Using Clustering or Association rules on Educational Data

In any learning management system or e-learning environment student accessibility to the study materials are varying in a very diverse manner. Many student are expecting study materials which can be easily understandable so that they can gather more knowledge through them. In order to provide the expected level of learning for the students identifying the learning behavior of each student is required. Due to this nature of different learning patterns of each student, teachers or tutors should be able to provide the materials much more pervasive manner. 

J. Mamcenko, I. Sileikiene, J. Lieponiene, R. Kulvietiene [2011] have tried to apply data mining methodologies to discover the different learning patterns of each students. In their approach they used clustering and association rule mechanisms to identify the learning patterns. 

For the research they focused their research on a programming course examination and the ways that the students have answered. Their collected data on questions given for the student and the answers given by the students with the amount of time that each student has spent on each question to construct the dataset. For the clustering mechanism they used Kohonen algorithm which is based on a self-organizing map (SOM) or self-organizing feature map (SOFM) that is a type of artificial neural network (ANN) and for the association rule mining they used Simultaneous Depth-First Expansion  (SIDE) algorithm.

The analysis of this research indicated that the students find more difficulties in understanding the course development policies. Another indication they found is that the student who are spending more time on questions answered them incorrectly than the questioned they answered in lesser time.

According to their research it can be concluded that the clustering mechanism they used can be used to discover the statistical information about the student behaviors and the learning patterns and the association rules are better way of identifying the complex rules behind student behaviors on e - examination data.   

Reference : J. Mamcenko, I. Sileikiene, J. Lieponiene, R. Kulvietiene, Analysis of E-Exam Data Using Data Mining Techniques, 2011

Performance Prediction Models on Educational Data

In educational systems like Learning Management Systems Students’ academic performance depends on diverse factors like personal, socio-economic, psychological and other environmental variables. Each of these factors can affect the student overall performance in different weights. Based on the level how each of these factor is appearing in the student education several learning patterns can be identified on each of these students. Based on these learning patterns prediction models can be implemented such that they include all these variables for the effective prediction of the performance of the students. The prediction of student performance with high accuracy is beneficial to identify the students with low academic achievements which enable the educators to assist those students individually.

In M. Ramaswami and R. Bhaskaran [2010] research they argued that the student performance could depend on diversified factors such as demographic, academic, psychological, socio-economic and other environmental factors. Based on these factors they constructed a CHAID prediction model with highly influencing predictive variables obtained through feature selection technique to evaluate the academic achievement of students.

Applying Data Mining as a tool to discover the learning behaviour

In online and distance education environments analyzing or observing the student's learning patterns is a huge challenge. To identify the students with learning problems understanding the student learning behaviors can be used as a open bridge by the tutors to provide adaptive and customized feedbacks, guidelines and personalized attention as needed. Most of the available Learning Management Systems (LMS) like moodle or commercial e-learning products provide very limited capability on tracing the student activities such as visit history, discussion boards etc. But the information which is provided can be used for the analysis process since different learning patterns can be identified through the student learning behavior.
 

Jui-Long Hung and Ke Zhang [2008] tried to research on applying data mining techniques on educational data to discover the learning patterns on the students. In their study they tried to differentiate as many online learning behaviors as possible by applying various data mining approaches on data. For this research they selected a undergraduate course in a University and the course module was access by a LMS known as Wisdom Master. The data were collected through server log files where 98 students were selected as the data source for this study.

In the data preprocessing phase the log file data was cleaned by removing all useless, irregular, and missing data from the original LMS common log files and after the initial preprocessing, a session filter was applied to the reduced log file for feature extractions. The purpose of the filter was to aggregate all user requests within a session into a single set of variables. Feature extractions filtered out the following primary variables: user identifier, session identifier, session start date and time, session end date and time, user’s hit count, and session duration in minutes and based on these derived variables (duration and frequency of data of each student) were extracted through calculating or accumulating primary variable data on a daily and weekly basis.

In this research the data mining phase included two sub-phases which were descriptive analysis, and artificial intelligence analysis. Descriptive analysis was used with summarizing, clustering, and association rules techniques to generate an overview on the dataset, to gain an insight into students’ characteristics, and to depict students’ learning patterns and the Artificial intelligence analysis was used for predictive purposes .

Clustering techniques were applied to classify students based on their shared characteristics. They used K-Means clustering mechanism to identify the student clusters based on the behaviors they showed within the LMS environment and Sequential association rules were applied to discover the daily learning patterns of the students in the LMS. Finally they used decision tree algorithm to build the predictive model on the students. According to the predictive model, the frequency of accessing course materials was the most important variable for performance prediction in this study. Also this study concludes that when students participated more actively that is having a higher value on frequency of accessing course materials, number of messages posted, number of messages read, and frequency of synchronous discussions attended they performed better than the others in academically.

Finally in this research paper the authors suggested that instructors would be able to get a quick view of basic learning data, such as login date, frequency, pages visited, etc. However, no functions or features are currently available to help instructors identify learners’ individual or group learning patterns, or to identify successful or less successful learning behavioral patterns, or to identify the predictive learning behaviors or to help identify necessary facilitation needs. Therefore, the researchers of this study strongly suggest that LMS developers should integrate data mining tools to facilitate effective online teaching and learning.

Reference: J. L. Hung and K. Zhang, “Revealing online learning behaviors and activity patterns and making predictions with data mining techniques in online teaching,” MERLOT Journal of Online Learning and Teaching, 2008.

Predicting Student Performance in Distance Learning Systems

In any distance learning environment ability of predicting a student’s performance is very important which is advantageous for the teachers and tutors to identify the students with different capabilities and their capacities. When it comes to University education where many students are accessing or following their studies through open and distance environment it requires a identification process upon the students to measure whether they achieve the required level of performance. Otherwise due to the nature of the distance education some students can be lagging behind while peer students have passed them by miles. If teachers and tutors can recognize them at the early stage of the course module necessary steps or decisions can be made in order to prevent them from dropping out from the course modules.

S. Kotsiantis, C. Pierrakeas, and P. Pintelas [2003] have suggested an approach which has used machine learning algorithms with the LMS data to prevent, student dropouts in university distance education. They tried to investigate the efficiency of machine learning techniques in such an environment with trained data sets provided by the “informatics” course of the Hellenic Open University.

In their research they used five different algorithms to study student data and they found that these algorithms can be used more appropriately to predict the student dropouts in study programs. In this research they used most common machine learning techniques which are Decision Trees, Bayesian Nets, Perceptron-based Learning, Instance-Based Learning and Rule-learning.

In their data collection process they collected student data under two categories of attributes which are Demographic attributes and Performance attributes. The Demographic attributes were collected by concerning students’ sex, age, marital status, number of children and occupation and Performance attributes represents attributes which were collected from tutors’ records concerning students’ marks on the written assignments and their presence or absence in face-to-face meetings.

In the above mentioned algorithms categories they used C4.5 algorithm for representing the decision tree, Naive Bayes algorithm was the representative of the Bayesian networks, the RIPPER algorithm was the representative of the rule-learning techniques, WINNOW as the representative of perceptron-based algorithms and finally 3-NN or 3- Nearest Neighbor as the Instance-Based Learning algorithm.

In order to rank the representative algorithms they used the prediction accuracy criterion was used. In the evaluation of the algorithms they found that there was no statistically significant difference between algorithms, but it showed that the Naive Bayes algorithm and the RIPPER had the best accuracy than the others. Among the Naive Bayes algorithm and the RIPPER, Naive Bayes has the advantage short computational time requirement and importantly Naive Bayes classifier can use data with missing values as inputs, whereas RIPPER cannot work with which gives a indication that the Naive Bayes is the most appropriate learning algorithm to be used for the construction of a software support tool in Learning Management Systems.

Other than the above it was found that there exist some obvious and some less obvious attributes that demonstrate a strong correlation with student performance where some gives the higher importance in consideration. Also it can be argued that the learning algorithms could enable tutors to predict student performance with satisfying accuracy long before final examination. 

Reference: S. Kotsiantis, C. Pierrakeas, and P. Pintelas, “Efficiency of Machine Learning Techniques in Predicting Students’ Performance in Distance Learning Systems,” Citeseer, 2002.

Classification Approaches in Learning Analytics, Does it always give the better results ????

In educational data mining many researchers have tried many different approaches available in data mining context to predict the learning patterns of the students to achieve better and quality results. All these approaches are mainly focusing on getting the results according to a particular student domain which highlights various specific features indicated through the Learning Management Systems.

Virtual learning is growing enormously and the student population those connect with these Learning management systems are increasing by numbers every day. With the necessity of understanding of each student learning pattern teachers should have a better way of predicting the performance of their students. In response to this necessity different classification techniques can be used to compare and interpret the educational data and improve the modeling of students in to different categories.

In order to make the student modeling process much easier Diego Garcia Saiz and Marta Zorrilla [2011] have researched on applying different classification techniques on the student data to predict their performances. In their research they tried to implement a tool known as Elearning Web Miner (EIWM) to discovering how the students are behaving and progress in the courses which is very helpful for the tutors to identify the students who need more attention among from a larger set of students.

One of the main reason that applying learning analytics in educational data sources is challengeable because of the dataset becomes very small comparing to the other application we see around us. Even though the number of student information which contains in a database is huge, most of these are dynamic and contain many variations among them. Since for this research they found it difficult to collect required data which made them to use the data for past three academic years for average student enrollment of 70  per year for a specific course module. For all of these student instances they considered attributes with mean values such as total time spent, number of sessions carried out, number of sessions per week, average time spent per week and average time per session.   

With the intention of analyzing and choosing  best classification algorithms for educational datasets they  analyzed four of the most common machine learning techniques, namely Rule-based algorithms, Decision Trees, Bayesian classifiers and Instance-based learner classifiers which are mainly were OneR, J48, Naive Bayes, BayesNet TAN and NNge. 

They tested these five algorithms using different parameter settings and different numbers of folds for cross validation, in order to discover whether they have a great effect on the result. In the evaluation process they found that Bayes algorithms perform better in accuracy and is comparable to J48 algorithm although it is worse at predicting than Naive Bayes which is the best in this aspect. Due to the results they achieved they highlighted that OneR suffered from over-fitting in this dataset, so that it should be discarded as a suitable classifier for very small datasets.

They also observed that NNge improves its performance in this dataset although the great number of rules which it offers as output makes it less interpretative for instructors than the rest of the models. Finally they conclude that Bayes Networks are suitable for small datasets in performing better than the Naive Bayes when the sample is smaller. As consequence of the fact that BayesNet TAN model is more difficult to interpret for a non-expert users and J48 is similar in accuracy to it.

One significant result which I see in their research is that the pre-processing step which they followed. In the dataset they found that there are instances which can be considered as outliers in the statistical sense and they suggested a mechanism to remove or eliminate those outliers in the data set which can improve the results by 20%. This makes a huge advantage when the data set is larger in size and provide with better quality results for the users.

What I believe about this research is that even though they suggested these approaches in classify the students, it cannot be proved that the same algorithm is suit for every situation we have in the educational domains. Some algorithms can perform well with small datasets and some can perform well with larger data samples and some are providing more interpretable results and some are not. Therefore depending on the problem situation and the context we have to choose the best algorithm that can be used for the specific process so that we get more acceptable quality output as final results.

Reference: D. García-Saiz and M. Zorrilla, “Comparing classication methods for predicting distance students’ performance,” 2011.
 

Sakai or Moodle ???

As I mentioned in my previous posts the Learning Management Systems (LMS) have started its process as assistant to a much more crucial role in higher education. In most of the organizations, Institutions and Universities currently use many different types of Learning Management Systems to provide their study programs for the students. The growth of the Learning Management Systems are been in a challenge between two categories of commercial or the open source where these two are competing each other for providing better service to the users.

The major open source learning management systems those currently dominating the educational space can be specify as Moodle and Sakai. The major factor behind the demand for this open source LMSs is because of their cost saving and more control.  With the available budgetary constraints people tend to move to open source LMSs due to the fact that any function you find in the commercial tools is available with the open source LMS as well.

As mentioned in the Sakai Project web Site the main objective Sakai is to design, build and deploy a new Collaboration and Learning Environment for better higher education. Sakai was initially started by the University of Michigan and Indiana University where both put their efforts to enhance the functionalities. After the grants given by the Mellon Foundation MIT and Stanford joined in and form the Sakai Project.

It is found that in an administrator's perspective, Sakai system is relatively easy to install and setup compared with the many other open source projects in their early stages of development which does not seem to be easy in its installation process. Even the some commercial tool users commented that the Sakai user interface experience very much familiar and easy to manage.

Moodle is a course management system which is a free and Open Source software package designed using sound principles to help educators create effective online learning among the students. It is found that Moodle has a large and diverse user community with over 100,000 registered users which are speaking 70 languages in 145 countries. Currently Moodle community has grown in to a much large number where many software developers are contributing enormously for the plug-ins which comes with different functionalities. Even for a single functionality you can find many different plug-ins which are implemented by different developers for various purposes.