Presently, educational institutions compile and store huge volumes of data, such as student enrolment and attendance records, as well as their examination results. Mining such data yields stimulating information that serves its handlers well. Rapid growth in educational data points to the fact that distilling massive amounts of data requires a more sophisticated set of algorithms. This issue led to the emergence of the field of educational data mining (EDM). Traditional data mining algorithms cannot be directly applied to educational problems, as they may have a specific objective and function. This implies that a preprocessing algorithm has to be enforced first and only then some specific data mining methods can be applied to the problems. One such preprocessing algorithm in EDM is clustering. Many studies on EDM have focused on the application of various data mining algorithms to educational attributes. Therefore, this paper provides over three decades long (1983–2016) systematic literature review on clustering algorithm and its applicability and usability in the context of EDM. Future insights are outlined based on the literature reviewed, and avenues for further research are identified.

A Systematic Review on Educational Data Mining

Traffic congestion is rapidly increasing in urban areas, particularly in mega cities. To date, there exist a few sensor network based systems to address this problem. However, these techniques are not suitable enough in terms of monitoring an entire transportation system and delivering emergency services when needed. These techniques require real-time data and intelligent ways to quickly determine traffic activity from useful information. In addition, these existing systems and websites on city transportation and travel rely on rating scores for different factors (e.g., safety, low crime rate, cleanliness, etc.). These rating scores are not efficient enough to deliver precise information, whereas reviews or tweets are significant, because they help travelers and transportation administrators to know about each aspect of the city. However, it is difficult for travelers to read, and for transportation systems to process, all reviews and tweets to obtain expressive sentiments regarding the needs of the city. The optimum solution for this kind of problem is analyzing the information available on social network platforms and performing sentiment analysis. On the other hand, crisp ontology-based frameworks cannot extract blurred information from tweets and reviews; therefore, they produce inadequate results. In this regard, this paper proposes fuzzy ontology-based sentiment analysis and semantic web rule language (SWRL) rule-based decision-making to monitor transportation activities (accidents, vehicles, street conditions, traffic volume, etc.) and to make a city-feature polarity map for travelers. This system retrieves reviews and tweets related to city features and transportation activities. The feature opinions are extracted from these retrieved data, and then fuzzy ontology is used to determine the transportation and city-feature polarity. A fuzzy ontology and an intelligent system prototype are developed by using Protege web ontology language (OWL) and Java, respectively. The experimental results show satisfactory improvement in tweet and review analysis and opinion mining.

Fuzzy ontology-based sentiment analysis of transportation and city feature reviews for safe traveling☆

Learning Analytics (LA) is an emerging field in which sophisticated analytic tools are used to improve learning and education. It draws from, and is closely tied to, a series of other fields of study like business intelligence, web analytics, academic analytics, educational data mining, and action analytics. The main objective of this research work is to find meaningful indicators or metrics in a learning context and to study the inter-relationships between these metrics using the concepts of Learning Analytics and Educational Data Mining, thereby, analyzing the effects of different features on student's performance using Disposition analysis. In this project, K-means clustering data mining technique is used to obtain clusters which are further mapped to find the important features of a learning context. Relationships between these features are identified to assess the student's performance.

Application of learning analytics using clustering data Mining for Students' disposition analysis

The major requirement of present e-learning system is to provide a personalized interface with adaptiveness. This is possible to provide by analyzing the learning behaviors of the learners in the e-learning portal through Web Usage Mining (WUM). In this paper, a method is proposed where the learning behavior of the learner is captured using web logs and the learning styles are categorized according to Felder-Silverman Learning Style Model (FSLSM). Each category of FSLSM learner is provided with the respective content and interface that is required for the learner to learn. Fuzzy C Means (FCM) algorithm is used to cluster the captured data into FSLSM categories. Gravitational Search based Back Propagation Neural Network (GSBPNN) algorithm is used to predict the learning styles of the new learner. This algorithm is a modification of basic Back Propagation Neural Network (BPNN) algorithm that calculates the weights using Gravitation Search Algorithm (GSA). The algorithm is validated on the captured data and compared using various metrics with the basic BPNN algorithm. The result shows that the performance of GSBPNN algorithm is better than BPNN. Based on the identified learning style, the adaptive contents and interface can be provided to the learner.

/pdf/prediction-of-learner-s-profile-based-on-learning-styles-in-2d2ru682qu.pdf

Prediction of Learner’s Profile based on Learning Styles in Adaptive E-learning System

Sentimental Analysis of Twitter Data with respect to General Elections in India

Every day, huge numbers of instant tweets (messages) are published on Twitter as it is one of the massive social media for e-learners interactions. The options regarding various interesting topics to be studied are discussed among the learners and teachers through the capture of ideal sources in Twitter. The common sentiment behavior towards these topics is received through the massive number of instant messages about them. In this paper, rather than using the opinion polarity of each message relevant to the topic, authors focus on sentence level opinion classification upon using the unsupervised algorithm named bigram item response theory (BIRT). It differs from the traditional classification and document level classification algorithm. The investigation illustrated in this paper is of threefold which are listed as follows: (1) lexicon based sentiment polarity of tweet messages; (2) the bigram cooccurrence relationship using naive Bayesian; (3) the bigram item response theory (BIRT) on various topics. It has been proposed that a model using item response theory is constructed for topical classification inference. The performance has been improved remarkably using this bigram item response theory when compared with other supervised algorithms. The experiment has been conducted on a real life dataset containing different set of tweets and topics.

/pdf/intelligent-topical-sentiment-analysis-for-the-2w6ep5dx0q.pdf

Intelligent Topical Sentiment Analysis for the Classification of E-Learners and Their Topics of Interest

This Research paper focus on the design and development of intelligent, personalized mobile agent for learning object classification and retrieval. We have used JADE (Java Agent Development Environment) platform to launch, migrate, classify and retrieve the learning content based on the customized query by a peer learners in an virtual e-learning environment like MOODLE. In turn the agent collects the user query and migrates into different Learning Object Repository, (LOR), learn and interact with them and retrieves the Learning Objects(LO) along with its Learning Object Metadata (LOM). From the retrieved learning objects the learner applies the machine learning algorithm for the purpose of classifying the LO based on his usefulness/interestingness/learning objective and etc., The retrieval agent has been trained by the machine learning algorithms and then this trained agents now migrates into different such LORs applies the classification in that respective place and retrieves only the relevant and ranked learning objects to the learner based on the learners pre classification techniques and interest. The main drawback in the case of traditional Client-Server based learning environment, the learner client portal takes the query of the learner, and retrieves all the result set irrespective of usefulness/interestingness of the learner. Here the learner spent time to get the irrelevant or non interested content along with the required set itself. The bandwidth also used to the transfer such uninterested content is waste. These two drawbacks can be avoided or rectified through the mobile agent which posses the capability of classification based on feature subset selection techniques like Infogain, entropy and machine learning algorithm then migrates into the different LOR for collecting the relevant LO. As soon as it is once migrated into the LOR, it applies the machine learning algorithm first and then classifies the result to eliminate the non interested content not to be retrieved and transported to the learner side. The result of experiment using there different classifier, TF-IDF, Bayesian and Fuzzy classifier for the design and development of trained document classifier are Presented. The feature subset selection algorithm can be integrated with this to improve further accuracy of classifications.(future work).

Automatic classification of learning objects through dimensionality reduction and feature subset selections in an e-learning system

The Apply of data mining technique in to domain specific applications is being drastically improved more and more by the researchers to improve the best decision making recommendation systems like e-learning ,e-commerce and etc.,In this research work we discuss how the datamining techniques will improve the learning style adaptation, learning content organisation and learning objects recommendations based on the instantaneous data collected through the web based learning management system like moodle. This paper focus the techniques like data classification and clustering techniques to predict the learning style of the peer learners based on the activities they have completed in the teaching learning activity of a particular course. The Experimental results shows the clear snopshot of the analysis.

Effect of mining educational data to improve adaptation of learning in e-learning system

A wireless based Mobile Ad Hoc Network, which is referred as MANET relies infrastructure-less based network composed nodes which are connected through wireless medium that permit communication among mobile nodes without any central base station. The dynamic behavior and unique characteristics of MANETs, providing a reliable and high stability route for transmitting either data or control packet to a shared working group becomes challenging. This paper presents seeks to propose a fuzzy-logic and Cross-layer optimized Multicast Route finding Protocol (C-MRP) which addresses and overcomes the issue of adhoc multicast on-demand table-use routing protocol. We integrate a light weight fuzzy set of rules to select optimal multiple routes to a group of destination nodes using route stability, accessible network bandwidth and node-to-node delay. The vital simulation result reports that C-MRP outperforms than existing solutions in all aspects.

Discovery of optimal multicast routes in MANETs using cross-layer approach and fuzzy logic support system

Diabetes mellitus is a metabolic illness that causes high blood sugar, which is widely known as diabetes. Insulin is a hormone produced by an organ situated behind the abdomen called the pancreas. This insulin agent moves glucose from your blood into the cells for energy and storage. With diabetic disorder, the body either will not create enough insulin or can’t effectively use the insulin it does create. Untreated high blood glucose or sugar from diabetic disorder will harm the nerves, eyes, kidneys, and different organs of the body. There are different data mining software tools to predict and analyze diabetes. Many attempts have been made by researchers to improve the efficiency of various models. The proposed method is Dimensionality reduction and clustering technique. It gives the highest accuracy for the larger dataset for both balanced and imbalanced datasets. In this paper, large and small datasets have been taken for clustering using K-means approach, Farthest first method, Density based technique, Filtered clustering method and X-means approach. K-means, density based and X-means gives the highest accuracy of 75.64%. For the larger balanced dataset when compared with the smaller balanced dataset.

T. Chellatamilan

Papers

Intelligent Topical Sentiment Analysis for the Classification of E-Learners and Their Topics of Interest

Automatic classification of learning objects through dimensionality reduction and feature subset selections in an e-learning system

Effect of mining educational data to improve adaptation of learning in e-learning system

Discovery of optimal multicast routes in MANETs using cross-layer approach and fuzzy logic support system

Detection of Type 2 Diabetes Using Clustering Methods – Balanced and Imbalanced Pima Indian Extended Dataset