data mining techniques are widely used in the educational system. They help the
institute in improving the performance of student and retrieving information
for many useful purposes. This review discusses a journal paper on the Evolutionary
algorithm for generating personalized system in educational data mining. We discourse
the methodology and implementation of the system in the study in detail. Further
we present the critical review and limitation of the study. we also deliberate the
suitable solution of the critics in the end.
Educational data mining(EDM)
is a vast research field related to machine learning, data mining and statistical
sciences. EDM help to retrieve information from tons of data in advance and
intelligent educational systems. The EDM techniques extract meaningful
information from large databases based on the need of tutor. They help in improvement
of student’s activities and learning ability. The raw data can be all library
books or students’ past results. The EDM techniques assist the student, tutor
or administration user to get the suitable material and process it for further
use. Many systems like predicating student’s performance, failure and final
grade, automated quiz systems and generating students group use EDM techniques
to improve their performance and achieve their goals.
Evolutionary algorithm is
a genetic algorithm in artificial intelligence which work well in predication and
evolution of results. Many researches have been using evolutionary algorithm in
data mining to achieve maximum productivity. Evolutionary algorithms are
actually used in biological prediction systems but a number of researchers are implementing
in educational data mining. Many researches concluded they work better from greedy
approach in data mining.
The review presents a brief
review on the use of evolutionary algorithm in educational data mining. Different
types of evolutionary algorithm are genetic programming, differential algorithm
and genetic algorithm. The review answers the following research questions:
Does the research article define what It claims
in the abstract?
Are the techniques and methodology used efficient
Are the results properly defined and concluded?
The Study presents are
brief detail of the educational data mining and where they are used in real
world. The data mining techniques are applied to retrieve information from
large databases of education institutes and process for the improvement of
tutor and student performance. The real-world applications of educational data
mining are predicting student performance and grades through the past results of
the student. Improvement of domain and student models, research into students
and learning material, predicting in the learning tools are some areas in
educational environment. These tools can be used tutors, students, course
author, institute and administration. Further the study defines the as that can
be assigned to educational systems that use educational data mining. Some tasks
Getting feedback for tutor.
Recommending suitable course to the
Making students’ group.
Predicting the performance of student
and regression techniques are implemented in these system for data mining. The
major task of these systems is help the instructor and student to develop their
courseware. The Evolutionary algorithm used in EDM have helped to improve its
working. The study shows that it has proved to be better than other
classification techniques. The study further presents a summary of the survey.
The educational systems depend on four parts:
the main task
The goal of the study was
to present an efficient evolutionary algorithm which is a solution to EDM problems.
It categorizes the EDM related journal papers in a table. It consists of the
courseware construction and maintenance problem as the main goal in the study. The
research also shows that the evolutionary algorithm has tend to work better
than other data mining techniques in EDM. They choose course authors as their
main focus in the study as the recommendation for them is an important aspect.
Table I shows 12 journal
papers that used evolutionary algorithm for their system implementation and
information extraction. The table is divided into four columns as the educational
system parts defined in section 2. Furthermore, the fig 1 is used to sketch the
number of publication related to the tasks mentioned in the table. The graph shows
that most of the journal paper used evolutionary algorithm for getting the feedback
for the tutor. On the other hand, from table we can easily conclude that
majority papers used genetic algorithm for their task.
The study than deliberate
the techniques of courseware construction and a literature survey on this
issue. It introduces many systems such as forming web tutor tree and cluster of
students for predicting their performances through the educational history. Also,
many articles for recommendation of the course to students are reviewed in the
study. many articles related to improvement if learning style are also reviewed
that used document index graph, association rule mining and other learning
styles. The author presents the benefits of using these techniques which can
help in the improvement of the EDM systems.
The study used KEEL
software for the generation of their results. The implementation of the genetic
algorithm is used to find the students performance. It shows the average of
support value is 0.36 whereas the confidence value is 1. Which concludes that
if the students lie between the given value than he is a sensitive learner. The
sample courseware construction can be implemented to get better results for students’
The study presents a
brief discussion of the evolutionary algorithm in educational data mining. The real-world
applications, different types of users and their tasks, three types of
evolutionary algorithm and the four parts of educational systems and their
problems are defined in detail in the study. It also presents a brief
literature survey on the key area. The study also categorized the journal
papers in table and show the number of publications in a graph.
The table shows the journal
articles on only genetic algorithm and programming while it claims to have a survey
on Evolutionary algorithm and no other type of EA. It means that the study is
not conducted overall on the evolutionary algorithms. While many previous
research articles show that differential algorithms prove to be the best in the
EDM systems. Further it can be clearly seen from the table that no journal has
been selected from the clustering techniques. Also, the study reviews only twelve
journal papers for this objective.
The paper also not
discusses the table and figure in detail and what they conclude from them. The
study doesn’t deliberate the main goal line of using these presentation
The study states all the evolutionary
algorithm in detail and defines all its factors. We can see that no limitations
and drawbacks of the algorithms are defined. The journal papers are only viewed
and the focus was only on their data mining techniques. while their drawbacks
and solution can be discussed in the paper. The definitions are not enough for
a survey paper.
The paper also defines no
selection criteria and research questions for the journal article. The paper
just defines the techniques used in the systems of different journal papers.
The author claims the
objective of their study to find an efficient evolutionary algorithm for the
EDM problem in section 4. While no where else they mention or conclude this
objective and not discuss the best algorithm in this perspective.