Michel Plantié

Web opinion mining: how to extract opinions from blogs?

The growing popularity of Web 2.0 provides with increasing numbers of documents expressing opinions on different topics. Recently, new research approaches have been defined in order to automatically extract such opinions from the Internet. They usually consider opinions to be expressed through adjectives, and make extensive use of either general dictionaries or experts to provide the relevant adjectives. Unfortunately, these approaches suffer from the following drawback: in a specific domain, a given adjective may either not exist or have a different meaning from another domain. In this paper, we propose a new approach focusing on two steps. First, we automatically extract a learning dataset for a specific domain from the Internet. Secondly, from this learning set we extract the set of positive and negative adjectives relevant to the domain. The usefulness of our approach was demonstrated by experiments performed on real data.

Survey on Social Community Detection

Community detection is a growing field of interest in the area of social network applications. Many community detection methods and surveys have been introduced in recent years, with each such method being classified according to its algorithm type. This chapter presents an original survey on this topic, featuring a new approach based on both semantics and type of output. Semantics opens up new perspectives and allows interpreting high-order social relations. A special focus is also given to community evaluation since this step becomes important in social data mining.

Is a Voting Approach Accurate for Opinion Mining

In this paper, we focus on classifying documents according to opinion and value judgment they contain. The main originality of our approach is to combine linguistic pre-processing, classification and a voting system using several classification methods. In this context, the relevant representation of the documents allows to determine the features for storing textual data in data warehouses. The conducted experiments on very large corpora from a French challenge on text mining (DEFT) show the efficiency of our approach.

Towards an automatic characterization of criteria

The number of documents is growing exponentially with the rapid expansion of the Web. The new challenge for Internet users is now to rapidly find appropriate data to their requests. Thus information retrieval, automatic classification and detection of opinions appear as major issues in our information society. Many efficient tools have already been proposed to Internet users to ease their search over the web and support them in their choices. Nowadays, users would like genuine decision tools that would efficiently support them when focusing on relevant information according to specific criteria in their area of interest. In this paper, we propose a new approach for automatic characterization of such criteria. We bring out that this approach is able to automatically build a relevant lexicon for each criterion. We then show how this lexicon can be useful for documents classification or segmentation tasks. Experiments have been carried out with real datasets and show the efficiency of our proposal.

From photo networks to social networks, creation and use of a social network derived with photos

With the new possibilities in communication and information management, social networks and photos have received plenty of attention in the digital age. In this paper, we show how social photos, captured during family events, representing individuals or groups, can be visualized as a network that reveals social attributes. From this photo network, social network is extracted that can help to build personalized albums. The photo network organization makes use of Formal Concept Analysis methods.

Knowledge Cartography and Social Network Representation: Application to Collaborative Platforms in Scientific Area

Our research revolves around collaborative platforms entirely dedicated to research activities for several scientific organizations. Here, researchers from different domains interact and exchange information using our platforms as the common ground involving new concepts, methods and services to encourage collaborative work for their research activities. The work is based on the co-operation and collaboration between scientific specialists and engineers building the platform. In our proposal we attempt to capture the individual information and then build social network representations to build a group representation of knowledge, attracting and encouraging people to participate in collaborative tasks.

complementarity of Persons sharing properties in social networks

Our previous work focused on the unified community detection in networks of people: social networks, communities of actors, etc. shown as generally bipartite graph. In this article. We define therefore the notion of complementarity between the vertices of a bipartite graph. We use for it the concepts of entropy and mutual information. We show the usefulness of such an approach and the value of the approach by an experiment on a well known example. Complementarity in social networks is an interesting approach to identify cohesion in groups of persons. Our previous works studied a first approach of complementarity in networks represented as bipartite graphs: social networks, communities of actors, etc. In this paper we try to respond to semantic complementarity problems that arise as soon as one wishes to associate people in order to best fulfil a goal. We compare several approaches of complementarity to find the most appropriate technique. In some definitions of complementarity, the problem is viewed as close to a classical research: find transversals in hypergraphs, with however differences in final goals. To validate our approach, we apply and compare our methods on well known graphs and real data whose sizes are very different: from small graphs to very large graphs.