The aim of this PhD thesis is to develop a framework for adaptive intelligent tutoring systems (ITS) in the domain of Modern Standard Arabic language. This framework will comprise of a new approach to using a fuzzy inference mechanism and generic rules in guiding the learning process. In addition, the framework will demonstrate another contribution in which the system can be adapted to be used in the teaching of different languages. A prototype system will be developed to demonstrate these features. This system is targeted at adult English-speaking casual learners with no pre-knowledge of the Arabic language. It will consist of two parts: an ITS for learners to use and a teachers‘ tool for configuring and customising the teaching rules and artificial intelligence components among other configuration operations. The system also provides a diverse teaching-strategies‘ environment based on multiple instructional strategies. This approach is based on general rules that provide means to a reconfigurable prediction. The ITS determines the learner‘s learning characteristics using multiple fuzzy inferences. It has a reconfigurable design that can be altered by the teacher at runtime via a teacher-interface. A framework for an independent domain (i.e. pluggable-domain) for foreign language tutoring systems is introduced in this research. This approach allows the system to adapt to the teaching of a different language with little changes required. Such a feature has the advantages of reducing the time and cost required for building intelligent language tutoring systems. To evaluate the proposed system, two experiments are conducted with two versions of the software: the ITS and a cut down version with no artificial intelligence components. The learners used the ITS had shown an increase in scores between the post-test and the pre-test with learning gain of 35% compared to 25% of the learners from the cut down version.

L’objectif de cette recherche en linguistique de corpus est d’appliquer, suivant les concepts et principes de la sémantique interprétative, une méthode d’analyse contrastive de textes pour l’apprentissage de la langue arabe, en utilisant l’outil de textométrie Lexico 3. Cette étude se base sur deux corpus : l’un de discours journalistiques (thème des révolutions arabes de 2011), et l’autre de discours politiques (de Gamal Abdel Nasser et Anouar Sadate). Nous posons l’hypothèse que, d’une part, la sémantique outillée permet de caractériser les orientations idéologiques et politiques des différents énonciateurs. D’autre part, nous supposons que les analyses permettront de proposer des pistes didactiques applicables dans le cadre d’un apprentissage de la langue arabe, et en particulier pour la compréhension et la production écrites.La première partie de cette étude présente la linguistique de corpus, situe et décrit la sémantique des textes dans les sciences du langage et expose quelques caractéristiques de la langue arabe. La deuxième partie présente nos analyses de textes journalistiques et politiques et met en évidence, les positions des journaux vis-à-vis des révolutions en Égypte et au Bahreïn et expose, les différences d’énonciation des deux présidents égyptiens sur les politiques conduites en Égypte et dans le monde arabe.La troisième et dernière partie présente le volet théorique et pratique de nos pistes didactiques. Elle ancre notre positionnement sur l’interdisciplinarité, en faisant appel au paradigme des "connaissances" (qui se distingue de la notion de "compétence") en didactique des langues. Cette partie décrit, enfin, l’expérimentation avec sept étudiants de langue arabe. Elle montre les difficultés et les apports de cette expérimentation et montre qu’il est possible de penser un processus de conscientisation vis-à-vis des données langagières, qui doit, en outre, marquer une rupture avec la simple transmission d’informations à l’apprenant. / The purpose of this research in corpus linguistics is to apply, in accordance with the concepts and principals of interpretive semantics, a method of contrastive analysis of texts for learning Arabic using the Textometry tool Lexico 3. It is based on two corpora: a journalistic discourse (from Arab revolutions of 2011), and political speeches (from Gamal Abdel Nasser and Anwar Sadat). We postulate that the Corpus Semantics allows us to characterize the ideological and political orientation of the different enunciators. Furthermore we assume that the study will provide practical didactic approaches in the context of learning the Arabic language, in particular for the understanding and writing learning.The first part of this study presents the Corpus Linguistics, situates and describes the Interpretive Semantics theory in the linguistics field and shows some characteristics of the Arabic language. The second part presents our analyses of journalistic and political texts, highlighting the stance of newspapers on the revolutions in Egypt and Bahrain and exposes the differences in articulation between two Egyptian presidents regarding their policies in Egypt and in the Arab world.The third and last part presents the theoretical and practical component of our educational tracks. It anchors our work on the interdisciplinarity by drawing on the paradigm of "knowledge" in language teaching (which is distinct from the notion of "competence"). This section describes the experiment with seven students of Arabic. It shows the difficulties and the benefits of this experiment and demonstrates that it is possible to think of a process of awareness in regards to the language data, which must, amongst other points, mark a break from the simple transmission of information to the learner.