Guy Melançon

Guy Melançon
2007 - University of Bordeaux · Computer Science

1991 - PhD Combinatorial Mathematics, Université du Québec à Montréal, Canada

About

166
Publications
34,015
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,285
Citations
Citations since 2016
38 Research Items
1771 Citations
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250

Publications

Publications (166)
Article
EGC ("Extraction et Gestion des Connaissances"1 in French) started in 2001 and is the reference conference for the french community in Knowledge Extraction and Management (equivalent to the French KDD).
Article
Full-text available
Querying and retrieving relevant information still remains a difficult task, one with a relatively high cognitive cost for users, who usually focus only on the first few pages of results. This issue drives effort to support the exploration of search results through clustering and visualization. This paper contributes to this challenge by providing...
Chapter
We present a visual analytics framework to aid the investigation of dynamic multilayer networks, focusing on the visual tracking of evolving communities. We were challenged by edges not persistent in time, rather hectic, inducing communities that are “volatile”. Working closely with field experts, three complementary perspectives are developed to t...
Article
Full-text available
Visualizing social networks, especially an overview emphasizing their structure, i.e., communities and their interconnections, is known to be a challenging problem. In this paper, we present a set of design rationales to build such overview visualizations of social networks and our solution called Jasper. We evaluate its performances against two of...
Chapter
Human-Computer Interaction (HCI) and Artificial Intelligence (AI) are two disciplines that followed parallel trajectories for about four decades. They also both complement each other and overlap in various problem-rich domains. This chapter is far from being exhaustive, but provides a representative story of how HCI and AI cross-fertilise each othe...
Article
Full-text available
We propose a mixed methods approach to digital ethnographic research. Treating online conversational environments as communities that ethnographers engage with as in traditional fieldwork, we represent those conversations and the codes made by researchers thereon in network form. We call these networks “semantic social networks” (SSNs), as they inc...
Experiment Findings
Full-text available
Les modes opératoires des groupes criminels se livrant à des faits de traite des êtres humains sont complexes et reposent sur des pratiques diverses : fabrication et mise en circulation de faux documents, violation des règles migratoires, détournement de la demande d’asile, fraude aux prestations sociales, circulation, transfert et blanchiment de f...
Article
Full-text available
Modelling relationship between entities in real-world systems with a simple graph is a standard approach. However, reality is better embraced as several interdependent subsystems (or layers). Recently, the concept of a multi-layer network model has emerged from the field of complex systems. This model can be applied to a wide range of real-world da...
Preprint
Modelling relationships between entities in real-world systems with a simple graph is a standard approach. However, reality is better embraced as several interdependent subsystems (or layers). Recently the concept of a multilayer network model has emerged from the field of complex systems. This model can be applied to a wide range of real-world dat...
Preprint
In this paper, we propose a new drag and drop interaction technique for graphs. We designed this interaction to support analysis in complex multidimensional and temporal graphs. The drag and drop interaction is enhanced with an intuitive and controllable animation, in support of comparison tasks.
Conference Paper
One task key to the analysis of large multimedia archive over time is to dynamically monitor the activity of concepts and entities with their interactions. This is helpful to analyze threads of topics over news archives (how stories unfold), or to monitor evolutions and development of social groups. Dynamic graph modeling is a powerful tool to capt...
Article
Full-text available
Nowadays we are living the apogee of the Internet based technologies and consequently web 2.0 communities, where a large number of users interact in real time and share opinions and knowledge, is a generalized phenomenon. This type of social networks communities constitute a challenge scenario from the point of view of Group Decision Making approac...
Conference Paper
Most successful online communities employ professionals, sometimes called “community managers”, for a variety of tasks including on boarding new participants, mediating conflict, and policing unwanted behaviour. We interpret the activity of community managers as network design: they take action oriented at shaping the network of interactions in a w...
Conference Paper
We propose a data-based approach to doing ethnographic research in a digital environment. It has three main components. First, it treats online conversational environments as human communities, that ethnographers can engage with as they would in onsite fieldwork. Second, it represents those conversations, and the fieldnotes made by researchers ther...
Conference Paper
Multimedia data is by nature heterogeneous, conveying semantic information through multiple cues. Text analysis of closed captions already brought us understanding of the spoken information. Today's advances in computer vision now enable us to look for relevant semantic information from the visual content of real-world archives. Combining these two...
Article
Full-text available
Online communities are used across several fields of human activities, as environments for large-scale collaboration. Most successful ones employ professionals, sometimes called “community managers” or “moderators”, for tasks including onboarding new participants, mediating conflict, and policing unwanted behaviour. Network scientists routinely mod...
Article
Full-text available
Cet article dessine le contexte d’une étude portant sur les réseaux criminels de traite des êtres humains et décrit la rencontre de trois champs disciplinaires engagés dans ces travaux : Droit, Sociologie et Informatique, ainsi que les éléments méthodologiques développés. Il pose les fondations d’une méthodologie venant en appui à l’étude juridique...
Book
We propose a data-based approach to doing ethnographic research in a digital environment. It has three main components. First, it treats online conversational environments as human communities, that ethnographers can engage with as they would in onsite fieldwork. Second, it represents those conversations, and the fieldnotes made by researchers ther...
Book
Most successful online communities employ professionals, sometimes called " community managers " , for a variety of tasks including onboarding new participants, mediating conflict, and policing unwanted behaviour. We interpret the activity of community managers as network design: they take action oriented at shaping the network of interactions in a...
Article
Full-text available
One of the most widely studied problem in mining and analysis of complex networks is the detection of community structures. The problem has been extensively studied by researchers due to its high utility and numerous applications in various domains. Many algorithmic solutions have been proposed for the community detection problem but the quest to f...
Article
Many interconnected systems and particularly social interactions can be modeled as networks. These networks often exhibit common properties such as high clustering coefficient, low average path lengths and degree distributions following power-law. Networks having these properties are called small world-scale free networks or simply complex networks...
Article
A multiplex network has links of different types, allowing it to express many overlapping types of relationships. A core task in network analysis is to evaluate and understand group cohesion; that is, to explain why groups of elements belong together based on the underlying structure of the network. We present Detangler, a system that supports visu...
Article
Full-text available
Numerous propagation models describing social influence in social networks can be found in the literature. This makes the choice of an appropriate model in a given situation difficult. Selecting the most relevant model requires the ability to objectively compare them. This comparison can only be made at the cost of describing models based on a comm...
Article
Full-text available
Prix du meilleur article académique (http://www.egc.asso.fr/Manifestations_dEGC/5-FR-Prix_EGC)
Conference Paper
Full-text available
Software designs are ever changing to adapt to new environments and requirements. Tracking and understanding changes in modules and relationships in a software project is difficult, but even more so when the software goes through several types of changes. The typical complexity and size of software also makes it harder to grasp software evolution p...
Article
Full-text available
Modeling propagation dynamics on networks is an amazingly fertile and active area of research. Roughly speaking, network models aim at gaining a better understanding of how actors influence the overall network behaviour through their individual actions. However, considering the extended literature surrounding the subject, one is entitled to think t...
Article
Full-text available
Hierarchical clustering of graphs is a useful strategy to mine, explore and visualize graphs. Popular approaches define ad hoc procedures to decide how subgraphs are subdivided or nested. The popularity of graph hierarchies certainly relates to the relevance of multilevel models appearing in the natural and social sciences. For instance, current mo...
Chapter
Full-text available
L’interaction personne-système et l’intelligence artificielle sont deux disciplines qui ont suivi des trajectoires parallèles au cours du temps tout en se rejoignant et se complémentant naturellement sur différents domaines aux problématiques riches depuis une quarantaine d’années. Sans souci d’exhaustivité mais plutôt de représentativité, après av...
Chapter
Full-text available
The analysis and exploration of a social network depends on the type of relations at play. Homophily (similarity) relationships form an important category of relations linking entities whenever they exhibit similar behaviors. Examples of homophily networks examined in this paper are: co-authorship, where homophily between two persons follows from h...
Book
SynonymsData analysis; Graph visualization; Visualization framework Tool's ID CardTool name: TulipCreation year: 1999Authors: David Auber (original author), Daniel Archambault, Romain Bourqui, Maylis Delest, Jonathan Dubois, Bruno Pinaud, Antoine Lambert, Patrick Mary, Morgan Mathiaut, and Guy MelançonScope: generalCopyright: LGPLType: program/libr...
Article
Full-text available
Journées communes aux Groupes de Travail EGC et AFIHM -- Big Data Mining and Visualization
Conference Paper
Full-text available
Exploring document collections remains a focus of research. This task can be tackled using various techniques, typically ranking documents according to a relevance index or grouping documents based on various clustering algorithms. The task complexity produces results of varying quality that inevitably carry noise. Users must be careful when interp...
Article
Full-text available
Recent interest in complex systems and specially social networks has catalyzed the development of numerous models to help understand these networks. A number of models have been proposed recently where they are either variants of the small-world model, the preferential attachment model or both. Three fundamental properties attributed to identify th...
Conference Paper
Full-text available
The analysis and exploration of a social network depends on the type of relations at play. Borgatti had proposed a type taxonomy organizing relations in four possible categories. Homophily (similarity) relationships form an important category where relations occur when entities of the network link whenever they exhibit similar behaviors. Examples a...
Conference Paper
Being able to produce a wide variety of layouts for a same graphs may prove useful when users have no preferred visual encoding for their data. The first contribution of this paper is a enhanced force-directed layout capable of producing different layouts of a same graph. We turn a well known force-directed algorithm (GEM) into a highly parametriza...
Chapter
Specific properties emerge from the structure of large networks, such as that of worldwide air traffic, including a highly hierarchical node structure and multi-level small world sub-groups that strongly influence future dynamics. We have developed clustering methods to understand the form of these structures, to identify structural properties, and...
Book
This leading-edge study focuses on the latest techniques in analysing and representing the complex, multi-layered data now available to geographers studying urban zones and their populations. The volume tracks the successful results of the SPANGEO Project, which was set up in 2005 to standardize, and share, the syncretic, multinational mapping tech...
Chapter
Network analysis naturally relies on graph theory and, more particularly, on the use of node and edge metrics to identify the salient properties in graphs. When building visual maps of networks, these metrics are turned into useful visual cues or are used interactively to filter out parts of a graph while querying it, for instance. Over the years,...
Article
Full-text available
Avec l'explosion des ressources en ligne, l'exploration efficace de collections de documents est une tâche quotidienne pour bon nombre de professions , mais paradoxalement reste un enjeu pour la recherche. Nous proposons trois outils pour aider à percevoir le contenu sémantique d'un ensemble de documents : un réseau pondéré d'interaction des termes...
Article
We define a class of Lyndon words, called Christoffel-Lyndon words. We show that they are in bijection with n-tuples of relatively prime natural numbers. We give a geometrical interpretation of these words. They are linked to an algorithm of Euclidean type. It admits an extension to n-tuples of real numbers; we show that if the algorithm is periodi...
Article
Full-text available
Exploring document collections remains a focus of research. This task can be tackled using various techniques, typically ranking documents according to a relevance index or grouping documents based on various clustering algorithms. The task complexity produces results of varying quality that inevitably carry noise. Users must be careful when interp...
Article
Graph rewriting systems (GRSs) operate on graphs by substituting local patterns according to a set of rewriting rules. The apparent simplicity of GRSs hides an incredible complexity and turns the study of these systems into an involved task requiring high-level expertise. We designed PORGY, an interactive visual environment to fully support GRSs re...
Article
Full-text available
Recent interest in complex networks has catalysed the development of numerous models to help artificially generate and understand these networks. Watts and Strogatz presented a model [37] to explain how the two properties of small world networks, high clustering coefficient and low average path length appear in networks. Barabási and Albert gave a...
Article
Full-text available
With the exponential growth in the size of data and networks, de-velopment of new and fast techniques to analyze and explore these networks is becoming a necessity. Moreover the emergence of scale free and small world properties in real world networks has stimulated lots of activity in the field of network analysis and data mining. Clustering remai...
Article
Full-text available
Recent interest in complex networks has catalyzed the development of numerous models to help artificially generate and understand these networks. Watts and Strogatz presented a model (Watts Strogatz 1998) to explain how the two properties of small world networks, high clustering coefficient and low average path length appear in networks. (Barabasi...
Article
Full-text available
Tulip is an information visualization framework dedicated to the analysis and visualization of relational data. Based on a decade of research and development of this framework, we present the architecture, consisting of a suite of tools and techniques, that can be used to address a large variety of domain-specific problems. With Tulip, we aim to pr...
Article
Interactive visualization interfaces for graph are an interesting perspective for data analysis, and by extension for decision support system. The aim of this project is to assist user in drawing graphs. Currently, one of the main difficulties for the user is to choose the best fitted algorithm for his graph. Indeed, there are lots of different alg...
Article
Nous donnons une généralisation de la décomposition de M. Hall des éléments du groupe libre en produits décroissant de commutateurs de Hall. Nous généralisons les identités de Thérien, qui expriment les exposants de la décomposition comme des sommes à coefficients entiers positifs de fonctions sous-mots. Nous étudions l’algèbre des fonctions sous-m...
Conference Paper
Full-text available
Graph rewriting systems are easily described and explained. They can be seen as a game where one iterates transformation rules on an initial graph, until some condition is met. A rule describes a local pattern (i.e. a subgraph) that must be identified in a graph and specifies how to transform this subgraph. The graph rewriting formalism is at the s...
Article
Full-text available
Nous proposons une méthode pour visualiser et analyser les évènements médiatiques à partir des sujets d'actualité des journaux télévisés de plusieurs chaînes annotées avec des descripteurs textuels. Nous présentons une interface d'exploration basée sur un modèle de graphe de similarité sémantique. Après une étape classique couplant clustering et de...