Alert button
Picture for Bernard Jacquemin

Bernard Jacquemin

Alert button


Receiving an algorithmic recommendation based on documentary filmmaking techniques

Sep 08, 2023
Samuel Gantier, Ève Givois, Bernard Jacquemin, Bouchra Atbane-El Houadi

This article analyzes the reception of a novel algorithmic recommendation of documentary films by a panel of moviegoers of the T{\"e}nk platform. In order to propose an alternative to recommendations based on a thematic classification, the director or the production period, a set of metadata has been elaborated within the framework of this experimentation in order to characterize the great variety of ``documentary filmmaking dispositifs'' . The goal is to investigate the different ways in which the platform's film lovers appropriate a personalized recommendation of 4 documentaries with similar or similar filmmaking dispositifs. To conclude, the contributions and limits of this proof of concept are discussed in order to sketch out avenues of reflection for improving the instrumented mediation of documentary films.

* Revue fran{\c c}aise des sciences de l'information et de la communication, 2023, 26  
* in French language 
Viaarxiv icon

Corpus sp{é}cialis{é} et ressource de sp{é}cialit{é}

Jun 19, 2015
Bernard Jacquemin, Sabine Ploux

Figure 1 for Corpus sp{é}cialis{é} et ressource de sp{é}cialit{é}
Figure 2 for Corpus sp{é}cialis{é} et ressource de sp{é}cialit{é}

"Semantic Atlas" is a mathematic and statistic model to visualise word senses according to relations between words. The model, that has been applied to proximity relations from a corpus, has shown its ability to distinguish word senses as the corpus' contributors comprehend them. We propose to use the model and a specialised corpus in order to create automatically a specialised dictionary relative to the corpus' domain. A morpho-syntactic analysis performed on the corpus makes it possible to create the dictionary from syntactic relations between lexical units. The semantic resource can be used to navigate semantically - and not only lexically - through the corpus, to create classical dictionaries or for diachronic studies of the language.

* Appears in Fran\c{c}ois Maniez; Pascaline Dury; Nathalie Arlin; Claire Rougemont. Corpus et dictionnaires de langues de sp{\'e}cialit{\'e}, Presses Universitaires de Granoble, pp.197-212, 2008  
* 16 pages, in French 
Viaarxiv icon

Du corpus au dictionnaire

Jan 26, 2009
Bernard Jacquemin, Sabine Ploux

Figure 1 for Du corpus au dictionnaire
Figure 2 for Du corpus au dictionnaire

In this article, we propose an automatic process to build multi-lingual lexico-semantic resources. The goal of these resources is to browse semantically textual information contained in texts of different languages. This method uses a mathematical model called Atlas s\'emantiques in order to represent the different senses of each word. It uses the linguistic relations between words to create graphs that are projected into a semantic space. These projections constitute semantic maps that denote the sense trends of each given word. This model is fed with syntactic relations between words extracted from a corpus. Therefore, the lexico-semantic resource produced describes all the words and all their meanings observed in the corpus. The sense trends are expressed by syntactic contexts, typical for a given meaning. The link between each sense trend and the utterances used to build the sense trend are also stored in an index. Thus all the instances of a word in a particular sense are linked and can be browsed easily. And by using several corpora of different languages, several resources are built that correspond with each other through languages. It makes it possible to browse information through languages thanks to syntactic contexts translations (even if some of them are partial).

* Cahiers de Linguistique. Revue de sociolinguistique et de sociologie de la langue fran\c{c}aise 33, 1 (2008) 63-84  
Viaarxiv icon

Interroger un corpus par le sens

May 31, 2008
Bernard Jacquemin

In textual knowledge management, statistical methods prevail. Nonetheless, some difficulties cannot be overcome by these methodologies. I propose a symbolic approach using a complete textual analysis to identify which analysis level can improve the the answers provided by a system. The approach identifies word senses and relation between words and generates as many rephrasings as possible. Using synonyms and derivative, the system provides new utterances without changing the original meaning of the sentences. Such a way, an information can be retrieved whatever the question or answer's wording may be.

* Dans "Mots, termes et contextes", Actes des septi\`emes Journ\'ees scientifiques du r\'eseau de chercheurs Lexicologie, Terminologie, Traduction - Bruxelles : Belgique (2005)  
* 13 pp 
Viaarxiv icon

Managing conflicts between users in Wikipedia

May 30, 2008
Bernard Jacquemin, Aurélien Lauf, Céline Poudat, Martine Hurault-Plantet, Nicolas Auray

Figure 1 for Managing conflicts between users in Wikipedia
Figure 2 for Managing conflicts between users in Wikipedia
Figure 3 for Managing conflicts between users in Wikipedia
Figure 4 for Managing conflicts between users in Wikipedia

Wikipedia is nowadays a widely used encyclopedia, and one of the most visible sites on the Internet. Its strong principle of collaborative work and free editing sometimes generates disputes due to disagreements between users. In this article we study how the wikipedian community resolves the conflicts and which roles do wikipedian choose in this process. We observed the users behavior both in the article talk pages, and in the Arbitration Committee pages specifically dedicated to serious disputes. We first set up a users typology according to their involvement in conflicts and their publishing and management activity in the encyclopedia. We then used those user types to describe users behavior in contributing to articles that are tagged by the wikipedian community as being in conflict with the official guidelines of Wikipedia, or conversely as being well featured.

* Dans BIS 2008 Workshop proceedings - 11th Conference on Business Information Systems (BIS 2008), Social Aspects of the Web Workshop (SAW 2008), Innsbruck : Autriche (2008)  
* 12 pp 
Viaarxiv icon

La fiabilité des informations sur le web

May 30, 2008
Bernard Jacquemin, Aurélien Lauf, Céline Poudat, Martine Hurault-Plantet, Nicolas Auray

Online IR tools have to take into account new phenomena linked to the appearance of blogs, wiki and other collaborative publications. Among these collaborative sites, Wikipedia represents a crucial source of information. However, the quality of this information has been recently questionned. A better knowledge of the contributors' behaviors should help users navigate through information whose quality may vary from one source to another. In order to explore this idea, we present an analysis of the role of different types of contributors in the control of the publication of conflictual articles.

* Dans Actes de la Conf\'erence en Recherche d'Information et Applications CORIA 2008 - Conf\'erence en Recherche d'Information et Applications 2008, Tr\'egastel : France (2008)  
* 8 pp 
Viaarxiv icon