Mineração de Dados Educacionais: Tendências e Métodos

Prévia do material em texto

A Review on Educational Data Mining and Research Trends 
EDUCATIONAL DATA MINING (EDM)
Educational data mining is concerned with developing, researching, and applying computerized methods to
detect patterns in large collections of educational data that would otherwise be hard or impossible to analyze
due to the enormous volume of data within which they exist [1]. In recent years there is an exponential
growth in education sector which leads to growing of education data so analyzing of education data become
important aspect. 
EDM analyze data generated by any type of information system supporting learning or education (in schools,
colleges, universities, and other academic or professional learning institutions providing traditional and
modern forms and methods of teaching, as well as informal learning). These data are not restricted to
interactions of individual students with an educational system (e.g., navigation behavior, input in quizzes and
interactive exercises) but might also include data from collaborating students (e.g., text chat), administrative
data (e.g., school, school district, teacher), demographic data (e.g., gender, age, school grades), student
affectivity (e.g., motivation, emotional states), and so forth. These data have typical characteristics such as
multiple levels of hierarchy (subject, assignment, question levels), context (a particular student in a particular
class encountering a particular question at a particular time on a particular date), fine grained (recording of
data at different resolutions to facilitate different analyses, e.g., recording data every 20 second), and
longitudinal (much data recorded over many sessions for a long period of time, e.g., spanning semester and
year-long courses) [1].
EDM can be drawn as the combination of three main areas (Figure 1): computer science, education, and
statistics. The intersection of these three areas also forms other subareas closely related to EDM such as
computer-based education, DM and machine learning, and learning analytics (LA) [1].
Figure 1 - Main areas related to educational data mining
The main aim of EDM is to improve educational system and the objectives of EDM are student/student
behavior modeling, prediction of performance, increase reflections and awareness, prediction of drop outs
and retention, improving assessments and feedback services, recommendation of resources [2]. Educational
system involves different groups of users or participants. They describe information related to education
according to their own mission, vision and objectives. Higher education can be classified into different
Users/Stakeholders as follows [3].
1. Learners / Students 
To personalize e-learning, recommend activities to learners, provide learning tasks that could further
improve their learning, to suggest interesting learning experiences to the students.
2. Educators / Teachers / Instructors 
To detect which students require support, to predict student performance, to classify learners into groups,
to find a learner’s regular as well as irregular patterns, to find the most frequently made mistakes, to
analyze student’s learning and behavior, to detect which students require support.
3. Course Developers / Educational Researchers 
To compare data mining techniques in order to be able to recommend the most useful one for each task,
to develop specific data mining tools for educational purposes etc.
4. System Administrators / Network Administrator 
To utilize available resources more effectively, to enhance educational program offers and determine the
effectiveness of the distance learning approach.
EDUCATIONAL KNOWLEDGE DISCOVERY PROCESS
The process of applying data mining to educational systems can be seen very similar to the general
knowledge discovery and data mining (KDD) process (Figure 2) [1].
Figure 2 - Educational knowledge discovery and data mining process
EDUCATIONAL DATA MINING METHODS
There are a number of popular methods within EDM. Some of them are widely acknowledged to be
universal across types of data mining, such as prediction, classification, clustering, outlier detecting,
relationship mining, Social Network Analysis (SNA), process mining, statistics and text mining. And others
have particular prominence within EDM, such as the distillation of data for human judgment, discovery with
models and knowledge tracing (KT).
Classification
It is a two way technique (training and testing) which maps data into a predefined class. This technique is
useful for success analysis with low, medium, high risk students used in [4], student monitoring systems [5],
predicting student performance, misuse detection used in [6] etc.
Clustering
It is a technique to group similar data into clusters in a way that groups are not predefined. This technique is
useful to distinguish learner with their preference in using interactive multimedia system used in [7],
Students comprehensive character analysis used in [8] and suitable for collaborative learning used in [9, 10].
Statistics
It is a technique to identify outlier fields, record using mean, mode etc. and hypothetical testing. This
technique is useful to improve the course management system & student response system [11].
Prediction
It is a technique which predicts a future state rather than a current state. This technique is useful to predict
success rate, drop out used in Dekker et al. [12, 13], and retention management used in [14] of students. 
Neural Network
It is a technique to improve the interpretability of the learned network by using extracted rules for learning
networks. This technique is useful to determine residency, ethnicity used in [15], to predict academic
performance used in [4], accuracy prediction in the branch selection used in [17] and explores learning
performance in a Teaching English as a Second Language (TESL based e-learning system [18].
Association Rule Mining
It is a technique to identify specific relationships among data. This technique is useful to identify students’
failure patterns [19], parameters related to the admission process, migration, contribution of alumni, student
assessment, co-relation between different group of students, to guide a search for a better fitting transfer
model of student learning etc. used in [20].
Web mining
It is a technique for mining web data. This technique is useful for building virtual community in
computational Intelligence used in [21], to determine misconception of learners used in [21] and to explore
cognitive sense.
 
Outlier Detection
The goal of outlier detection is to discover data points that are significantly different than the rest of data. An
outlier is a different observation (or measurement) that is usually larger or smaller than the other values in
data. In EDM, outlier detection can be used to detect students with learning difficulties, deviations in the
learner’s or educator’s actions or behaviors, and for detecting irregular learning processes [1].
Social Network Analysis (SNA)
The goal of SNA is to understand and measure the relationships between entities in networked information.
SNA views social relationships in terms of network theory consisting of nodes (representing individual
actors within the network) and connections or links (which represent relationships between the individuals,
such as friendship, kinship, organizational position, sexual relationships, etc.). In EDM, SNA can be used for
mining to interpret and analyze the structure and relations in collaborative tasks and interactions with
communication tools [1].
Process Mining
The goal of process mining is to extract process related knowledge from event logs recorded by an
information system to have a clear visual representation of the whole process. It consists of three subfields:
conformance checking, model discovery, and modelextension. In EDM, process mining can be used for
reflecting students’ behavior in terms of their examination traces consisting of a sequence of course, grade,
and timestamp triplets for each student [1].
Text Mining
The goal of text mining, also referred to as text data mining or text analytics, is to derive high-quality
information from text. Typical text mining tasks include text categorization, text clustering, concept/entity
extraction, production of granular taxonomies, sentiment analysis, document summarization, and entity
relation modeling. In EDM, text mining has been used to analyze the content of discussion boards, forums,
chats, Web pages, documents, and so forth [1].
Distillation of Data for Human Judgment
The goal is to represent data in intelligible ways using summarization, visualization and interactive interfaces
to highlight useful information and support decision-making. On the one hand, it is relatively easy to obtain
descriptive statistics from educational data to obtain global data characteristics and summaries and reports on
learner behavior. On the other hand, information visualization and graphic techniques help to see, explore,
and understand large amounts of educational data at once. In EDM, it also known as distillation for human
judgment13 and it has been used for helping educators to visualize and analyze the students’ course activities
and usage information [1].
Discovery with Models
The goal of discovering with models is to use a previously validated model of a phenomenon (using
prediction, clustering, or manual knowledge engineering) as a component in another analysis such as
prediction or relationship mining. It is particularly prominent in EDM and it supports the identification of
relationships between student behaviors and students’ characteristics or contextual variables, the analysis of
research questions across a wide variety of contexts, and the integration of psychometric modeling
frameworks into machine-learning models [1].
Knowledge Tracing
KT is a popular method for estimating student mastery of skills that has been used in effective cognitive tutor
systems. It uses both a cognitive model that maps a problem-solving item to the skills required, and logs of
students’ correct and incorrect answers as evidence of their knowledge on a particular skill. KT tracks
student knowledge over time and it is parameterized by four variables. There is an equivalent formulation of
KT as a Bayesian network [1].
EDUCATIONAL DATA MINING APPLICATIONS
Visualization of facts
Inserting a common term in a visual context is to guide the people to identify the significance of the data is
known as data visualization. According to user trends the reports were generated monthly or weekly
schedule. Using of materials, studying topics sequence, studying activity patterns and time schedules are
noted as usage summary. It is very easy to know about patterns and correlations in visualization software,
which are hidden in text-based data [23].
Predicting Student Performance
The Marks, knowledge and student performance are frequently predicted values in educational data mining.
To improve the learning and teaching procedure, the performance of students will be predicted to guide the
learners and educators in correct way. The percentage and grade are mostly used in educational data mining
by the researchers. This technique is used to combine the labeled items based upon the quantitative traits and
training sets which are gathered earlier in the process [5].
Enrollment Management
To structure the enrollment of the college to achieve the goals the enrollment management is used in higher
education. The data analysis is used in enrollment management for achieving desired results of the
management is the traditional way of educational data mining techniques. The educational institutions are
planned to perform set of activities to influence frequently over the students enrollments will lead to reduce
the drop-outs in higher education [24].
Grouping Students
The student groups are formed according to the personality and efficiency to improve the system. To
construct a learning system to support the group learning methodology will make the learning techniques are
more effective and easier for the students to develop themselves. Discover the student groups in related
learning which is based on huge sequences are performed by clustering algorithm [7].
Predicting Students Profiling
At the time of admission the information collected by the management from students will hold the details
like demographic, geographic and psychographic individual of the students. The best technique to identify
the different types of student’s individuality is Neural networking [9]. The prediction of student performance
are possible by using different techniques like Bayesian networks, decision trees and neural networks will
make the management to take appropriate decisions to improve the students performance in higher
education. The prediction about final grade and course completion are major things found in this student
profiling techniques to view the success rate of students [25]. 
Planning and scheduling
The Educational process like planning, course scheduling, resource allotment and going for new courses will
make idea for admissions and counseling. These are the important aspects for the management to make an
impact in the educational system. While planning the course activities the decision trees and link analysis are
used to find course completion rates and preferences. To find the course classifications in educational
training the clustering analysis, decision trees and back-propagation neural networks techniques are used to
improve the student level in higher education [23].
DATA MINING TOOLS
Nowadays, there is a group of tools that have been developed by a research community and data analysis
enthusiasts, they are offered free of charge using one of the existing open-source licenses. An open-source
development model usually means that the tool is a result of a community effort, not necessary supported by
a single institution but instead the result of contributions from an international and informal development
team. This development style offers a means of incorporating the diverse experiences. Data mining provides
many mining techniques to extract data from databases. Data mining tools predict future trends, behaviors,
allowing business to make proactive, knowledge driven decisions. The development and application of data
mining algorithms requires use of very powerful software tools. As the number of available tools continues
to grow the choice of most suitable tool becomes increasingly difficult [43]. This paper is trying to find out
tools which will helpful for the research community to mine educational data as per requirement. 
WEKA
Waikato Environment for Knowledge Analysis. Weka is a collection of machine learning algorithms for data
mining tasks. These algorithms can either be applied directly to a data set or can be called from your own
Java code. The Weka (pronounced Weh-Kuh) workbench contains a collection of several tools for
visualization and algorithms for analytics of data and predictive modeling, together with graphical user
interfaces for easy access to this functionality [26].
KEEL
Knowledge Extraction based on Evolutionary Learning is an application package of machine learning
software tools. KEEL is designed for providing solution to data mining problems and assessing evolutionary
algorithms. It has a collection of libraries for preprocessing and post-processing techniques for data
manipulating, soft-computing methods in knowledge of extracting and learning, and providing scientific and
research methods [26].
R
Revolution is a free software programming language and software environment for statisticalcomputing and
graphics. The R language is widely used among statisticians and data miners for developing statistical
software and data analysis. One of R's strengths is the ease with which well-designed publication-quality
plots can be produced, including mathematical symbols and formulae where needed [26].
KNIME
Konstanz Information Miner, is an open source data analytics, reporting and integration platform. It has been
used in pharmaceutical research, but is also used in other areas like CRM customer data analysis, business
intelligence and financial data analysis. It is based on the Eclipse platform and, through its modular API, and
is easily extensible. Custom nodes and types can be implemented in KNIME within hours thus extending
KNIME to comprehend and provide first tier support for highly domain-specific data format [26].
RAPIDMINER
Rapidminer is a software platform developed by the company of the same name that provides an integrated
environment for machine learning, data mining, text mining, predictive analytics and business analytics. It is
used for business and industrial applications as well as for research, education, training, rapid prototyping,
and application development and supports all steps of the data mining process. Rapid Miner uses a
client/server model with the server offered as Software as a Service or on cloud infrastructures [26].
ORANGE
Orange is a component-based data mining and machine learning software suite, featuring a visual
programming frontend for explorative data analysis and visualization, and Python bindings and libraries for
scripting. It includes a set of components for data preprocessing, feature scoring and filtering, modeling,
model evaluation, and exploration techniques. It is implemented in C++ and Python. Its graphical user
interface builds upon the cross-platform framework [26].
TRENDS OF EDM RESEARCH DURING THE PERIOD 2005-2017
A survey on EDM for the period 2005 to 2017 is listed in table-3. The leverage points of this survey are the
trends of Reference, Data Mining Techniques, Algorithms, Objectives, Tools, Dataset used and respective
Educational outcomes. 
Table 1: Literature survey on EDM trends during the period 2005-2017
Reference
And Year 
Data Mining
Techniques
Algorithms Objectives Tools Dataset Educational Outcomes
35 (2005) Clustering TwoStep Discover the
navigational behavior
of the students of an
e-learning virtual
environment
A subset of 111
students taking a
degree in
Computer
Science
Determine whether such
navigational patterns are
related to the academic
performance achieved by
the students or not, and
which behaviors can be
identified as more
successful.
9 (2009) Clustering
Sequential Apriori (GSP
Mining)
Discover patterns of
online collaborative
learning data
Interesting patterns
characterizing the work of
stronger and weaker
students
27 (2012) Association
rules
Apriori Discover the 
knowledge for 
analysis student 
motivation 
Weka Student’s data
from the ITC
and Learning
Course 2010-
2011.
Model the student behavior
outcomes and the model for
the ongoing improvement
of e-Learning course.Classification Decision
tree(ID3,J48)
28 (2017) Association 
rules and 
Clustering 
with 
collaborative 
Filtering 
Find the students
visiting patterns.
Web server logs Construct a browsing
behavioral model that is
helpful in supporting E-
learning resources
29 (2013) Association
rules
Apriori Predicting students’
performance
Weka The dataset of
60 students from
MCA course 
Student’s performance
level can be Improved in
university result by
identifying students who
are poor unit Test,
Attendance, Assignment
and graduation and giving
them additional guidance to
improve the university
result.
30 (2011) Classification Decision Tree
(ID3)
Predicting students’
the performance
The data set of
50 students
-course MCA
from session
2007 - 2010.
helps earlier in identifying
the dropouts and students
who need special attention
and allow the teacher to
provide appropriate
advising/counseling
31 (2017) Clustering K-Means Recommendation of
courses to a learner
based on his/her
profile
Weka A dataset with
100 students
Predicting student’s
performance timely can
help them to improve their
learning process,
consequently improving
student academic
performance.
32 (2014) Usage Mining HITS Personalized
recommendation
based on users
browsing history
Server logs Better performance
improvement
Content
Mining
Lingo
Clustering 
33 (2016) Classification Decision Tree
(CART*,C4.5
,ID3,CHAID)
Predicting the
students’
performance based
on related personal
and social factors.
Weka,
Rapid
Miner
Dataset by
survey – 270
records
It was slightly found that
the student’s performance
is not totally dependent on
their academic efforts
34 (2014) Association SDAR Predicting students’
behavior and
performance as well
as teachers’
performance
Weka 3RD year B. Tec
Engineering
students
Improve their standards and
reputations by introducing
the new courses or
branches. As a result the
quality of education can be
improved.
Clustering K-Means
Classification RBC
Classification
(learner point
of view)
Naïve
bayes,ID3,CA
RT and LAD
36 (2014) Clustering K-Means Students interaction
with an e-learning
Weka,
R
A group of 412
students' access
The majority of the student
population are not self-
system through
instructor-led non-
graded and graded
courses
behavior motivated to do self-
learning.(Self-Directed
Learning)
37 (2014) Clustering Expectation
Maximization
and K-Means
The clustering of
elementary school
slow learner students
behavior for the
discovery of optimal
learning patterns
Weka Dataset of
elementary
school student
Enhance student learning
capacities
38 (2010) Clustering K-Means Analysis of learners’
behavior
Weka,
Statist
ica
528 students in
15 distance
learning courses
Find out the factors that
influence final evaluations
of students’
39 (2012) Clustering
Association
K-Means
Aprioir
FPGrowth
Identify
the navigation
patterns of users
online.
Weka Server logs of
the Virtual
Campus of Open
University of
Catalonia.
Assist web designers to
achieve optimized
site structuring and
facilitate users’ activity
online.
40 (2015) Clustering Expectation
Maximization
(EM)
Discover students’
navigation paths or
trails in Moodle
Weka Dataset from 84
undergraduate
Psychology
students who
followed an
online course
obtain more specific and
accurate trails.
41 (2016) Feature
Selection
Classification
Correlation
based feature
Subset
Attribute
evaluation
and Gain-
Ratio
Attribute
evaluation
Naïve Bayes
Show that
the feature selection
techniques can
improve the accuracy
and efficiency of the
classification
algorithm 
Weka Dataset was a
collection of
first year
students
information
contains 5
undergraduate
degree courses
collected period
of 2013-2014.
Improve the student
performance.
42 (2016) Classification Decision Tree
Fuzzy
Generic 
Develop student's
academic
performance
prediction model
Dataset from the
Bachelor and
Master degree
students in
Computer
Science and
Electronics and
Communication
streams
A decision to take care
about risk students and
mental satisfaction for safe
students.
43 (2015) Classification Decision Tree
Naïve Bayes
Rule Based
Predicting students’
academic
performance
Weka The data were
collected from 8
year period
intakes
from July
2006/2007 until
July 2013/2014
Take early actions to help
and assist the poor and
average category
students to improve their
results.
44 (2017) Clustering
Classification
Enhanced K-
Means
Support
Vector
Machine
Student performance
prediction
Dataset of 650
UG students
enrolled during
the year 2015,
Number of
Attributes: 52
The students to perform
poor in academic activitiesand it even leads to course
drop outs.
DISCUSSION
This literature survey focused on research trends on EDM since the year 2005 to 2017 and found that
maximum research focuses were on academic objectives. The other issues are:
Challenges of EDM
 Educational data is incremental in nature
Due to the exponential growth of data, the maintaining the data warehouse is difficult. To monitor the
operational data sources, infer the student interest, intentions and its impact in a particular institution is the
main issue [44]. 
 Lack of Data Interoperability
Scalable Data management has become critical considering wide range of storage locations, data platform
heterogeneity and a plethora of social networking sites [44].
 Possibility of Uncertainty
Due to the presence of uncertain errors, no model can predict hundred percent accurate results in terms of
student modeling or overall academic planning [44].
 Research Expertise Relation between Student-Teacher
In most of the higher Educational institutions (e.g. Engineering Institutions) final year students have a
compulsory project work which is a research work based on their area of interest. Generally Supervisors are
assigned as per availability and area of expertise in the respective department. But still it is not possible to
assign all the students –supervisor with similar area of interest hence the result of the project is nots
applicable to real scenarios. There is need to find the relation between areas of interest, students' interest,
applicability of the project/research and mining cross faculty interest. It will be beneficial to introduce using
Association Mining to optimize this issue [44].
Limitations of this research
This literature survey work studied around 20 EDM research papers from various journals/conferences of
repute in the context of Reference, Data Mining Techniques, Algorithms, Objectives, Tools, Dataset used and
respective Educational outcomes. Since it is not possible to cover all the research papers, from all corners
and explores each and every contexts.
REFERENCES
[1] C. Romero and S. Ventura, "Data mining in education," WIREs Data Mining and Knowledge Discovery, vol. 3, pp.
12-27, 2012. 
[2] C. Papamitsiou and A. A. Economides, "Learning Analytics and Educational Data Mining in Practice: A Systematic
Literature Review of Empirical Evidence," Educational Technology & Society, vol. 17, no. 4, pp. 49-64, 2014. 
[3] H. Kumar and N. Modi, "A Survey on Educational Data Mining and Research Trends," KAAV INTERNATIONAL
JOURNAL OF SCIENCE, vol. 4, no. 3, pp. 84-89, 2017. 
[4] Vandamme, J.P. et al. (2007), “Predicting academic performance by Data Mining methods”, Taylor and Francis
group Journal Education Economics.Vol.15, No.4, pp.405-419.
[5] Luan, J., (2002), “Data mining, knowledge management in higher education, potential applications”, In Workshop
associate of institutional research international conference. Toronto, pp.1- 18.
[6] Baker, R.S, Corbett, A.T., Koedinger, K.R (2004) , “Detecting Student Misuse of Intelligent Tutoring Systems” in
Proc. Lecture Notes in Computer Science,Vol.3220,531-540.
[7] Chrysostomu K. el al. (2009), “Investigation of users’ preference in interactive multimedia learning systems: a data
mining approach”,Taylor and Francis online journal Interactive learning environments. Vol. 17, No. 2.
[8] Zhang Y.et al. (2010), “Using data mining to improve student retention in HE: a case study”, in Proc.12th Int. Conf.
on Enterprise Information Systems, Volume 1: Databases and Information Systems Integration.Portugal, pp.190-197.
[9] Perera,D. et al.(2009), “Clustering and sequential pattern mining of online collaborative learning data”, IEEE
Transactions on Knowledge and Data Engineering,Vol.21, No.6,pp.759-772.
[10] Baker, R.S.J.D.,and Yacef, K.(2009), “The state of Educational Data Mining in 2009:A review and future vision”,
Journal of Educational Data Mining, Vol.1,No. 1,pp.3-17.
[11] Campbell, J.P., and Oblinger, D.G. (2007, Oct.). Academic Analytics. EDUCAUSE, Washington, D.C. [Online].
Available: http://net.educause.edu/ir/library/pdf/pub6101.pdf,2007.
http://net.educause.edu/ir/library/pdf/pub6101.pdf,2007
[12] Dekker, G., Pechenizkiy, M., and Vleeshouwers J. (2009), “Predicting students drop out: A case study”, In
Proceedings of the 2nd International Conference on Educational Data Mining, pp.41-50.
[13] Zhang Y.et al. (2010), “Using data mining to improve student retention in HE: a case study”, in Proc.12th Int .
Conf. on Enterprise Information Systems, Volume 1: Databases and Information Systems Integration.Portugal, pp.190-
197.
[14] Lin, S.H. (2012), “Data Mining for student retention management” ACM journal of Computing Sciences in
CollegesI. Vol.27, No.4, pp. 92-99.
[15] Yu et al. (2010), “A data mining approach for identifying predictors of student retention from sophomore to junior
year”, Journal of Data Science.Vol.8, pp.307-325.
[17] Dutta Borah, M., Jindal, R., Gupta, D.,Deka,G.C (2011), “Application of knowledge based decision technique to
Predict student’s enrolment decision. In Proc. Int. Conf. on Recent Trends in Information Systems, India: IEEE, pp.180-
184, DOI: 10.1109/ReTIS.2011.6146864.
[18] Wang and Liao. (2011), “Data Mining for adaptive learning in a TESL based e-learning system”, in Elsevier
journal Expert systems with applications, Vol.38, No.6, pp.6480-6485.
[19] Oladipupo, O.O.,Oyelade,O.J.(2009), “Knowledge Discovery from Students’ Result Repository: Association Rule
Mining Approach”, International Journal of Computer Science & Security,Vol.4,No.2,pp.199-207.
[20] Freyberger,J., Heffernan, N., Ruiz, C.(2004), “Using association rules to guide a search for best fitting transfer
models of student learning”, Workshop on Analyzing Student-Tutor Interactions Logs to Improve Educational Outcomes
at ITS Conference.
[21] Zurada, J.M.et al.(2009), “Building Virtual Community in Computational Intelligence and Machine Learning”,
IEEE Computational Intelligence Mazazine.pp.43-54,.DOI: 10.1109 / MCI. 2008. 9309 86.
[22] Lee, G.,and Chen, Y.C.(2012), “Protecting sensitive knowledge in association pattern mining”, John Wiley & Sons,
Inc .2, pp.60-68.,DOI:10.1002/widm.50.
[23] Monika Goyal and Rajan Vohra - “Applications of Data Mining in Higher Education” - IJCSI International
Journal of Computer Science Issues, Vol. 9, Issue 2, No 1, March 2012.
[24] U. K. Pandey and S. Pal - “A Data mining view on class room teaching language”, International Journal of
Computer Science Issue, Vol. 8, Issue 2, pp. 277-282, ISSN:1694- 0814,2011.
[25] Dr. P. Nithya, B. Umamaheswari, A. Umadevi – “A Survey on Educational Data Mining in Field of Education” -
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), Volume 5 Issue 1,
January 2016.
[26] K. Rangra and K. Bansal, "Comparative Study of Data Mining Tools", International Journal of Advanced
Research in Computer Science and Software Engineering, vol. 4, no. 6, pp. 216-223, 2014.
[27] K. Kularbphettong and C. Tongsiri, "Mining Educational Data to Analyze the Student Motivation Behavior",
World Academy of Science, Engineering and Technology International Journal of Information and Communication
Engineering, vol. 6, no. 8, pp. 1032-1036, 2012.
[28] Sunil and M. Doja2, "Data Mining Techniques to Discover Students Visiting Patterns in E-learning Resources",
International Journal of Computer Science and Mobile Computing, vol. 6, no. 6, pp. 363 – 368, 2017.
[29] S. Borkar and K. Rajeswari, "Predicting Students Academic Performance Using Education Data Mining",
International Journal of Computer Science and Mobile Computing, vol. 2, no. 7, pp. 273 – 279, 2013.
[30] B. Kumar and S. Pal, "Mining Educational Data to Analyze Students Performance", International Journal of
Advanced Computer Science and Applications, vol. 2, no. 6, pp. 63-69, 2011.
[31] B. Rawatand S. Dwivedi, "An Architecture for Recommendation of Courses in E-learning System", I.J.
Information Technology and Computer Science, vol. 4, pp. 39-47, 2017.
[32] M. Chakurkar and P. Adiga, "A Web Mining Approach for Personalized E-Learning System", International Journal
of Advanced Computer Science and Applications, vol. 5, no. 3, pp. 51-56, 2014.
[33] A. Abu, "Educational Data Mining & Students’ Performance Prediction", International Journal of Advanced
Computer Science and Applications, vol. 7, no. 5, pp. 212-220, 2016.
[34] "Educational Data Mining and its role in Educational Field", International Journal of Computer Science and
Information Technologies, vol. 5, no. 2, pp. 2458-2461, 2014.
[35] J. M. Carbo, E. Mor and J. Minguillon, "User navigational behavior in e-learning virtual environments," The 2005
IEEE/WIC/ACM International Conference on Web Intelligence (WI'05), 2005, pp. 243-249.doi: 10.1109/WI.2005.155.
[36] I. P. Ratnapala, R. G. Ragel and S. Deegalla, "Students behavioural analysis in an online learning environment
using data mining," 7th International Conference on Information and Automation for Sustainability, Colombo, 2014,
pp.1-7, doi: 10.1109/ICIAFS.2014.7069609.
[37] T. Z. and A. M.Mahmoud, "Clustering of Slow Learners Behavior for Discovery of Optimal Patterns of Learning",
International Journal of Advanced Computer Science and Applications, vol. 5, no. 11, pp. 102-108, 2014.
[38] S. Preidys and L. Sakalauskas, "Analysis of students’ study activities in virtual learning environments using data
mining methods", Technological and Economic Development of Economy, vol. 16, no. 1, pp. 94-108, 2010.
[39] F. Xhafa, A. L. Martinez, S. Caballé, V. Kolici and L. Barolli, "Mining Navigation Patterns in a Virtual
Campus,"2012 Third International Conference on Emerging Intelligent Data and Web Technologies, Bucharest, 2012,
pp.181-189, doi: 10.1109/EIDWT.2012.65.
[40] A. Bogarín, C. Romero and R. Cerezo, "Discovering students’ navigation paths in Moodle", in Proceedings of the
8th International Conference on Educational Data Mining, 2015.
[41] C. Anuradha and T. Velmurugan, "FEATURE SELECTION TECHNIQUES TO ANALYSE STUDENT
ACADAMIC PERFORMANCE USING NAÏVE BAYES CLASSIFIER", in The 3 rd International Conference on
Small & Medium Business 2016, Nikko Saigon Hotel, Hochiminh, Vietnam, 2016.
[42] H. Hamsa, S. Indiradevi and J. Kizhakkethottam, "Student Academic Performance Prediction Model Using
Decision Tree and Fuzzy Genetic Algorithm", Procedia Technology, vol. 25, pp. 326-332, 2016.
[43] K. Rangra and K. Bansal, "Comparative Study of Data Mining Tools", International Journal of Advanced Research
in Computer Science and Software Engineering, vol. 4, no. 6, pp. 216-223, 2014.
[44] R. Jindal and M. Borah, "A Survey on Educational Data Mining and Research Trends", International Journal of
Database Management Systems, vol. 5, no. 3, pp. 53-73, 2013.
	EDUCATIONAL DATA MINING (EDM)
	EDUCATIONAL KNOWLEDGE DISCOVERY PROCESS
	EDUCATIONAL DATA MINING METHODS
	EDUCATIONAL DATA MINING APPLICATIONS
	DATA MINING TOOLS
	TRENDS OF EDM RESEARCH DURING THE PERIOD 2005-2017
	DISCUSSION
	REFERENCES