National Research Repository
The National Research Fund facilitates research for the advancement of Science, Technology and Innovation. One of our core functions is to compile and maintain a national database of research and innovation projects funded by the Fund and other agencies as per the STI Act of 2013.
Browse Collections
Select a community to browse its collections.
Registry of Repositories in Kenya (RoRiK)
NRF is developing a Registry of Research Repositories in Kenya (RoRiK) in an effort to promote access to research data in the country.
Recent Submissions
Use of Intelligent Agents in Collaborative MLearning: Case of Facilitating Group Learner Interactions
(I.J. Modern Education and Computer Science, 2017-10-08) Stephen T. Njenga Murang’a, Robert O. Oboko and Elijah I. Omwenga Elizaphan M. Maina
Intelligent agents have been used in
collaborative learning. However, they are rarely used to
facilitate group interactions in collaborative m-learning
environments. In view of this, the paper discusses the use
of intelligent agents in facilitating collaborative learning
in mobile learning environments. The paper demonstrates
how to design intelligent agents and integrate them in
collaborative mobile learning environments to allow
group learners to improve their levels of group
knowledge construction. The design was implemented in
a collaborative mobile learning system running on
Modular Object-Oriented Dynamic Learning
Environment (Moodle) platform. The application was
used in some experiments to investigate the effects of
those facilitated interactions on the level of group
knowledge construction. The results showed improved
levels of group knowledge construction in instances
where the facilitations were enabled compared to where
they were disabled. The paper concludes that the use of
intelligent agents in facilitating learner group interactions
in collaborative mobile learning environments improves
the levels of group knowledge construction. For future
work, the use of intelligent agents can be tested in other
areas of group interactions to enhance group learning
Evaluation of Intelligent Grouping Based on Learners’ Collaboration Competence Level in Online Collaborative Learning Environment
(Athabasca University Press (AU Press), 2016-02) Maina Elizaphan Muuro, Robert Obwocha Oboko and Waiganjo Peter Wagacha
In this paper we explore the impact of an intelligent grouping algorithm based
on learners’ collaborative competency when compared with (a) instructor
based Grade Point Average (GPA) method level and (b) random method, on
group outcomes and group collaboration problems in an online collaborative
learning environment. An intelligent grouping algorithm has been added in a
Learning Management System (LMS) which is capable of forming
heterogeneous groups based on learners’ collaborative competency level. True
experiment design methodology was deployed to examine whether there is
any association between group formation method and group scores, learning
experiences and group problems. From the findings, all groups had almost
similar mean scores in all group tests, and shared many similar group
collaboration problems and learning experiences. However, with the
understanding that GPA group formation method involves the instructor, may
not be dynamic, and the random method does not guarantee heterogeneity
based on learner’s collaboration competence level, instructors are more likely
to adopt our intelligent grouping method as the findings show that it has
similar results. Furthermore, it provides an added advantage in supporting
group formation due to its guarantee on heterogeneity, dynamism, and less
instructor involvement.
Using Machine Learning Techniques to Support Group Formation in an Online Collaborative Learning Environment
(2017-03) Elizaphan Maina, Robert Oboko, and Peter Waiganjo Wagacha
The current Learning Management Systems
used in e-learning lack intelligent mechanisms which can
be used by an instructor to group learners during an
online group task based on the learners‟ collaboration
competence level. In this paper, we discuss a novel
approach for grouping students in an online learning
group task based on individual learners‟ collaboration
competence level. We demonstrate how it can be applied
in a Learning Management System such as Moodle using
forum data. To create the collaboration competence levels,
two machine learning algorithms for clustering namely
Skmeans and Expectation Maximization (EM) were
applied to cluster data and generate clusters based on
learner‟s collaboration competence. We develop an
intelligent grouping algorithm which utilizes these
machine learning generated clusters to form
heterogeneous groups. These groups are automatically
made available to the instructor who can proceed to
assign them to group tasks. This approach has the
advantage of dynamically changing the group
membership based on learners‟ collaboration competence
level.
Using Educational Data Mining Techniques to Identify Profiles in Self-Regulated Learning: An Empirical Evaluation
(Athabasca University Press (AU Press), 2022-02) Eric Araka, Robert Oboko, Elizaphan Maina and Rhoda Gitonga
With the increased emphasis on the benefits of self-regulated learning (SRL), it
is important to make use of the huge amounts of educational data generated
from online learning environments to identify the appropriate educational
data mining (EDM) techniques that can help explore and understand online
learners’ behavioral patterns. Understanding learner behaviors helps us gain
more insights into the right types of interventions that can be offered to online
learners who currently receive limited support from instructors as compared
to their counterparts in traditional face-to-face classrooms. In view of this, our
study first identified an optimal EDM algorithm by empirically evaluating the
potential of three clustering algorithms (expectation-maximization,
agglomerative hierarchical, and k-means) to identify SRL profiles using trace
data collected from the Open University of the UK. Results revealed that
agglomerative hierarchical was the optimal algorithm, with four clusters. From
the four clusters, four SRL profiles were identified: poor self-regulators,
intermediate self-regulators, good self-regulators, and exemplary
self-regulators. Second, through correlation analysis, our study established that
there is a significant relationship between the SRL profiles and students’ final
results. Based on our findings, we recommend agglomerative hierarchical as
the optimal algorithm to identify SRL profiles in online learning environments.
Furthermore, these profiles could provide insights on how to design a learning
management system which could promote SRL, based on learner behaviors.
Using Machine Learning Algorithms to Predict Students’ Performance and Improve Learning Outcome: A Literature Based Review
(Stratford Peer Reviewed Journals and Book Publishing, 2020-03) Francis Ofori, Dr. Elizaphan Maina and Dr. Rhoda Gitonga
The application of machine learning techniques in predicting students’ performance, based on
their background and their in-term performance has proved to be a helpful tool for foreseeing
poor and good performances in various levels of education. Early prediction of students’
performance is useful in taking early action of improving learning outcome. The prediction of
the student's academic performance is important as it helps increase graduation rates by
appropriately guiding students, guiding changes in university academic policies, informing
instructional practices, examining efficiency and effectiveness of learning, providing meaningful
feedback for teachers and learners and modifying learning environments. A high prediction
accuracy of the students’ performance is helpful to identify the low performance students at the
beginning of the learning process. However, to achieve these objectives, large volume of student
data must be analyzed and predicted using various machine learning models. Moreover, it is not
clear which model is best in predicting performance and which machine learning model is
appropriate in improving learning in among students. The paper through intensive literature
review attempts to identify best machine learning model in predicting student performance and
appropriate machine learning model in improving learning. The empirical review indicated
contentious results on machine learning model that best predicts students’ performance.
Moreover, it is not clear among the various machine learning algorithms which one derives the
best approach in predicting students’ performance while improving learning outcome. The
varying prediction level by various machine learning models may be as a result of differences in
socioeconomic. It may also be important to note that student’s academic performances are
affected by many factors, like socioeconomic factors of students like family income, parental level of education and employment status of students or parents but are not considered when
testing the accuracy of various machine learning models in predicting students’ performance.
Moreover, the various machine learning models did not identify the most appropriate machine
learning model in improving students’ outcome. Most models focused largely in predicting
students’ performance without considering mechanisms to improve learning outcome of
students. As a result, it is important to test the accuracy of various machine learning models that
best predicts students’ performance and the one that is most appropriate in improve learning
outcome while considering socio economic and demographic factors of the students. The study
makes a conclusion that predicting students’ performance is of the highest priority for any
learning institution across the globe. Using various machine learning methods to accurately
predict student’s performance would be highly required. It is important to accurately rank
machine models based on their prediction capabilities in predicting students’ performance and in
improving learning outcome.





