Résumé. Dans cet article, nous proposons un cadre visant à automatiser la construction de variables pour l’apprentissage supervisé, en particulier dans le cadre multi-tables. La connaissance du domaine est spécifiée d’une part en structurant les données en variables, tables et liens entre tables, d’autre part en choisissant des règles de construction de variables. L’espace de construction de va...

Modeling the diffusion of information on social media has mainly been treated as a diffusion process on known graphs, and under closed world assumptions. We introduce here a new approach to this problem whose principle is to learn a mapping of the observed interacting users onto a latent representation space in such a way that information diffusion can be modeled efficiently using a heat diffus...

Building and exploiting a French corpus for sentiment analysis This work introduces a French corpus for sentiment analysis. We describe the construction and organization of the corpus. We then apply machine learning techniques to automatically predict whether a text is positive or negative (the opinion classification task). Two techniques are used : logistic regression and classification based ...

In this paper, we apply a general reinforcement learning method to automatically design the behavior of non player characters of the Counter-Strike first person shooter computer game. The result of the learning process is a set of decision trees that represents compactly and easily readable a model of the problem itself and the decision policy of characters. Beyond this example, we discuss the ...

In this article we motivate and present a methodology based on a collaborative production as realistic way to meet teachers’ skills for an efficient production of e-learning documents. The proposed methodology points out the “Macro Design” as an independent task to be supported during the first phase of the production. This paper presents an efficient method to support the Macro Design using th...

More and more companies are migrating their legacy document management systems toward XML format, the industrial standard for data exchange. In order to reduce the migration cost we propose an approach aimed at automating the conversion of layout-oriented documents to semantic-oriented annotations. The conversion module uses supervised machine learning techniques to learn a conversion model for...

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau...

depuis les nouvelles méthodologies, les didacticiens/méthodologues considèrent l’apprenant comme le centre d’intérêt dans le processus de l’enseignement/apprentissage. dans chaque domaine disciplinaire, les enseignants doivent faire une attention particulière aux particularités des sujets apprenants. en général, si nous voulons diviser les apprenants en différents groupes, une partie des appren...

L’enseignement-apprentissage du rythme de la langue enseignée et étudiée, française dans ce cas, n’a pas, nos jours, une place prépondérante en didactique méthodologie française, malgré l’impossibilité le dissocier l’intonation, des sons système communication. En interrogeant personnellement étudiants français Espagne sur leur perception tant qu’objet d’étude consultant globalement partie l’off...