analysis protocol and interview protocol were used as research tools. Test analysis protocol was consisted of two criteria; wording criteria and practicing criteria. Selected test items were analysed based on these two criteria and Bloom’s cognitive domain. The study revealed that major test items were developed in a way which direct students towards lower level learning. Few test items were focused to students understanding, application and higher order learning. In practice, students were engaged to only memorization and understanding through SSC examination assessment. Few test items were devoted to application level learning of students. Higher order learning was totally ignored in SSC examination questions.
Virtual School Leader Dissertation DefenseMark Sivy
This was the presentation for the defense of my doctoral dissertation entitled "State-led Virtual School Leaders: An Exploratory Study". This information will benefit leaders of virtual schools, cyber schools, and other online educational programs. It will also be of benefit to the design and creation of leader preparation programs and professional development.
In our department, we're required to present our study proposals for comment before submission to Higher Degrees. This allows for the group to give feedback for final corrections in the hope that the proposal is accepted without having to make major revisions.
This is the proposal presentation I gave to my department a few days ago. The feedback I received, although mainly editorial, means that the structure of this content is not the same as it will be in the final submission e.g. the Method has received another step in the process.
PhD Proposal Defense Team Psychological Safety, Team Learning and Team Knowle...Peter Cauwelier
Presentation I used to present my proposal in front of the PhD committee at Bangkok University. My model links team psychological safety and team learning, with the creation of knowledge at the team level. Happy to say the proposal defense went very well !
An Inquiry on the Self-Esteem and Self-Efficacy Level of Information Technolo...IJAEMSJORNAL
This study aimed to identify, analyze and determine the level of self-efficacy and self-esteem of B.S. Information Technology (BSIT) students of a higher learning institution in Nueva Ecija, Philippines. It was conducted during the 1st Semester of the academic year 2019-2020. This research utilized descriptive approach to describe the level of self-esteem and self-efficacy of the students and to draw valuable insights that may contribute to the improvement of the teaching and learning practices of the faculty members in the college. The researchers used random sampling to ensure that all year levels are well represented in the study. There were 285 students who voluntarily responded after the researchers explained to them the purpose of this study. Responses were tallied, summarized and interpreted. Results show that the level of self-esteem and self-efficacy of the students were moderate/medium (WM=2.03, WM=2.08). This indicates that depending on the given situation or context, students may increase or decrease the level of their self-esteem and self-efficacy. This study suggest that students may be exposed to more activities that may help them improve their self-esteem and self-efficacy to greatly contribute to their holistic development. Future studies may be conducted to a larger number of respondents and to understand the link between self-efficacy and self-esteem on their academic performance, drop-out rates, and retention rates.
THE RELATIONS OF METACOGNITIVE AWARENESS, MULTIPLE INTELLIGENCES, AND GENDER ...ijma
Learning Introductory Programming has always been challenging to computer science and information
technology undergraduates and such problems, most notably comes from the lack of metacognitive
awareness. Other important factors are multiple intelligences, gender, and motivation in using learning
tools can also have a huge impact on learning the subject matter. A survey study was carried out with the
aim to investigate the relationship among metacognitive awareness, gender and multiple intelligences
towards perceived motivation of the students in learning using multimedia tools. 103 fresh undergraduates
were recruited to participate in the survey. The data analysed using Pearson correlation and multiple
linear regression analysis. The result showed that the correlation between metacognitive awareness and
motivation in using multimedia tools was significant, positive, and moderately strong. These finding
suggest that students with higher metacognitive awareness will be highly motivated in using multimedia
tools compared to those with lower metacognitive awareness.
International Journal of Engineering Research and Development is an international premier peer reviewed open access engineering and technology journal promoting the discovery, innovation, advancement and dissemination of basic and transitional knowledge in engineering, technology and related disciplines.
Exploring General Science Questions of Secondary School Certificate (SSC) Exa...Md. Mehadi Rahman
Creative question is generally considered as a tool to measure students’ various levels of learning. The study focused on exploring the present situation of General Science test items/creative questions in Bangladesh. This descriptive study was conducted using a concurrent triangulation research design. To conduct this study both quantitative and qualitative data were collected. 16 test of General Science test items/creative question papers of 2015 or 2016 were selected purposively as sample from all educational boards. 48 students were selected conveniently for interview from those who had been passed the SSC examination of 2015 or 2016. For collecting data from these sources test analysis protocol and interview protocol were used as research tools. Test analysis protocol was consisted of two criteria; wording criteria and practicing criteria. Selected test items were analysed based on these two criteria and Bloom’s cognitive domain. The study revealed that major test items were developed in a way which direct students towards lower level learning. Few test items were focused to students understanding, application and higher order learning. In practice, students were engaged to only memorization and understanding through SSC examination assessment. Few test items were devoted to application level learning of students. Higher order learning was totally ignored in SSC examination questions.
Virtual School Leader Dissertation DefenseMark Sivy
This was the presentation for the defense of my doctoral dissertation entitled "State-led Virtual School Leaders: An Exploratory Study". This information will benefit leaders of virtual schools, cyber schools, and other online educational programs. It will also be of benefit to the design and creation of leader preparation programs and professional development.
In our department, we're required to present our study proposals for comment before submission to Higher Degrees. This allows for the group to give feedback for final corrections in the hope that the proposal is accepted without having to make major revisions.
This is the proposal presentation I gave to my department a few days ago. The feedback I received, although mainly editorial, means that the structure of this content is not the same as it will be in the final submission e.g. the Method has received another step in the process.
PhD Proposal Defense Team Psychological Safety, Team Learning and Team Knowle...Peter Cauwelier
Presentation I used to present my proposal in front of the PhD committee at Bangkok University. My model links team psychological safety and team learning, with the creation of knowledge at the team level. Happy to say the proposal defense went very well !
An Inquiry on the Self-Esteem and Self-Efficacy Level of Information Technolo...IJAEMSJORNAL
This study aimed to identify, analyze and determine the level of self-efficacy and self-esteem of B.S. Information Technology (BSIT) students of a higher learning institution in Nueva Ecija, Philippines. It was conducted during the 1st Semester of the academic year 2019-2020. This research utilized descriptive approach to describe the level of self-esteem and self-efficacy of the students and to draw valuable insights that may contribute to the improvement of the teaching and learning practices of the faculty members in the college. The researchers used random sampling to ensure that all year levels are well represented in the study. There were 285 students who voluntarily responded after the researchers explained to them the purpose of this study. Responses were tallied, summarized and interpreted. Results show that the level of self-esteem and self-efficacy of the students were moderate/medium (WM=2.03, WM=2.08). This indicates that depending on the given situation or context, students may increase or decrease the level of their self-esteem and self-efficacy. This study suggest that students may be exposed to more activities that may help them improve their self-esteem and self-efficacy to greatly contribute to their holistic development. Future studies may be conducted to a larger number of respondents and to understand the link between self-efficacy and self-esteem on their academic performance, drop-out rates, and retention rates.
THE RELATIONS OF METACOGNITIVE AWARENESS, MULTIPLE INTELLIGENCES, AND GENDER ...ijma
Learning Introductory Programming has always been challenging to computer science and information
technology undergraduates and such problems, most notably comes from the lack of metacognitive
awareness. Other important factors are multiple intelligences, gender, and motivation in using learning
tools can also have a huge impact on learning the subject matter. A survey study was carried out with the
aim to investigate the relationship among metacognitive awareness, gender and multiple intelligences
towards perceived motivation of the students in learning using multimedia tools. 103 fresh undergraduates
were recruited to participate in the survey. The data analysed using Pearson correlation and multiple
linear regression analysis. The result showed that the correlation between metacognitive awareness and
motivation in using multimedia tools was significant, positive, and moderately strong. These finding
suggest that students with higher metacognitive awareness will be highly motivated in using multimedia
tools compared to those with lower metacognitive awareness.
International Journal of Engineering Research and Development is an international premier peer reviewed open access engineering and technology journal promoting the discovery, innovation, advancement and dissemination of basic and transitional knowledge in engineering, technology and related disciplines.
Learning analytics - what can we achieve together.pptxRebecca Ferguson
Keynote given on 7 June 2023 by Rebecca Ferguson of The Open University in the UK at the Learning Analytics Summer Institute (LASI) organised by the Society for Learning Analytics Research (SoLAR) in Singapore.
Self-Efficacy in M-Learning
Jason Hutcheson
Running head: 3Capella UniversityTable of Contents
Literature Review5
Self-Efficacy Theory5
Theoretical Foundations.5
Intentional Development of Self-Efficacy.7
Self-Efficacy in Learning9
Role of Self-Efficacy in Andragogy.9
Relationship between Self-Efficacy and Academic Achievement.10
Integration of Self-Efficacy in Learning Design.12
Self-Efficacy in Technology Acceptance14
Technology Acceptance Modeling.14
Mobile Technology Acceptance.16
Methodology and Approach16
Methodology and Rationale17
Research Methodology Analysis.17
Methodology Selection Rationale.18
Population and Sample19
Sample Recruitment Strategy19
Instrument19
Conclusion20
Abstract
Technology has become engrained into daily life. The most prominent technology today is mobile technology. Through mobile “smart” phones, tablets, and laptops, the modern population is connected through mobile technology; everywhere, all of the time. However, many of the benefits of mobile technology have not translated into the educational environment. This represents a problem for both the education and the information technology industries. In order to effectively address this problem, researchers need to understand the challenges of integrating mobile technology in the course room and determine the drivers influencing the acceptance of mobile technology. Existing literature has indicated a relationship between self-efficacy and the acceptance of mobile technology in the course room. However, the degree of correlation between learner self-efficacy and the acceptance of mobile technology has not yet been determined. This paper analyzes the existing literature concerning the role of self-efficacy in mobile learning (m-learning) and presents the foundation for research concerning the relationship between self-efficacy and mobile technology acceptance.
Self-Efficacy in M-Learning
Existing literature has identified value in the integration of mobile technology in the course room with respect to the promotion of collaboration (Fuegen, 2012; Liljestrom, Enkenberg, & Pollanen, 2013; Pegrum, Oakley, & Faulkner, 2013; Shree Ram & Selvaraj, 2012). Still, mobile technology for education remains underutilized. Existing literature extensively discusses the challenges associated with transitioning to an m-learning enabled environment (Cheon, Lee, Crooks, & Song, 2012; Eteokleous & Ktoridou, 2009; Ktoridou, Gregoriou, & Eteokleous, 2007; Male & Pattinson, 2011; Rossing, 2012). Chief among the challenges for transitioning to m-learning is the acceptance of mobile technology in learning, which lends to the importance of identifying and classifying key determinates for mobile technology acceptance.
This paper analyzes the existing literature concerning self-efficacy in order to assess the role of self-efficacy in m-learning. The paper begins by analyzing the theoretical foundations of self-efficacy and how self-efficacy can be developed. This is follo.
RELATIONSHIP OF NON-COGNITIVE SKILLS AND ACADEMIC ACHIEVEMENTS OF UNDERGRADUA...Dr.Nasir Ahmad
Introduction: Universities prepare students to play their role in the society and equip students with cognitive and non-cognitive skills. Having the significance of non-cognitive skills in mind, the study was designed to investigate the non-cognitive skills of undergraduate students at university level. Therefore, the objectives of the study were to measure non-cognitive skills of university students and to measure the relationship of non-cognitive skills and academic performance among them.
Material & Methods: The population of the study was 7189 undergraduate students and a sample of 368 students was selected through simple random sampling for data collection. A questionnaire was developed and validated for gathering the data. The collected data were analysed through mean scores, standard deviation, chi-square test and Pearson correlation.
Results: The mean score of the students on self-control was 4.71 having significance indicating that the participants had self-control over themselves. The mean score of the students on academic self-efficacy was 3.96 which again indicates that majority of them were academically self-effective. The mean score on goal setting scale 3.63 which was significant.
Conclusion: The study found that the non-cognitive skills, i.e., self-control, self-efficacy, goal-setting and self-regulated learning has positive relationship with academic achievement of students.
Summative Case Study In Nursing
Practice Of Summative Assessment
Comparing Formative And Summative Evaluations
Formative Vs. Summative Assessment
Summative Versus Formative Assessments Essay
Reflection On Summative Assessment
Essay about Summative Assessment Preparation
Summative Paper
Assessment And Summative Assessment
Summary : Formative And Summative Assessments
Summative Assessment
Summative Assessment Case Study
Formative And Summative Assessment
End-Of-Year Summative Review
What Is Formative And Summative Assessment
Educational Data Mining (EDM) is one of the crucial application areas of data mining which helps in predicting educational dropout and hence provides timely help to students. In Indian context, predicting educational dropouts is a major problem. By implementing EDM, we can predict the learning habits of the student. At present EDM has not been introduced at higher education level. Due to this we cannot recognize the genuine problems of students during their education. The objective of this analysis is to find the existing gaps in predicting educational dropout and find the missing attributes if any, which my further contribute for better prediction. After that we try to find the best attributes and DM techniques which are frequently used for dropout prediction. Based on the combination of missing attribute and best attribute of student data thus far, a new algorithm can be tested which may overcome the shortcomings of previous work done.
The Effect of the Involvement Intensity in Extracurricular Activities and Sof...inventionjournals
There are many graduates of higher education who are academically good, but weak in terms of soft skills; and it is becoming main cause of unemployment among the educated. This study examines the relationship between the intensity of involvement in extracurricular activities with soft skills quality and work readiness of the graduates. The population in this study was college graduates in East Java in 2014. The sample was determined by accidental sampling technique for college graduates in Surabaya, Malang, Jember and Kediri. Data analysis was done by using multiple analysis of variance. The results showed the more intensively involved in extracurricular activities, the better quality of soft skills and work readiness which the graduates have. Suggestion is proposed to universities to develop extracurricular activities that must be followed by all students.
Similar to Self-motivation and Academic Performance In Computer Programming Language Using a Hybridised Machine Learning Technique (20)
Welocme to ViralQR, your best QR code generator.ViralQR
Welcome to ViralQR, your best QR code generator available on the market!
At ViralQR, we design static and dynamic QR codes. Our mission is to make business operations easier and customer engagement more powerful through the use of QR technology. Be it a small-scale business or a huge enterprise, our easy-to-use platform provides multiple choices that can be tailored according to your company's branding and marketing strategies.
Our Vision
We are here to make the process of creating QR codes easy and smooth, thus enhancing customer interaction and making business more fluid. We very strongly believe in the ability of QR codes to change the world for businesses in their interaction with customers and are set on making that technology accessible and usable far and wide.
Our Achievements
Ever since its inception, we have successfully served many clients by offering QR codes in their marketing, service delivery, and collection of feedback across various industries. Our platform has been recognized for its ease of use and amazing features, which helped a business to make QR codes.
Our Services
At ViralQR, here is a comprehensive suite of services that caters to your very needs:
Static QR Codes: Create free static QR codes. These QR codes are able to store significant information such as URLs, vCards, plain text, emails and SMS, Wi-Fi credentials, and Bitcoin addresses.
Dynamic QR codes: These also have all the advanced features but are subscription-based. They can directly link to PDF files, images, micro-landing pages, social accounts, review forms, business pages, and applications. In addition, they can be branded with CTAs, frames, patterns, colors, and logos to enhance your branding.
Pricing and Packages
Additionally, there is a 14-day free offer to ViralQR, which is an exceptional opportunity for new users to take a feel of this platform. One can easily subscribe from there and experience the full dynamic of using QR codes. The subscription plans are not only meant for business; they are priced very flexibly so that literally every business could afford to benefit from our service.
Why choose us?
ViralQR will provide services for marketing, advertising, catering, retail, and the like. The QR codes can be posted on fliers, packaging, merchandise, and banners, as well as to substitute for cash and cards in a restaurant or coffee shop. With QR codes integrated into your business, improve customer engagement and streamline operations.
Comprehensive Analytics
Subscribers of ViralQR receive detailed analytics and tracking tools in light of having a view of the core values of QR code performance. Our analytics dashboard shows aggregate views and unique views, as well as detailed information about each impression, including time, device, browser, and estimated location by city and country.
So, thank you for choosing ViralQR; we have an offer of nothing but the best in terms of QR code services to meet business diversity!
State of ICS and IoT Cyber Threat Landscape Report 2024 previewPrayukth K V
The IoT and OT threat landscape report has been prepared by the Threat Research Team at Sectrio using data from Sectrio, cyber threat intelligence farming facilities spread across over 85 cities around the world. In addition, Sectrio also runs AI-based advanced threat and payload engagement facilities that serve as sinks to attract and engage sophisticated threat actors, and newer malware including new variants and latent threats that are at an earlier stage of development.
The latest edition of the OT/ICS and IoT security Threat Landscape Report 2024 also covers:
State of global ICS asset and network exposure
Sectoral targets and attacks as well as the cost of ransom
Global APT activity, AI usage, actor and tactic profiles, and implications
Rise in volumes of AI-powered cyberattacks
Major cyber events in 2024
Malware and malicious payload trends
Cyberattack types and targets
Vulnerability exploit attempts on CVEs
Attacks on counties – USA
Expansion of bot farms – how, where, and why
In-depth analysis of the cyber threat landscape across North America, South America, Europe, APAC, and the Middle East
Why are attacks on smart factories rising?
Cyber risk predictions
Axis of attacks – Europe
Systemic attacks in the Middle East
Download the full report from here:
https://sectrio.com/resources/ot-threat-landscape-reports/sectrio-releases-ot-ics-and-iot-security-threat-landscape-report-2024/
PHP Frameworks: I want to break free (IPC Berlin 2024)Ralf Eggert
In this presentation, we examine the challenges and limitations of relying too heavily on PHP frameworks in web development. We discuss the history of PHP and its frameworks to understand how this dependence has evolved. The focus will be on providing concrete tips and strategies to reduce reliance on these frameworks, based on real-world examples and practical considerations. The goal is to equip developers with the skills and knowledge to create more flexible and future-proof web applications. We'll explore the importance of maintaining autonomy in a rapidly changing tech landscape and how to make informed decisions in PHP development.
This talk is aimed at encouraging a more independent approach to using PHP frameworks, moving towards a more flexible and future-proof approach to PHP development.
Generative AI Deep Dive: Advancing from Proof of Concept to ProductionAggregage
Join Maher Hanafi, VP of Engineering at Betterworks, in this new session where he'll share a practical framework to transform Gen AI prototypes into impactful products! He'll delve into the complexities of data collection and management, model selection and optimization, and ensuring security, scalability, and responsible use.
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfPeter Spielvogel
Building better applications for business users with SAP Fiori.
• What is SAP Fiori and why it matters to you
• How a better user experience drives measurable business benefits
• How to get started with SAP Fiori today
• How SAP Fiori elements accelerates application development
• How SAP Build Code includes SAP Fiori tools and other generative artificial intelligence capabilities
• How SAP Fiori paves the way for using AI in SAP apps
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™UiPathCommunity
In questo evento online gratuito, organizzato dalla Community Italiana di UiPath, potrai esplorare le nuove funzionalità di Autopilot, il tool che integra l'Intelligenza Artificiale nei processi di sviluppo e utilizzo delle Automazioni.
📕 Vedremo insieme alcuni esempi dell'utilizzo di Autopilot in diversi tool della Suite UiPath:
Autopilot per Studio Web
Autopilot per Studio
Autopilot per Apps
Clipboard AI
GenAI applicata alla Document Understanding
👨🏫👨💻 Speakers:
Stefano Negro, UiPath MVPx3, RPA Tech Lead @ BSP Consultant
Flavio Martinelli, UiPath MVP 2023, Technical Account Manager @UiPath
Andrei Tasca, RPA Solutions Team Lead @NTT Data
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...James Anderson
Effective Application Security in Software Delivery lifecycle using Deployment Firewall and DBOM
The modern software delivery process (or the CI/CD process) includes many tools, distributed teams, open-source code, and cloud platforms. Constant focus on speed to release software to market, along with the traditional slow and manual security checks has caused gaps in continuous security as an important piece in the software supply chain. Today organizations feel more susceptible to external and internal cyber threats due to the vast attack surface in their applications supply chain and the lack of end-to-end governance and risk management.
The software team must secure its software delivery process to avoid vulnerability and security breaches. This needs to be achieved with existing tool chains and without extensive rework of the delivery processes. This talk will present strategies and techniques for providing visibility into the true risk of the existing vulnerabilities, preventing the introduction of security issues in the software, resolving vulnerabilities in production environments quickly, and capturing the deployment bill of materials (DBOM).
Speakers:
Bob Boule
Robert Boule is a technology enthusiast with PASSION for technology and making things work along with a knack for helping others understand how things work. He comes with around 20 years of solution engineering experience in application security, software continuous delivery, and SaaS platforms. He is known for his dynamic presentations in CI/CD and application security integrated in software delivery lifecycle.
Gopinath Rebala
Gopinath Rebala is the CTO of OpsMx, where he has overall responsibility for the machine learning and data processing architectures for Secure Software Delivery. Gopi also has a strong connection with our customers, leading design and architecture for strategic implementations. Gopi is a frequent speaker and well-known leader in continuous delivery and integrating security into software delivery.
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
Self-motivation and Academic Performance In Computer Programming Language Using a Hybridised Machine Learning Technique
1. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 12
Self-motivation and Academic Performance In Computer
Programming Language Using a Hybridised Machine Learning
Technique
Isaac Kofi Nti ntious1@sgmail.com
Department of Computer Science
Sunyani Technical University
Sunyani, Ghana
Juanita Ahia Quarcoo juan83p@yahoo.com
Department of Computer Science
Sunyani Technical University
Sunyani, Ghana
Abstract
The advancement in artificial intelligence (AI) and Machine learning (ML) have made it easier to
foreknown feature happens from current and past trends. Once Self-efficacy and self-confidence
are believed to be, an individual trait associated with academic brilliance. Using a hybridised
Random Forest and Support Vector Machine (RFSVM) ML model we predicted students’
academic performance in computer programming courses, based on their self-confidence, self-
efficacy, positive thinking, focus, big goals, a motivating environment and demographic data.
Benchmarking our RFSVM model against Decision Tree (DT) and K-Nearest Neighbour (K-NN)
model, the RFSVM recorded and accuracy of 98% as against 95.45% for DT and 36.36% for K-
NN. The error between actual values and predicted values of the RFSVM model was better
(RMSE = 0.326401, MAE = 0.050909) and compared with the K-NN (RMSE = 2.671397, MAE =
1.954545) and DT models (RMSE = 0.426401, MAE = 0.090909). The results further revealed
that students with a high level of self-confidence, self-efficacy and positive thinking performed
well in computer programming courses.
Keywords: Self-Confidence, Self-Efficacy, Individual-Interest, Positive-Thinking, Focus, Personal
Goals, Motivating Environment, Academic Performance, Random Forest, Super Vector Machine.
1. INTRODUCTION
Effectively achievement of a preferred academic long-term goal requires both intelligence and
effort. Even though much attention in research is regularly paid to cognitive factors, such as
intellect and academic ability, non-cognitive factors significantly contribute to academic
performance (Jung, Zhou, & Lee, 2017). Academic self-directive is a crucial contributor to
academic achievement (Honicke & Broadbent, 2016; Jung et al., 2017; Lee, Lee, & Bong, 2014),
it signifies the orderly and the active application of self-development to achieve academic goals,
but students’ carry out academic self-directive more efficiently when they are hugely motivated
(Lee et al., 2014). Having low motivation towards study-associated tasks may be a common and
frequent obstacle in self-regulated learning.
Consequently, students should regulate their motivation to attain their study-associated goals,
particularly on choices and actions that affect their academic work (e.g., meeting friends). To
control their motivation students can harness from the various psychological feature regulation
methods, that is, self-monitoring methods that aim to manage and improve motivation (Grunschel,
Schwinger, Steinmayr, & Fries, 2016). When students have strong self-believe about their
2. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 13
competence, high values for their academic goal, they are more likely strategised, observer and
reflect their goal accomplishment and fine-tune their regulatory processes accordingly.
In (Dweck, Walton, & Cohen, 2014) the authors argue that psychological factors also known as a
motivational or non-cognitive factor are higher predictors students’ academic performance as
compared cognitive factors in some cases. Again in (Dweck et al., 2014), authors further
elaborated that these motivational factors also offer hopeful levers for levitating the achievement
of underprivileged children and, eventually, narrowing achievement gaps based on race and
income. In other studies, the authors see every person as an island of their own with different
inbuilt motivations, ambitions, perception and abilities. Whiles self-efficacy has long been seen as
a critical factor of academic performance. A counter-position is that self-efficacy is simply a mirror
image of past performance (Talsma, Schüz, Schwarzer, & Norris, 2018).
Despite the numerous contribution in research on the effect of cognitive and non-cognitive factors
on academic performance, little is known on how demographic data and non-cognitive factors
jointly affect students’ academic performance in a specific course such as computer programming
language.
The present study proposes an artificial intelligence (AI) model to predict students’ academic
performance in programming courses such as C++, JAVA and VB.net based on their self-
motivation level and demography data, using a hybridised machine learning technique of Random
Forest (RF) and Support Vector Machine (SVM) (RFSVM). To achieve our stated aim, this study
outline these specific objectives: (i) to proposed a hybridised Random Forest (RF) and Support
Vector Machine (SVM) (RFSVM) students’ academic performance prediction model. (ii) To
identify the weak, learners in programming courses at the earliest stage of their computer science
education, so that counsellor and management can offer them the necessary help. (iii) Reduce
students’ failure in computer programming courses by increasing their academic performance in
programming courses. It is hypothesised that (i) student with a higher motivation level would
perform better in computer programming courses (ii) Good performance in programming courses
has nothing to do with age.
The current study would lead to students’ academic performance prediction based on their
demographic data and self-motivation level, so that course lectures and an academic counsellor
will be able to take the necessary actions to identify weak learners and help them accordingly.
Also, based on the outcome, the probable performance of newly admitted students can be the
accessed forehead
The remaining of the current paper is organised as follows. Section 2 covers the review of the
literature on students’ academic performance and cognitive and non-cognitive factors. Section 3
discusses our methodology for analysing and predicting students’ academic performance in
programming language courses based on the degree of self-motivation. Section 4 presents
finding and discusses results. Section 5 concludes this study and Section 6 describes limitations
and possibilities for future research.
2. SELF-MOTIVATION
Self-motivation is believed to be complicated; it is linked with one’s level of creativity in setting
thought-provoking goals for him or herself. The following are considered for building a healthy
level of self-motivation; the following four factors are needed. (i) Self-confidence and self-efficacy.
(ii) Positive-thinking and positive thinking about the future. (iii) Focus and strong goals. (iv) A
motivating environment.
Self-confidence and Self-efficacy: a crucial part of being self-motivated is having acceptable
levels of self-assurance, self-efficacy and self-confidence. Self-efficacy is defined as a belief in
one’s capability to succeed and one’s ability to achieve the goals set for oneself (AL-Baddareen,
Ghaith, & Akour, 2015). High self-efficacy to results in an individual’s ability to see tough goals as
3. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 14
a dare, whereas individuals with low self-efficacy would likely see same goals as being away from
their capabilities, and might not even try to attain them.
Positive-thinking and Positive-thinking about The Future: thinking positively is closely
associated with self-confidence as a factor in self-motivation. It is vital to look at everything
positively, even when things are going opposite to planned. Thinking positively helps one to think
about an attractive future.
Focus and healthy goals: setting a goal for oneself gives a clear direction. One goal should be
clear, measurable, and specificity and behaviour based not outcomes, Challenge, commitment
and regularity of feedback.
Motivating environment: the last point is surrounding oneself with the resources and people that
remind one of his/her goals.
2.1 Related Works
The environment of tertiary education comprises several stakeholders, such as learners, parents,
staff, faculty, university administrators, and other contributors (Ferguson, 2017). Each to
contribute to the academic success of their learners, thus their semester overall grade point
average (GPA). The performance of a student is a key and essential factor in the life of every
student and the university administration. Tertiary education demands high academic success of
every student; low academic success can lead to academic failure, which can cause one to go on
probation, loss a scholarship and grant or expelled from the institution for good. Most students go
to universities and colleges, progress through the system, and generally graduate successfully
without having a deeper understanding of what it takes to be successful academically and what
factors will possibly contribute to that success. Hence, everything that contributes either positively
or negatively, to the academic performance of students’ needs to be examined.
The following researchers (Bernard & Dzandza, 2018; Maya, 2015; Okyeadie Mensah, Nizam,
Mensah, & Nizam, 2016; Owusu-Acheaw & Larson, 2015; Rashid & Asghar, 2016; Salomon &
Ben-David, 2016; Sudha & Kavitha, 2016; Wentworth & Middleton, 2014) surveyed how students
impact students' academic performance use of social media. Their results revealed that a small
negative correlation exists between the amounts of time students spent on social media and their
academic performance. Other surveys of social media by (Al-rahmi, 2013; Al-rahmi, Zeki, Alias, &
Saged, 2017) effect on academic performance, concluded that social media aids the academic
experience of students, but there is a need for them to manage and control their time (Alwagait,
Shahzad, & Alim, 2015).
In (AL-Baddareen et al., 2015), the authors examined the effects that achievement goal self-
efficacy and metacognition bear on the academic motivation of university students in Jordan. The
study outcome revealed that the joint effect of metacognition and mastery goals influence the
university student’s academic motivation; that is, metacognition and mastery goals can predict
academic motivation of university students. The effects of 3 prominent five personality qualities
(conscientiousness, agreeableness, and openness to experience) on academic achievement
were examined by (Mammadov, Cross, & Ward, 2018) on 161 gifted middle and high school
learners. The researchers established that a relationship existed between all these three qualities
and academic achievement. In other research work, the link between one’s trait of emotional
intelligence (TEI) and academic performance (AP) was examined based on perceived social
support (PSS), engagement coping (EC), and adjustment, in the environment of the university
transition. Their outcome showed that TEI is a direct predictor of higher PSS and the greater use
of EC strategies (Perera & DiGiacomo, 2015).
The effect of using motivational regulation strategies on academic procrastination, students'
academic performance, and well-being were examined (Grunschel et al., 2016). The extent to
which students’ AP is affected by their engagement (learners’ participation in academic activities
and commitment to the school’s rules, vision and mission), academic self-efficacy (the learners’
4. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 15
intellect of their own abilities), and academic motivation (the learners’ wish in intensification of
their academic performance) (Dogan, 2015). The effect of self-efficacy and the big five
personality traits on AP was carried out by (Stajkovic, Bandura, Locke, Lee, & Sergent, 2018). An
assessment of the influence of learner-faculty communications on student academic motivation
was carried out in (Trolian, Jach, Hanson, & Pascarella, 2017). Their outcome revealed that
learner-faculty communications greatly influence student's self-motivation. In (Holland et al.,
2016), the authors investigated the effect of improved extrinsic motivation on fluent (i.e., efficient
and accurate) AP in pediatric medulloblastoma survivors.
The associations between self-regulation of learning, self-efficacy and AP was examined in
(Agustiani, Cahyad, & Musa, 2016) among students of faculty of Psychology at Universitas
Padjadjaran. Their results revealed a positive relationship exists between self-efficacy, self-
regulation of learning and AP of students. Also, in (Schwartz, 2017) an assessment of the effect
of the weekly student-led discussions on goal-setting, goal accomplishment, effort, achievement,
intrinsic motivation, and satisfaction. In (Cetin, 2015), a survey in the Early Childhood Education
Department revealed that there is no correlation between academic self-regulated learning,
academic-motivation and students’ academic performance. Again (Suprayogi & Valcke, 2014)
examined the association between goal orientation, academic efficacy and academic
achievement and see which of these, is a crucial predictor of academic achievement.
In (Cigan, 2014), the relationship between the strength of learners’ inherent and extrinsic
learning-motivation and their socio-demographic characteristics were examined. The relation
between self-discipline, self-efficacy and AP was examined in (Jung et al., 2017). In the report
presented in (Ferguson, 2017), an assessment of the correlation between AP and mindset,
academic motivation, academic Self-Efficacy among Undergraduate communication sciences and
disorders students at Andrews University. In (Lee et al., 2014), the researchers examined how
personal interest, as a sentimental motivational variable, could predict academic performance
and self-regulation, beyond what academic self-efficacy can predict. The link between AP and
self-efficacy was examined in (Komarraju & Nadler, 2013). In (Ross, Perkins, & Bodey, 2016) the
authors examined the interrelationships between information literacy, self-efficacy and the
different types of academic motivation. (Wilson & Narayan, 2016) investigated the associations
between self-efficacy, self-regulated learning strategy use and AP.
In (Chang et al., 2014), the authors investigated by what means does Internet self-efficacy aids
learners to convert motivation into learning achievement, and its effect on learning performance.
In (Zimmerman & Kitsantas, 2014), authors compared learners’ self-directive and self-discipline
measures and their prediction of AP. Research work by (Rimfeld, Kovas, Dale, & Plomin, 2016)
examined how personal pure perseverance and passion for long-term goals and genetics predicts
academic achievement. The impact of students’ motivation and personality traits on academic
performance in blended and online learning environs was investigated in (Alkış & Temizel, 2018).
An investigation of the association between achievement-motivation, academic self- concept and
academic achievement of high school students was conducted by (Affum-osei, Adom, Barnie, &
Forkuoh, 2014). An examination of the connections sandwiched between motivational beliefs
(task value, self-efficacy and control of learning beliefs) and use of metacognitive learning
schemes amid teacher education students in Uganda was carried out by (Muwonge, Schiefele,
Ssenyonga, & Kibedi, 2017). According to reviewed literature, the demographic data, which affect
a student’s performance, are as shown in Table 1.
S/N Factor Reference
1. Age (Kieti, 2017; Musso, Kyndt, Cascallar, & Dochy, 2013;
Oladokun, Adebanjo, & Charles-Owaba, 2008)
2. Gender (Chen, Hsieh, & Do, 2014; Musso et al., 2013; Oladokun et
al., 2008)
3. Father’s occupation (Bhardwaj & Pal, 2011; Devasia, Vinushree, & Hegde, 2016;
Goga, Kuyoro, & Goga, 2015; Musso et al., 2013; Yadav &
Pal, 2012; Yusif, Yussof, & Noor, 2011)
5. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 16
4. Mother’s occupation (Bhardwaj & Pal, 2011; Devasia et al., 2016; Fleischer, 2015;
Goga et al., 2015; Musso et al., 2013; Yadav & Pal, 2012;
Yusif et al., 2011)
5. Ethnicity Ethnicity (Adejo & Connolly, 2018; Attuquayefio, NiiBoi, &
Addo, 2014; Schmitt et al., 2009; Tuen et al., 2019)
6. Parents’ marital status (Cortez & Silva, 2008; Goga et al., 2015)
7. Family size (Agrawal & Mavani, 2015; Bhardwaj & Pal, 2011; Devasia et
al., 2016; Goga et al., 2015; Khasanah & Harwati, 2017;
Osmanbegovic & Suljic, 2012; Osmanbegović, Suljić, & Agić,
2014; Yadav & Pal, 2012; Yeboah, 2014; Yusif et al., 2011)
TABLE 1: Demographic data and students’ academic performance.
Given the relationship between one’s self-motivation (self-confidence, self-efficacy, positive
thinking, focus, reasonable goals, and a motivating environment) and demographic data, it is
possible that demographic data will play a role in the effects that self-motivation has on academic
performance. However, little is known about how demographic data may influence the
relationship between self-motivation and academic performance, especially in developing
countries. This paper examined the extent to which the combination of students’ demographic
data and self-motivation (self-confidence, self-efficacy, individual interest, positive thinking, focus,
personal goals, and a motivating environment) predict students’ academic performance among
Computer Science (CPS) and Information and Communication Technology (ICT) students in
computer programming language. Using a hybridised machine learning technique of Random
Forest (RF) and Support Vector Machine (SVM) (RFSVM).
3. MATERIALS AND METHODS
A quantitative and experimental research approach was adopted for this study. Self-motivation
factors priority order questionnaire was adopted for the collection of the research primary data.
The first phase of the questionnaire concentrated on getting the demographic data (gender, age,
educational background and region of origin). The second part, Self-Motivation had four
subsections, which tested each participant’s (i) Self-confidence and self-efficacy. (ii) Positive-
thinking and positive-thinking about the future. (iii) Focus and reasonable goals (iv) A motivating
environment.
3.1 Research Model
Figure 1 shows the research model for this study, showing how the independent variable’s
demographic data (gender, age, educational background and region of origin) and self-motivation
(self-confidence, self-efficacy, individual interest, positive thinking, focus, personal goals, and a
motivating environment) joint predict student’s score in 3 programming language courses.
6. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 17
Demographic Variables (DVs)
Gender
Age
Educational background
Region of origin
Motivation Variable (MVs)
self-confidence
self-efficacy
individual interest
positive thinking
Focus
personal goals
motivating environment
Academic Performance
End of semester score in
C++
Java
VB.Net
DVs + MVs
Independent variables
Dependent Variables
FIGURE 1: Research Model.
3.2 Variables
Two variables were considered, Student’s performance (course score) as the dependent variable
while demographic data and self-motivation as independent variables. Semester exams score for
C++, JAVA and VB.Net were obtained from the Department with the participant’s consent to
measure academic performance.
3.3 Research Design
This section gives the details of the approaches adopted by this work to analyse the joint effect of
students’ self-motivation and demographic data on their academic performance.
3.3.1 Machine Learning Algorithms
Machine-Learning is the science of making computers to learn and behave like humans, and with
an autonomous-improvement in their learning over time, by feeding them data and information in
the form of observations and real-world interactions (Faggella, 2018). There are various machine-
learning algorithms. Nevertheless, the scope of this paper is not to describe the different types of
machine-learning algorithm. This section offers a brief description of the two chosen machine-
learning algorithms and how they were used in this study.
Support Vector Machine (SVM): SVM is a supervised machine learning algorithm for performing
regression and classification task (Belgiu & Drăgu, 2016). SVM serves as the linear separator
sandwiched between two data-points to detect two different classes in the multidimensional
environs (Vaghela, Bhatt, & Patel, 2015). The SVM algorithm is as follows:
Let the dataset for training be denoted by
The SVM is optimised by
7. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 18
With the function , the vectors (training dataset) are mapped into a dimension of higher
space. At this dimension, the SVM finds a linear separating hyperplane with the best margin. The
kernel function was formulated as . Four underlying kernels are available;
however, for this study, the linear given in equation (3.3) was used.
Linear:
Random forest RF: the RF is a supervised machine learning algorithm, combines the
performance of the various decision-tree algorithm (Rodriguez-Galiano, Sanchez-Castillo, Chica-
Olmo, & Chica-Rivas, 2015; Wakefield, 2013). The RF accepts an input of (u), with u been a
vector consisting of the variable of different evidential features examined for a given training area.
Several regression or classification trees (N) are built by the RF and averages their results.
Therefore, for N tress, the FR predictor is given as:
The RF is used as a feature selection mechanism to select inputs that are highly correlated
students’ academic performance to feed the SVM
3.3.2 Data Collection and Integration Framework
Figure 2 shows the framework for data collection and integration. The model has four distinct
phases, namely:
Data collection and integration: 216 records from students, offering CPS and ICT consist of
their demographic data (Dataset A), self-motivation answered questionnaires (Dataset B), and
past academic records (Dataset C) are integrated at this stage using SQL database server 2014.
Thus and Dataset A + Dataset B = Dataset D and Dataset A + Dataset B + Dataset C = Dataset
E.
Data Transformation: this stage took care of the data pre-processing. At this stage the
integrated datasets (D and E) were passed through 3 stages, (i) data cleaning, which includes
filling in missing values, smoothing noise, identification and removing of outliers where necessary
and resolving data inconsistency. (ii) Data normalisation and aggregation (iii) data reduction,
where the volume of data is reduced, but produce same or similar analytical results using feature
selection and feature extraction. All this was carried out using python.
Patterns Extraction: Python, an open source software, was used to construct the predicting
(RFSVM) model.
8. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 19
Self-Multivation
Student
Database
Data SelectionData Cleaning
Normalization
Testing
Data (15%)
Training
Data (85%)
Splitter
Clean Data Partitioning
Clean
Data
Demographic
Data
0111
0011
1010Data
Reduction
Data Collection & Integration Phase
Data Transformation
Pattern
Extraction
Training, Testing & Evaluation
SQL
Python
Weka
&
Python
Dataset A
Dataset BDataset C
Dataset D
Dataset E
Course
score
A+
A
B+
B
C+
C
D+
D
F
Output
Result
Evaluation
Accuracy
Closeness
SVM
Learned Pattern
RF
FIGURE 2: Study Framework for Data Collection and Integration.
Feature Selection
In a quest to use the feature that has high impact, we calculated feature impact by using feature
importance ranking by (Breiman, 2001) to remove features of least importance. A single random
forest (RF) was trained using the training dataset (D_Train) to rank features.
Feature selection Algorithm
1. Train an FR suing D_Train (all k features)
2. Compute average RMSE of model for cross-validation data (C-V)
3. Rank performance by
4. For each subset of k
5. Train a new forest from ki features, highest VI
6. Calculate the average RMSE of the model on C-V set
7. Re-rank the features (k)
8. End for
9. Find ji with smallest RMSE
9. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 20
3.3.3 Data Normalisation
Our selected feature was transformed within the range [0, 1] using equation (3.5) for better
performance of the predictive model. Where: V
’
is the new scaled value obtained after
normalisation; v the value to be normalised, are the minimum and maximum value
of the dataset.
3.3.4 Training Techniques
The learning process adopted by this paper was by the supervised process, where the intended
input variables (student self-motivation and demographic data) and outputs target (student test
score) is entered into the network.
3.3.5 Evaluation Performance Metrics
Root mean squared error (RMSE), Mean absolute percentage error (MAPE) and Correlation
coefficient (R) as defined in (Javed, Gouriveau, & Zerhouni, 2014; Rajashree, Dash, & Bisoi,
2014) and calculated as in question (3.6), (3.7) and (3.8) respectively, were used as performance
metrics measure.
3.4 Procedure
Self-motivation Scale (SMS) designed by (Mind-Tools, 2018) was adopted for assessing
students’ self-motivation level. The questionnaire consisted of 4 parts (Self-Confidence & Self-
Efficacy, Positive thinking, focus & Strong goals and Motivating environment) with 5 points Likert
scale, where participants expressed their consent ranging from not at all to very often. The score
for each phase was calculated, and a higher score indicates that a particular self-motivation
attribute has a higher level. The overall Self-Motivation Index (SMI) was calculated based on
(Mind-Tools, 2018), for this research participant with SMI within (12 – 27), (28 – 43) and (44 – 60)
was interpreted as below-average, average and high self-motivation respectively.
3.5 Participants
Using purposeful sampling technique, 216 students from the Department Computer Science in
Sunyani Technical University in Sunyani, Ghana, offering higher National Diploma (HND) in
Information Communication and Technology (ICT) and Computer Science took part in this
research. Participants of the current study completed an online questionnaire at their
convenience within 30 days. Participants were up-to-date with the purpose of the study, their
approval was sought, and participation was voluntary. A pre-test of the questionnaire was
performed on a small group of students from Catholic University College in Sunyani to enhance
questionnaire significance, simplicity, and specificity. Participant of the pre-test gave a verbal
response to researchers expressing the easy in understanding each question and whether each
respondent can provide the needed data. Results from the pre-test helped design the
questionnaire to suit the expected purpose of the study.
10. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 21
4. Experiments and Analysis of Results
The results obtained by the methodology described in this paper are presented in this section.
Statistical tools such mean, standard deviation, variance skewness and kurtosis were applied,
and results presented. The dataset for the experiment was divided into two sets, namely: training
and testing sets, as shown in Table 2.
Total Dataset Training Dataset Testing Dataset
516 85% 15%
TABLE 2: Dataset Partitioning.
4.1 Results and Discussions
The descriptive statistics were performed with Statistical Package for the Social Sciences on the
collected data, while Python was used for the implementation of the proposed RFSVM classifier.
4.2 Descriptive Statistics
Table 3 gives the gender analysis of respondents. The results reveal that a high percentage of
63.9% of respondents were males. This difference in gender is because of less female studying
science and engineering related courses in higher education.
Gender Frequency Percent Valid Percent
Cumulative
Percent
Female
78 36.1 36.1 36.1
Male 138 63.9 63.9 100.0
Total 216 100.0 100.0
TABLE 3: Gender Analysis of Respondents.
The age distribution of respondents is, as shown in Table 4. A higher percentage (83.3%) of the
respondents were with the age bracket of (21 – 25), 11.1% with the brackets of (26 – 30) and
5.6% in the brackets of (15 – 20).
Age Group Frequency Percent Valid Percent
Cumulative
Percent
15 - 20 12 5.6 5.6 5.6
21 - 25 180 83.3 83.3 88.9
26 - 30 24 11.1 11.1 100.0
Total 216 100.0 100.0
TABLE 4: Age Analysis of Respondents.
Table 5 shows the statistical results of the response obtained from respondents. The results
reveal that the data distribution is moderately skewed. Again, the computed values of Kurtosis
reveals that the data distribution is slightly leptokurtic and platykurtic.
11. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 22
Features
Statistic Mean
Std.
Deviation Variance Skewness Kurtosis
N Range Min. Max. Statistic
Std.
Error Statistic Statistic
Statis
tic
Std.
Error
Statist
ic
Std.
Error
Age 216 11 15 26 21.22 .148 2.180 4.750 -.125 .166 3.421 .330
Focus 216 8 2 10 6.73 .121 1.772 3.139 -.304 .166 -.371 .330
Gender
216 1 0 1 .64 .033 .481 .232 -.582 .166
-
1.676
.330
Motivating 216 4 1 5 3.25 .068 1.000 1.000 .203 .166 -.610 .330
Positive 216 11 9 20 14.40 .174 2.555 6.529 -.021 .166 -.558 .330
Self-Efficacy 216 11 9 20 14.42 .196 2.881 8.300 .338 .166 -.602 .330
Thinking 216 6 4 10 7.80 .110 1.623 2.635 -.458 .166 -.644 .330
Valid N
(listwise)
216
TABLE 5: Descriptive Statistics of Respondents.
4.2.1 Feature Ranking and Importance
Table 6 and figure 3 shows the independent's input variables rankings and importance offered by
the random forest algorithm. From figure 3, Self-Confidence & Self-Efficacy is the highest
predictor of students’ academic performance in programming courses with an importance score
of (0.239825), which disagrees with (Talsma et al., 2018) arguments that self-efficacy is simply a
mirror image of past performance, however, agrees with (AL-Baddareen et al., 2015) studies.
Positive thinking was second with (0.228370) importance score. Focus and reasonable goals with
an importance score of (0.211707) followed by Motivating Environment with an importance score
of (0.183711).
The study revealed that demography data gender had a better score of importance (0.098140)
which confirms (Chen et al., 2014; Musso et al., 2013; Oladokun et al., 2008) studies, as
compared with age, which had little significance score of (0.038248), nevertheless, there is a
relation with age and academic performance as argued by (Kieti, 2017; Musso et al., 2013;
Oladokun et al., 2008).
S/N Feature Feature importance’s
0 Gender 0.098140
1 Age 0.038248
2 Self-Confidence & Self-Efficacy 0.239825
3 Positive Thinking 0.228370
4 Focus & Strong goals 0.211707
5 Motivating Environment 0.183711
TABLE 3: Feature ranking by RF.
The result also revealed that is better to inculcate desirable and high personality traits such (self-
confidence & self-efficacy, positive thinking and focus & strong goals) in students within the
school environments, than instead creating a motivation-motivating environment. That is building
these traits in them enable them to perform well academically than building a motivating
environment around them, which confirms (Dweck et al., 2014) assessment. The age factor
cannot be left out; the results reveal that age plays a little factor of importance in learning
programming. Hence, programming as a course should be introduced early within the first year or
during the first semester of the second year. Since students within the ages of 15 – 25 performed
better than 26 – 30.
12. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 23
FIGURE 3: Feature Ranking and Importance.
However, the outcome clearly showed that self-motivation indication factors are of higher
importance in predicting students’ academic performance, and confirms studies by (Dweck et al.,
2014; Lee et al., 2014). That is, for a student to be better academically in programming courses,
such students must exhibit a high level of self-motivation. To measure how efficient is our
proposed model, we benchmarked our RFSVM model with other known machine-learning
algorithms such as Decision Tree (DT) and K-Nearest Neighbour and Table 7, shows the RMSE,
MAE, Accuracy and R
2
values. The proposed model obtained an accuracy of approximately 98%
as compared with 95% for DT, 0.36% for K-NN. The error between actual values and predicted
values of our proposed model was less (RMSE = 0.326401, MAE = 0.050909) and compared with
the K-NN (RMSE = 2.671397, MAE = 1.954545) and DT models (RMSE = 0.426401, MAE =
0.090909).
Models RMSE MAE R^2 Accuracy
DT 0.426401 0.090909 0.944724 0.954545
K-NN 2.671397 1.954545 -1.169598 0.363636
RFSVM 0.326401 0.050909 0.974724 0.979945
TABLE 4: Accuracy Metric Comparison.
13. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 24
FIGURE 4: Boxplot Comparison of Models.
The outcome of the boxplot shown in figure 4, shows that the RFSVM model is the most suitable
for students’ academic performance prediction based on self-motivation and demographic data.
5. CONCLUSIONS
This paper proposed a hybridised machine learning technique to predict the academic
performance of students in computer programming courses based on their self-motivation and
demography data. Like all other studies on students’ academic performance, we sought in
identifying weak learners in computer programming courses at the earliest stage of their
academic ladder, so that the necessary help can be offered to them by their respective academic
counsellor and school management. The proposed model was compared with other machine
learning algorithm base on model prediction efficiency, RMSE and MAE. All machine learning
models (Decision Tree (DT), K-Nearest Neighbour (K-NN) and RFSVM) used for the study gained
satisfactory results. However, the result revealed that the proposed hybrid model (RFSVM)
performed better than DT and K-NN.
The proposed model yield and overall accuracy measure of 97.9945% and gave a better error
value as compared with DT and K-NN. The proposed model was able to identify almost all
students with self-motivation index of below average. The outcome confirms an agreement with
past research work, that machine-learning techniques have the power to produce an efficient
model for predicting students’ academic performance.
Also, the study revealed that personality traits such as (Self-Confidence & Self-Efficacy, Positive
Thinking and Focus & Strong goals) of a student has a higher impact on their academic as far as
computer programming is concerned. Students with higher personal traits turn to perform well in
computer programming. That is building these personality traits in them offer better academic
performance than building a motivating environment around them. Age was observed to pose a
little significance on the academic performance of students in programming; hence, it is
concluded that programming should be introduced at the early stage of the educational ladder. If
not primary education, secondary at most is better.
The weaker learners identified were directed to the school counselling units to work on their self-
motivation area that is not strong. Though their performance afterwards has not yet been verified,
it is believed that some improvement would be realised. With this outcome, we propose the
14. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 25
incorporation of building a better self-motivation into students’ academic calendar, which we
believe will help them academically. It is hoped that the proposed model is implemented in
academic institutions to help promote academic excellence in programming languages.
6. LIMITATIONS AND FUTURE RESEARCH
The outcomes of the present study are limited to only the experimental sample, which should, in
future, be extended across regions to make the outcome globally applicable. Future research
work could feather include more demographic data such a father’s occupation, mother’s
occupation, ethnicity, parents’ marital status and family size as input features to impact prediction
accuracy.
7. ACKNOWLEDGEMENT
Glory be to God Almighty for bringing us this far. We also express our sincere thanks and
acknowledged the contribution and assistance of all staffs of Computer Science and Electrical &
Electronic Engineering Department of STU.
Financial and Ethical Disclosures
Funding: Authors did not receive any fund anywhere.
Conflict of Interest: The authors of the current study declare that they have no conflict of
interest.
8. REFERENCES
[1] Adejo, O. W., & Connolly, T. (2018). Predicting student academic performance using multi-
model heterogeneous ensemble approach. Journal of Applied Research in Higher
Education, 10(1), 61–75. https://doi.org/10.1108/JARHE-09-2017-0113.
[2] Affum-osei, E., Adom, E. A., Barnie, J., & Forkuoh, S. K. (2014). Achievement motivation,
academic self-concept and academic achievement among high school students. European
Journal of Research and Reflection in Educational Sciences, 2(2), 24–37.
https://doi.org/10.1016/B978-0-08-097086-8.92153-6.
[3] Agrawal, H., & Mavani, H. (2015). 10 Student Performance Prediction using Machine
Learning, 4(03), 111–113.
[4] Agustiani, H., Cahyad, S., & Musa, M. (2016). Self-efficacy and Self-Regulated Learning as
Predictors of Students Academic Performance. The Open Psychology Journal, 9(1), 1–6.
https://doi.org/10.2174/1874350101609010001.
[5] AL-Baddareen, G., Ghaith, S., & Akour, M. (2015). Self-Efficacy, Achievement Goals, and
Metacognition as Predicators of Academic Motivation. Procedia - Social and Behavioral
Sciences, 191, 2068–2073. https://doi.org/10.1016/j.sbspro.2015.04.345.
[6] Al-rahmi, W. M. (2013). The Impact of Social Media use on Academic Performance among
university students : A Pilot Study. Journal Of Information Systems Research and
Innovation, 1–10. https://doi.org/http://seminar.utmspace.edu.my/jisri/.
[7] Al-rahmi, W. M., Zeki, A. M., Alias, N., & Saged, A. A. (2017). Social Media and its Impact on
Academic Performance among University Students. The Anthropologist, 28(1–2), 52–68.
https://doi.org/10.1080/09720073.2017.1317962.
[8] Alkış, N., & Temizel, T. T. (2018). The Impact of Motivation and Personality on Academic
Performance in Online and Blended Learning Environments. Journal of Educational
Technology & Society, 21(3), 35–47.
[9] Alwagait, E., Shahzad, B., & Alim, S. (2015). Impact of social media usage on students
academic performance in Saudi Arabia. Computers in Human Behavior.
15. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 26
https://doi.org/10.1016/j.chb.2014.09.028.
[10] Attuquayefio, NiiBoi, S., & Addo, H. (2014). Using the UTAUT model to analyze students’
ICT adoption. International Journal of Education & Development Using Information &
Communication Technology, 10(3), 75–86. Retrieved from
http://ezproxy.usq.edu.au/login?url=http://search.ebscohost.com/login.aspx?direct=true&db=
ehh&AN=97923459&site=ehost-live.
[11] Belgiu, M., & Drăgu, L. (2016). Random forest in remote sensing: A review of applications
and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31.
https://doi.org/10.1016/j.isprsjprs.2016.01.011.
[12] Bernard, K. J., & Dzandza, P. E. (2018). Effect of social media on academic performance of
students in Ghanaian Universities: A case study of University of Ghana, Legon. Library
Philosophy and Practice, 2018(February).
[13] Bhardwaj, B. K., & Pal, S. (2011). Data Mining : A prediction for performance improvement
using classification. International Journal of Computer Science and Information Security,
9(4), 136–140.
[14] Bingham, T., & Conner, M. (2010). The New Social Learning: A Guide to Transforming
Organizations through Social Media. Berrett-Koehler Store, San Francisco, CA.
[15] Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
[16] Cetin, B. (2015). Academic Motivation And Self-Regulated Learning In Predicting Academic
Achievement in College. Journal of International Education Research (JIER), 11(2), 95–106.
https://doi.org/10.19030/jier.v11i2.9190.
[17] Chang, C. S., Liu, E. Z. F., Sung, H. Y., Lin, C. H., Chen, N. S., & Cheng, S. S. (2014).
Effects of online college student’s Internet self-efficacy on learning motivation and
performance. Innovations in Education and Teaching International, 51(4), 366–377.
https://doi.org/10.1080/14703297.2013.771429.
[18] Chen, J. F., Hsieh, H. N., & Do, Q. H. (2014). Predicting student academic performance: A
comparison of two meta-heuristic algorithms inspired by cuckoo birds for training neural
networks. Algorithms, 7(4), 538–553. https://doi.org/10.3390/a7040538.
[19] Cigan, V. (2014). Relationship between students’ motivation and their socio-demographic
characteristics. Linguistica, 54(1), 11–30. https://doi.org/10.4312/linguistica.54.1.11-30.
[20] Cortez, P., & Silva, A. (2008). Using Data Mining To Predict Secondary School Student
Performance. 5th Annual Future Business Technology Conference, 2003(2000), 5–12.
https://doi.org/10.13140/RG.2.1.1465.8328.
[21] Devasia, T., Vinushree, T. P., & Hegde, V. (2016). Prediction of Students Performance using
Educational Data Mining. 16.
[22] Dogan, U. (2015). Student engagement, academic self-efficacy, and academic motivation as
predictors of academic performance. Anthropologist, 20(3), 553–561.
https://doi.org/10.1080/09720073.2015.11891759.
[23] Dweck, S. carol, Walton, M. G., & Cohen, L. G. (2014). Academic Tenacity. United States
and. Retrieved from www.gatesfoundation.org.
[24] Faggella, D. (2018). What is Machine Learning? Retrieved October 8, 2018, from
https://www.techemergence.com/what-is-machine-learning/.
16. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 27
[25] Ferguson, L. H. (2017). Mindset, Academic Motivation, And Academic Self-Efficacy As
Correlates Of Academic Achievement Among Undergraduate Students in Communication
Sciences and. Andrews University. Retrieved from
https://digitalcommons.andrews.edu/dissertations/1648/.
[26] Fleischer, J. E. (2015). Information Communication Technology Usage Patterns in Second
Cycle Schools: A Study of Two Selected Senior High Schools in Ghana.
[27] Goga, M., Kuyoro, S., & Goga, N. (2015). A recommender for improving the student
academic performance. Procedia - Social and Behavioral Sciences, 180(November 2014),
1481–1488. https://doi.org/10.1016/j.sbspro.2015.02.296.
[28] Grunschel, C., Schwinger, M., Steinmayr, R., & Fries, S. (2016). Effects of using
motivational regulation strategies on students’ academic procrastination, academic
performance, and well-being. Learning and Individual Differences, 49, 162–170.
https://doi.org/10.1016/j.lindif.2016.06.008.
[29] Holland, A. A., Hughes, C. W., Harder, L., Silver, C., Bowers, D. C., & Stavinoha, P. L.
(2016). Effect of motivation on academic fluency performance in survivors of pediatric
medulloblastoma. Child Neuropsychology, 22(5), 570–586.
https://doi.org/10.1080/09297049.2015.1023272.
[30] Honicke, T., & Broadbent, J. (2016). The influence of academic self-efficacy on academic
performance: A systematic review. Educational Research Review, 17, 63–84.
https://doi.org/10.1016/j.edurev.2015.11.002.
[31] Javed, K., Gouriveau, R., & Zerhouni, N. (2014). SW-ELM: A summation wavelet extreme
learning machine algorithm with a priori parameter initialization. Neurocomputing, 123, 299–
307. https://doi.org/10.1016/j.neucom.2013.07.021.
[32] Jung, K. R., Zhou, A. Q., & Lee, R. M. (2017). Self-efficacy, self-discipline and academic
performance: Testing a context-specific mediation model. Learning and Individual
Differences, 60(October), 33–39. https://doi.org/10.1016/j.lindif.2017.10.004.
[33] Khasanah, A. U., & Harwati. (2017). A Comparative Study to Predict Student’s Performance
Using Educational Data Mining Techniques. IOP Conference Series: Materials Science and
Engineering, 215(1). https://doi.org/10.1088/1757-899X/215/1/012036.
[34] Kieti, J. M. (2017). An Investigation into Factors Influencing Students’ Academic
Performance in Public Secondary Schools in Matungulu Sub-County, Machakos County.
South Eastern Kenya University. https://doi.org/10.1111/j.1469-7610.2010.02280.x.
[35] Komarraju, M., & Nadler, D. (2013). Self-efficacy and academic achievement: Why do
implicit beliefs, goals, and effort regulation matter? Learning and Individual Differences, 25,
67–72. https://doi.org/10.1016/j.lindif.2013.01.005.
[36] Lee, W., Lee, M. J., & Bong, M. (2014). Testing interest and self-efficacy as predictors of
academic self-regulation and achievement. Contemporary Educational Psychology, 39(2),
86–99. https://doi.org/10.1016/j.cedpsych.2014.02.002.
[37] Mammadov, S., Cross, T. L., & Ward, T. J. (2018). The Big Five personality predictors of
academic achievement in gifted students: Mediation by self-regulatory efficacy and
academic motivation. High Ability Studies, 00(00), 1–23.
https://doi.org/10.1080/13598139.2018.1489222.
[38] Maya, k. G. (2015). Achievement scripts, media influences on Blacks students’ academic
performance, self-perceptions and carrier interests. Journal of Black Psychology, 42(3),
195–220. https://doi.org/10.1177/0095798414566510.
17. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 28
[39] Mind-Tools. (2018). How Self-Motivated Are You: Taking Charge of Your Goals and
Achievements. Retrieved from https://www.mindtools.com/pages/article/newLDR_57.htm.
[40] Musso, M. F., Kyndt, E., Cascallar, E. C., & Dochy, F. (2013). Predicting general academic
performance and identifying the differential contribution of participating variables using
artificial neural networks. Frontline Learning Research, 1(1), 42–71.
https://doi.org/10.14786/flr.v1i1.13.
[41] Muwonge, C. M., Schiefele, U., Ssenyonga, J., & Kibedi, H. (2017). Self-regulated learning
among teacher education students: Motivational beliefs influence on the use of
metacognition. Journal of Psychology in Africa, 27(6), 515–521.
https://doi.org/10.1080/14330237.2017.1399973.
[42] Okyeadie Mensah, S., Nizam, D. I., Mensah, O. S., & Nizam, I. (2016). the Impact of Social
Media on Students’ Academic. International Journal Of Education, Learning & Training
(IJELT), 1(1), 14–21. https://doi.org/10.24924/ijelt/2016.11/v1.iss1/14.21.
[43] Oladokun, V. O., Adebanjo, A. T., & Charles-Owaba, O. E. (2008). Predicting students’
academic performance using artificial neural network: A case study of an engineering
course. The Pacific Journal of Science and Technology, 9(1), 72–79.
[44] Osmanbegovic, E., & Suljic, M. (2012). Data mining approach for predicting student
performance. Journal of Economics and Business, X(1), 3–12.
[45] Osmanbegović, E., Suljić, M., & Agić, H. (2014). Determining Dominant Factor for Students
Performance Prediction by Using Data Mining. Vitez-Tuzla-Zagreb-Beograd-Bucharest,
XVII(34), 147–158.
[46] Owusu-Acheaw, M., & Larson, A. G. (2015). Use of Social Media and its Impact on
Academic Performance of Tertiary Institution Students: A Study of Students of Koforidua
Polytechnic, Ghana. Journal of Education and Practice, 6(6), 94–101.
[47] Perera, H. N., & DiGiacomo, M. (2015). The role of trait emotional intelligence in academic
performance during the university transition: An integrative model of mediation via social
support, coping, and adjustment. Personality and Individual Differences, 83, 208–213.
https://doi.org/10.1016/j.paid.2015.04.001.
[48] Rajashree, D., Dash, P. K., & Bisoi, R. (2014). A self adaptive differential harmony search
based optimized extreme learning machine for financial time series prediction. Swarm and
Evolutionary Computation, 19, 25–42. https://doi.org/10.1016/j.swevo.2014.07.003.
[49] Rashid, T., & Asghar, H. M. (2016). Technology use, self-directed learning, student
engagement and academic performance: Examining the interrelations. Computers in Human
Behavior, 63, 604–612. https://doi.org/https://doi.org/10.1016/j.chb.2016.05.084.
[50] Rimfeld, K., Kovas, Y., Dale, P. S., & Plomin, R. (2016). True grit and genetics: Predicting
academic achievement from personality. Journal of Personality and Social Psychology,
111(5), 780–789. https://doi.org/10.1037/pspp0000089.
[51] Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., & Chica-Rivas, M. (2015).
Machine learning predictive models for mineral prospectivity: An evaluation of neural
networks, random forest, regression trees and support vector machines. Ore Geology
Reviews, 71, 804–818. https://doi.org/10.1016/j.oregeorev.2015.01.001.
[52] Ross, M., Perkins, H., & Bodey, K. (2016). Academic motivation and information literacy self-
efficacy: The importance of a simple desire to know. Library and Information Science
Research, 38(1), 2–9. https://doi.org/10.1016/j.lisr.2016.01.002.
18. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 29
[53] Salomon, A., & Ben-David, K. Y. (2016). High-school students’ perceptions of the effects of
non-academic usage of ICT on their academic achievements. Computers in Human
Behavior, 64, 143–151. https://doi.org/https://doi.org/10.1016/j.chb.2016.06.024.
[54] Schmitt, N., Keeney, J., Oswald, F. L., Pleskac, T. J., Billington, A. Q., Sinha, R., & Zorzie,
M. (2009). Prediction of 4-Year College Student Performance Using Cognitive and
Noncognitive Predictors and the Impact on Demographic Status of Admitted Students.
Journal of Applied Psychology, 94(6), 1479–1497. https://doi.org/10.1037/a0016810.
[55] Schwartz, T. D. B. (2017). The Effect of Student-Led Conferencing at School and at Home
on Goal-Setting , Goal-Fulfillment , Effort , Achievement , Intrinsic Motivation , and
Satisfaction for Montessori Lower Elementary 3rd Year Students. The St. Catherine
University. Retrieved from https://sophia.stkate.edu/maed/224.
[56] Stajkovic, A. D., Bandura, A., Locke, E. A., Lee, D., & Sergent, K. (2018). Test of three
conceptual models of influence of the big five personality traits and self-efficacy on academic
performance: A meta-analytic path-analysis. Personality and Individual Differences,
120(February 2017), 238–245. https://doi.org/10.1016/j.paid.2017.08.014.
[57] Sudha, S., & Kavitha, E. S. (2016). The Effect of Social Networking on Students ’ Academic
Performance : the Perspective of Faculty Members of Periyar. Library Philophy and Practice,
14(55). Retrieved from
http://digitalcommons.unl.edu/libphilprac%0Ahttp://digitalcommons.unl.edu/libphilprac/1455.
[58] Suprayogi, M. N., & Valcke, M. (2014). Academic Efficacy, Goal Orientation, and Academic
Achievement; A Comparative Study between Belgium and Indonesian Students.
[59] Talsma, K., Schüz, B., Schwarzer, R., & Norris, K. (2018). I believe, therefore I achieve (and
vice versa): A meta-analytic cross-lagged panel analysis of self-efficacy and academic
performance. Learning and Individual Differences, 61(October 2017), 136–150.
https://doi.org/10.1016/j.lindif.2017.11.015.
[60] Trolian, T. L., Jach, E. A., Hanson, J. M., & Pascarella, E. T. (2017). Influencing Academic
Motivation : The Effects of Student – Faculty Interaction Influencing Academic Motivation :
The Effects of Student – Faculty Interaction. Journal of College Student Development, 57(7),
810–826.
[61] Tuen, W., Leung, V., Yee, T., Pan, W., Wu, C., Lung, S. C., & Spengler, J. D. (2019).
Landscape and Urban Planning How is environmental greenness related to students ’
academic performance in English and Mathematics ? Landscape and Urban Planning,
181(1), 118–124. https://doi.org/10.1016/j.landurbplan.2018.09.021.
[62] Vaghela, C., Bhatt, N., & Patel, P. U. (2015). A Survey on Various Classification Techniques
for Clinical Decision Support System. International Journal of Computer Applications,
116(23), 975–8887.
[63] Wakefield, K. (2013). A guide to machine learning algorithms and their applications.
Retrieved August 1, 2018, from
https://www.sas.com/en_gb/insights/articles/analytics/machine-learning-algorithms.html.
[64] Wentworth, D. K., & Middleton, J. H. (2014). Technology use and academic performance.
Computers and Education, 78(September 2014), 306–311.
https://doi.org/10.1016/j.compedu.2014.06.012.
[65] Wilson, K., & Narayan, A. (2016). Relationships among individual task self-efficacy, self-
regulated learning strategy use and academic performance in a computer-supported
collaborative learning environment. Educational Psychology, 36(2), 236–253.
19. Isaac Kofi Nti & Juanita Ahia Quarcoo
International Journal of Artificial Intelligence and Expert Systems (IJAE), Volume (8) : Issue (2): 2019 30
https://doi.org/10.1080/01443410.2014.926312.
[66] Yadav, S. K., & Pal, S. (2012). Data Mining : A Prediction for Performance Improvement of
Engineering Students using Classification. World of Computer Science and Information
Technology Journal WCSIT, 2(2), 51–56. https://doi.org/10.1142/9789812771728_0012.
[67] Yeboah, Y. K. (2014). Investigating the Low Performance of Students’ English in the Basic
Education Certificate Examination in the Sunyani Municipality. UNIVERSITY OF GHANA,
LEGON. https://doi.org/10.1038/253004b0.
[68] Yusif, H. M., Yussof, I., & Noor, A. H. S. M. (2011). Determinants of Students Academic
Perform- Ance in Senior High Schools : a Binary Logit Approach, 31(3), 107–117.
https://doi.org/10.4314/just.v31i3.12.
[69] Zimmerman, B. J., & Kitsantas, A. (2014). Comparing students’ self-discipline and self-
regulation measures and their prediction of academic achievement. Contemporary
Educational Psychology, 39(2), 145–155. https://doi.org/10.1016/j.cedpsych.2014.03.004.