Educational Data Mining is a new growing research area that can be defined as the application of data mining techniques on raw data from educational systems in order to respond to the educational questions and problems, and also to discover the information hidden after this data. Over the last few years, the popularity of this field enhanced a large number of research studies that is difficult to surround and to identify the contribution of data mining techniques in educational systems. In fact, exploit and understand the raw data collected from educational systems can be ''a gold mine'' to help the designers and the users of these systems improving their performance and extracting useful information on the behaviors of students in the learning process. The use of data mining techniques in e-learning systems could be very interesting to resolve learning problems. Researchers' ambition is to respond to questions like: What can predict learners' success? Which scenario sequence is more efficient for a specific student? What are the student actions that indicate the learning progress? What are the characteristics of a learning environment allowing a better learning? etc. The current feedback allows detecting the usefulness of applying EDM on visualizing and describing the learning raw data. The predictions take also an interest, particularly the prediction of performance and learners' behaviors. The aim of this chapter is to establish a bibliographic review of the various studies made in the field of educational data mining (EDM) to identify the different aspects studied: the analyzed data, the objectives of these studies, the used techniques and the contribution of the application of these techniques in the field of computer based learning. The goal is not only to list the existing work but also to facilitate the use and the understanding of data mining techniques to help the educational field specialists to give their

Identifying learners' behaviors and learning preferences or styles in a Web-based learning environment is crucial for organizing the tracking and specifying how and when assistance is needed. Moreover, it helps online course designers to adapt the learning material in a way that guarantees individualized learning, and helps learners to acquire meta-cognitive knowledge. The goal of this research is to identify learners' behaviors and learning styles automatically during training sessions, based on trace analysis. In this paper, we focus on the identification of learners' behaviors through our system: Indicators for the Deduction of Learning Styles. We shall first present our trace analysis approach. Then, we shall propose a 'navigation type' indicator to analyze learners' behaviors and we shall define a method for calculating it. To this end, we shall build a decision tree based on semantic assumptions and tests. To validate our approach, and improve the proposed calculation method, we shall present and discuss the results of two experiments that we conducted.

No abstract

Text to speech (TTS) is a crucial tool needed in many domains, mainly for visually impaired users. The availability of TTS open sources improves access to computers and gives more valuable applications. eSpeak provides support for several languages. It is a tool that provides rules and phoneme files for more than 50 languages, besides, eSpeak is a light, fast, low memory consumption and used in multi-platforms. In this paper, we have explored the possibility to adapt the existing text to speech converters into Arabic language in eSpeak. We attempt to define new text to speech conversion rules, adapting existed phonemes and adding missing phonemes for Arabic under eSpeak. The contributions are quite significant; however, the software's developers will be able to integrated these enhancements within the new version, so that users who have problems with visual impairments or children with special needs will utilise this development of eSpeak. The availability of such support, open new fields to use Arabic in TTS environment, especially for blind persons.

International audienceResearch in individual differences and in particular, learning and cognitive style, has become a basis to consider learner preferences in a Web-based educational context. How learnerpsilas learning style influences his/her navigation behavior has been investigated by several studies, which indicate that we can deduce the learning style from the navigation behavior. In this paper, we propose an indicator of ldquonavigation typologyrdquo. We detail the way in which this indicator is calculated, based on tracks analysis, which are aggregated into low and intermediate level indicators to determine the value of the navigation typology