Marian Cristian Mihăescu

Building Intelligent E-Learning Systems by Activity Monitoring and Analysis

E-Learning area has been intensively developed in recent years. One of the important research areas is related to improving e-Learning activity by giving the intelligent character to this activity besides core functionalities that is implemented in all e-Learning platforms.

Classification of users by using support vector machines

Proper classification of students is one of the key aspects in e-Learning environments. This paper uses support vector machines (SVM) for classifying users whose features are represented by the performed activity. The classification of students is performed at discipline level since the features are related only to general activities. The output of the process is represented by a set of classes. The obtained classes are further used for classifying new users, whose activity data has not been used for building the classifier.

Data analysis on social media traces for detection of “spam” and “don’t care” learners

Classification methods are becoming more and more useful as part of the standard data analyst’s toolbox in many application domains. The specific data and domain characteristics of social media tools used in online educational contexts present the challenging problem of training high-quality classifiers that bring important insight into activity patterns of learners. Currently, standard and also very successful model for classification tasks is represented by decision trees. In this paper, we introduce a custom-designed data analysis pipeline for predicting “spam” and “don’t care” learners from eMUSE online educational environment. The trained classifiers rely on social media traces as independent variables and on final grade of the learner as dependent variables. Current analysis evaluates performed activities of learners and the similarity of two derived data models. Experiments performed on social media traces from five years and 285 learners show satisfactory classification results that may be further used in productive environment. Accurate identification of “spam” and “don’t care” users may have further a great impact on producing better classification models for the rest of the “regular” learners.

Improving Peer-to-Peer Communication in e-Learning by Development of an Advanced Messaging System

This chapter presents an advanced messaging system, whose goal is to improve the peer-to-peer communication in e-Learning. The improvement is based on the ability of the developed system to produce information that is highly related to the informational needs of the person, who accesses it. The system is an intelligent one because it integrates a classification procedure for retrieval of the messages that have a high potential of being interesting to peers. It uses as input data activity logs obtained by monitoring the communication that takes place within the e-Learning platform. The main data analysis goal is to create a user’s model, for which derived classes are in close relation with specific set of messages. The outcome is in the form of a tool that allows learners to receive a set of recommended messages that is highly to be interesting for them. The tool analyzes the user’s features, classifies them and according with the class label obtained set of messages. The tool also acts as a message indexing system by storing messages in correlation with labels assigned to learners. A classical classification procedure is used for obtaining a labeling. The data used to train the classifier is gathered from the on-line educational environment and contains all the necessary information (i.e., the features) regarding the activities performed by learners on the platform. The high quality of the system is based also on a text-mining module that uses stemming, annotation, and concept detection for a proper assignment of messages to learner’s labels.

Using Mathematics for Data Traffic Modeling Within an E-Learning Platform.

E-Learning data traffic characterization and modeling may bring important knowledge about the characteristics of that traffic. Without measurement, it is considered impossible to build realistic traffic models. We propose an analysis architecture employed for characterization and modeling using data mining techniques and mathematical models. The main problem is that real data traffic usually has to be measured in real time, saved, and later analyzed. The proposed architecture uses data from the application level. In this way the data logging process becomes a much easier task, with practically the same outcomes.

A Structure for Management of Requirements Set for e-Learning Applications

Extracting and managing requirements is one of the most important tasks in creating a reliable software product. This step of the overall software engineering process becomes even more critical when the development process is to become a global one. This paper presents an approach for passing from ad hoc requirements management to systematic requirements management. This step is often needed due to the increasing scale of software system and increasing globalization. The study is presented for an e-Learning platform that has been developed and reached a certain maturity level such that these kind of activities are needed. The proposed solution in the paper allows centralization of requests among involved parties (developers and beneficiaries). It is proposed a custom structure for requests that has at its basis the very specificity of developed application. The structuring of requirements is customized for platform’s functionality such that the process which determines what functionalities may be outsourced is improved.