Abstract: The construction of the ETL (Extract-Transform-Load) process is one of the biggest tasks of building a warehouse. ETL processes area has little research, because of its difficulty and lack of formal model for representing ETL activities that map the incoming data from different sources to be in a suitable format for loading into the warehouse. A main problem in data warehousing of multidimensional text databases is to deal with the content in its text cells. In this paper, we propose a model for textual data warehouse ETL processes called ETL-Text. It combines classical data warehousing tasks, information retrieval (IR) techniques, and information processing in particular the language modeling. Our approach is based on Wikipedia as external knowledge source to extract the semantics of the textual documents. To validate our approach, we develop a prototype composed of several processing modules that illustrate the different ETL-Text processes. Also, we use the 20 Newsgroups corpus to perform our experimentation.

Abstract: Les technologies d'entreposage de données et d'analyse en ligne OLAP (On-Line Analytical Processing) ont largement fait leurs preuves pour l'analyse de données structurées, mais elles sont inadaptées pour l'analyse des données textuelles, faute d'outils et de méthodes adaptés. Nous proposons dans cet article, un modèle de cube textuel nommé TCube, qui comporte plusieurs dimensions sémantiques, pour une meilleure prise en charge de la sémantique des données textuelles. Les attributs de chaque dimension sémantique sont regroupés dans une hiérarchie de concepts, extraite d'une ontologie de domaine comme une ressource externe. Notre cube de textes comprend une mesure d'analyse textuelle qui s'appuie sur un modèle vectoriel adapté à l'analyse OLAP et une technique de propagation de pertinence. Il est également associé à un nouvel opérateur d'agrégation permettant d'agréger les données textuelles dans un environnement OLAP. Les résultats préliminaires de notre étude expérimentale montrent l'intérêt de notre approche.

Abstract: Twitter have become a significant means by which people communicate with the world and describe their current activities, opinions and status in short text snippets. Tweets can be analyzed automatically in order to derive much potential information such as, interesting topics, social influence, user's communities, etc. Extraction communities within social networks has been a focus of recent work in several areas. Different from the most community discovery methods focused on the relations between users, we aim to derive user's communities based on common topics from user's tweets. For instance, if two users always talk about politic in their tweets, thus they can be grouped in the same community which is related to politic topic. To achieve this goal, we propose a new approach called CETD: Community Extraction based on Topic-Driven-Model. This approach combines our proposed model used to detect topics of the user's tweets based on a semantic taxonomy together with a community extraction method based on the hierarchical clustering technique. Our experimentation on the proposed approach shows the relevant of the users communities extracted based on their common topics and domains.

---------

Abstract: Access to relevant information adapted to the needs and the context of the user is a real challenge. The user context can be assimilated to all factors that can describe his intentions and perceptions of his surroundings. It is difficult to find a contextual information retrieval system that takes into account all contextual factors. In this paper, both types of context user context and query context are integrated in an Information Retrieval (IR) model based on language modeling. Here, the query context include the integration of linguistic and semantic knowledge about the user query in order to explore the most exact understanding of user's information needs. In addition, we consider one of the important factors of the user context, the user's domain of interest or the interesting topic. A thematic algorithm is proposed to describe the user context. We assume that each topic can be characterized by a set of documents from the experimented corpus. The documents of each topic are used to build a statistical language model, which is then integrated to expand the original query model and to re-rank the retrieved documents. Our experiments on the 20_Newsgroups corpus show that the proposed contextual approach improves significantly the retrieval effectiveness compared to the basic approach, which does not consider contextual factors.

Abstract: Access to relevant information adapted to the needs and the context of the user is a real challenge in Web Search, owing to the increases of heterogeneous resources and the varied data on the web. There are always certain needs behind the user query, these queries are often ambiguous and shortened, and thus we need to handle these queries intelligently to satisfy the user’s needs. For improving user query processing, we present a context-based hybrid method for query expansion that automatically generates new reformulated queries in order to guide the information retrieval system to provide context-based personalized results depending on the user profile and his/her context. Here, we consider the user context as the actual state of the task that the user is undertaking when the information retrieval process takes place. Thus State Reformulated Queries (SRQ) are generated according to the task states and the user profile which is constructed by considering related concepts from existing concepts in domain ontology. Using a task model, we will show that it is possible to determine the user’s current task automatically. We present an experimental study in order to quantify the improvement provided by our system compared to the direct querying of a search engine without reformulation, or compared to the personalized reformulation based on a user profile only. The preliminary results have proved the relevance of our approach in certain contexts.