Publications, by year

@article{bdcc6010023,
  author = {Zhu, Tiange and Fournier-S’niehotta, Raphaël and Rigaux, Philippe and Travers, Nicolas},
  title = {A Framework for Content-Based Search in Large Music Collections},
  journal = {Big Data and Cognitive Computing},
  volume = {6},
  year = {2022},
  number = {1},
  article-number = {23},
  url = {https://www.mdpi.com/2504-2289/6/1/23},
  file = {/bibliography/files/ZhuFournierRigauxTravers-MusicSearch-BDCC22.pdf},
  issn = {2504-2289},
  doi = {10.3390/bdcc6010023},
  topic = {Musique}
}

We address the problem of scalable content-based search in large
              collections of music documents. Music content is highly complex
              and versatile and presents multiple facets that can be considered
              independently or in combination. Moreover, music documents can be
              digitally encoded in many ways. We propose a general framework for
              building a scalable search engine, based on (i) a music
              description language that represents music content independently
              from a specific encoding, (ii) an extendible list of
              feature-extraction functions, and (iii) indexing, searching, and
              ranking procedures designed to be integrated into the standard
              architecture of a text-oriented search engine. As a proof of
              concept, we also detail an actual implementation of the framework
              for searching in large collections of XML-encoded music scores,
              based on the popular ElasticSearch system. It is released as
              open-source in GitHub, and available as a ready-to-use Docker
              image for communities that manage large collections of digitized
              music documents.

@article{ismirLBD22-Zhu,
  file = {/bibliography/files/.pdf},
  author = {Zhu, Tiange and Fournier-S’niehotta, Raphaël and Rigaux, Philippe},
  title = {{Computation and visualization of differences between two XML
                 music score
                 files}},
  booktitle = {{23th International Society for Music
                 Information Retrieval Conference, ISMIR 2019 (Late-breaking Demo)}},
  year = {2022},
  status = {accepted},
  topic = {Musique},
  url = {https://ismir2022.ismir.net/program/lbd/}
}

@conference{arxiv.2211.16414,
  file = {/bibliography/files/TMLN-David-2211.16414.pdf},
  doi = {10.48550/ARXIV.2211.16414},
  url = {https://arxiv.org/abs/2211.16414},
  author = {David, Victor and Fournier-S'niehotta, Raphaël and Travers, Nicolas},
  keywords = {Artificial Intelligence (cs.AI), Social and Information Networks (cs.SI), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Parameterisation of Reasoning on Temporal Markov Logic Networks},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International},
  topic = {IA}
}

@conference{foscarin:hal-03300102,
  title = {{PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation}},
  author = {Foscarin, Francesco and Audebert, Nicolas and Fournier-S'Niehotta, Rapha{\"e}l},
  url = {https://hal.archives-ouvertes.fr/hal-03300102},
  booktitle = {{International Society for Music Information Retrieval Conference (ISMIR)}},
  address = {Online, India},
  year = {2021},
  month = nov,
  pdf = {https://hal.archives-ouvertes.fr/hal-03300102/file/PKSpell.pdf},
  file = {/bibliography/files/PKSpell-FoscarinAudebertFournier-ISMIR2021.pdf},
  hal_id = {hal-03300102},
  hal_version = {v1},
  topic = {Musique,IA}
}

@conference{DangWICE21,
  author = {Dang, Chen and Randrianarivo, Hicham and Fournier-S'niehotta, Rapha{\"{e}}l and Audebert, Nicolas},
  booktitle = {{GEM @ ECML-PKDD 21}},
  title = {{Web Image Context Extraction with Graph Neural Networks and Sentence Embeddings on the DOM tree}},
  year = {2021},
  month = sep,
  file = {/bibliography/files/GEM21-WICE-GNN-DOM.pdf},
  poster = {/bibliography/files/GEM21-WICE-GNN-DOM-poster.pdf},
  status = {accepted},
  topic = {Graphes,IA},
  url = {https://gem-ecmlpkdd.github.io/program/}
}

Web Image Context Extraction (WICE) consists in obtaining the textual information describing an image using the content of the surrounding webpage. A common preprocessing step before performing WICE is to render the content of the webpage. When done at a large scale (e.g., for search engine indexation), it may become very computationally costly (up to several seconds per page). To avoid this cost, we introduce a novel WICE approach that combines Graph Neural Networks (GNNs) and Natural Language Processing models. Our method relies on a graph model containing both node types and text as features. The model is fed through several blocks of GNNs to extract the textual context. Since no labeled WICE dataset with ground truth exists, we train and evaluate the GNNs on a proxy task that consists in finding the semantically closest text to the image caption. We then interpret importance weights to find the most relevant text nodes and define them as the image context. Thanks to GNNs, our model is able to encode both structural and semantic information from the webpage. We show that our approach gives promising results to help address the large-scale WICE problem using only HTML data.

@article{RAMACIOTTIMORALES202180,
  title = {Measuring diversity in heterogeneous information networks},
  journal = {Theoretical Computer Science},
  volume = {859},
  pages = {80-115},
  year = {2021},
  issn = {0304-3975},
  doi = {https://doi.org/10.1016/j.tcs.2021.01.013},
  url = {https://www.sciencedirect.com/science/article/pii/S0304397521000256},
  author = {{Ramaciotti Morales}, Pedro and Lamarche-Perrin, Robin and Fournier-S'niehotta, Raphaël and Poulain, Rémy and Tabourier, Lionel and Tarissan, Fabien},
  keywords = {Diversity measures, Heterogeneous information networks, Random walks on graphs, Recommender systems, Social network analysis},
  file = {/bibliography/files/Diversity-HIN-2020.pdf},
  topic = {Recommandation,Graphes}
}

Diversity is a concept relevant to numerous domains of research varying from ecology, to information theory, and to economics, to cite a few. It is a notion that is steadily gaining attention in the information retrieval, network analysis, and artificial neural networks communities. While the use of diversity measures in network-structured data counts a growing number of applications, no clear and comprehensive description is available for the different ways in which diversities can be measured. In this article, we develop a formal framework for the application of a large family of diversity measures to heterogeneous information networks (HINs), a flexible, widely-used network data formalism. This extends the application of diversity measures, from systems of classifications and apportionments, to more complex relations that can be better modeled by networks. In doing so, we not only provide an effective organization of multiple practices from different domains, but also unearth new observables in systems modeled by heterogeneous information networks. We illustrate the pertinence of our approach by developing different applications related to various domains concerned by both diversity and networks. In particular, we illustrate the usefulness of these new proposed observables in the domains of recommender systems and social media studies, among other fields.

@conference{RTF20asonam,
  author = {Ramaciotti-Morales, Pedro and Tabourier, Lionel and Fournier-S'niehotta, Rapha{\"{e}}l},
  booktitle = {{IEEE/ACM International Conference on Social Networks Analysis and Mining (ASONAM 2020)}},
  title = {{Testing the Impact of Semantics and Structure on Recommendation Accuracy and Diversity}},
  year = {2020},
  month = dec,
  file = {/bibliography/files/CRV-ASONAM-2020_paper_4.pdf},
  status = {accepted},
  topic = {Recommandation,Graphes},
  url = {https://web.ntpu.edu.tw/~myday/doc/ASONAM2020/ASONAM2020_Proceedings/pdf/index.html}
}

@article{VIARD2019127,
  file = {/bibliography/files/AugmentingCBRatingPredictionLinkStreamFeatures_ViardFournier_ComNet.pdf},
  title = {Augmenting content-based rating prediction with link stream features},
  journal = {Computer Networks},
  volume = {150},
  pages = {127 - 133},
  year = {2019},
  issn = {1389-1286},
  doi = {https://doi.org/10.1016/j.comnet.2018.12.002},
  url = {http://www.sciencedirect.com/science/article/pii/S1389128618313215},
  author = {Viard, T. and Fournier-S’niehotta, R.},
  keywords = {Link streams, Recommender systems, Interpretability, Temporal networks, Graphs},
  topic = {Recommandation,Graphes}
}

While graph-based collaborative filtering recommender systems have been introduced several years ago, there are still several shortcomings to deal with, the temporal information being one of the most important. The new link stream paradigm is aiming at extending graphs for correctly modelling the graph dynamics, without losing crucial information. We investigate the impact of such link stream features for recommender systems. We design link stream features, that capture the intrinsic structure and dynamics of the data. We show that such features encode a fine-grained and subtle description of the underlying system. We focused on a traditional recommender system context, the rating prediction on the MovieLens20M movie dataset and the Goodreads book dataset. We input link stream features along with some content-based ones into a gradient boosting machine (XGBoost) and show that itoutperforms significantly a sole content-based solution. These encouraging results call for further exploration of this original modelling and its integration to complete state-of-the-art recommender systems algorithms. Link streams and graphs, as natural visualizations of recommender systems, may offer more interpretability in a time when algorithm transparency is an increasingly important topic of discussion. We also hope that these results will sparkle interesting discussions in the community about the connections between link streams and traditional methods (matrix factorization, deep learning).

@conference{VF19,
  author = {Viard, Tiphaine and Fournier-S'niehotta, Rapha{\"{e}}l},
  booktitle = {{LEG @ ECML-PKDD 19}},
  title = {{Encoding temporal and structural information in machine learning models for recommandation}},
  year = {2019},
  month = sep,
  file = {/bibliography/files/Encoding_temporal_and_structural_information_in_machine_learning_models_for_recommandation.pdf},
  status = {accepted},
  topic = {Recommandation,Graphes},
  url = {https://leg-ecmlpkdd19.loria.fr/index.php%3Faction=program.html}
}

@conference{FJF19,
  author = {Foscarin, Francesco and Fournier-S'niehotta, Rapha{\"{e}}l and Jacquemard, Florent},
  booktitle = {{6th International Conference on Digital Libraries for Musicology (DLfM 2019)}},
  title = {{A diff procedure for XML music score files}},
  year = {2019},
  month = nov,
  file = {/bibliography/files/DLfM_2019_paper_13.pdf},
  status = {accepted},
  topic = {Musique},
  url = {https://dlfm.web.ox.ac.uk/2019-programme}
}

@conference{FJF19b,
  author = {Foscarin, Francesco and Fournier-S'niehotta, Rapha{\"{e}}l and Jacquemard, Florent},
  booktitle = {{20th International Society for Music
                 Information Retrieval Conference, ISMIR 2019 (Late-breaking Demo)}},
  title = {{Computation and visualization of differences between two XML
                 music score
                 files}},
  year = {2019},
  status = {accepted},
  topic = {Musique},
  url = {https://ismir2019.ewi.tudelft.nl/?q=lbd},
  file = {/bibliography/files/DiffScores-FoscarinJacquemardFournier-IsmirLBD19.pdf}
}

@conference{VFLM18,
  author = {Viard, Tiphaine and Fournier, Rapha{\"{e}}l and Magnien, Clémence and Latapy, Matthieu},
  booktitle = {{(CompleNet'18) International Workshop on Complex Networks}},
  title = {{Discovering Patterns of Interest in IP Traffic Using Cliques in Bipartite Link Streams}},
  year = {2018},
  month = mar,
  doi = {https://doi.org/10.1007/978-3-319-73198-8_20},
  file = {/bibliography/files/PatternsInterestIPTrafficCliquesBipartiteLinkStreamsViardFournierMagnienLatapy_CompleNet2018.pdf},
  url = {https://link.springer.com/chapter/10.1007/978-3-319-73198-8_20},
  topic = {Graphes,Réseau}
}

@book{dunodL1,
  author = {Delacroix, Joëlle and Barthélémy, François and Fournier-S'niehotta, Raphaël and Gil-Michalon, Isabelle and Lambert, Amélie and Plateau, Agnès and Rovédakis, Stéphane and Simonot, Marianne and Thion, Virginie and Waymel, Emmanuel},
  publisher = {Dunod},
  title = {Informatique},
  year = {2017},
  address = {Paris},
  edition = {1e},
  isbn = {3257227892},
  month = jun,
  series = {Fluoresciences},
  url = {https://www.dunod.com/sciences-techniques/informatique}
}

@article{FRT17,
  author = {Fournier-S'niehotta, R. and Rigaux, P. and Travers, N.},
  journal = {(IS'18) Information Systems},
  title = {{Modeling Music as Synchronized Time Series: Application to Music Score Collections}},
  year = {2017},
  pages = {1--36},
  doi = {10.1016/j.is.2017.12.003},
  file = {:/bibliography/files/ModelingMusicSynchronizedTimeSeriesApplicationMusicScoreCollections_FournierSniehottaTraversRigaux_IS17.pdf:},
  url = {https://doi.org/10.1016/j.is.2017.12.003},
  topic = {Musique}
}

Music is a temporal organization of sounds, and we can therefore assume that any music representation has a structure that reflects some conceptual principles. This structure is hardly explicitly accessible in many encodings, such as, for instance, audio files. However, it appears much more clearly in the language of music notation.

We propose to use the music notation language as a framework to model and manipulate the content of digital music objects, whatever their specific encoding may be. We describe an algebra that relies on this structured music representation to extract, restructure, and search such objects. The data model leverages the hidden structure of digital music encodings to enable powerful manipulations of their content.

We apply the model to collections of music scores. We describe a system, based
on an extension of XQuery with our algebra, that provides search,
reorganization, and extraction functionalities on top of large collections of
XML-encoded digital scores. Beyond its application to music objects, our work
shows how one can rely on a structured content embedded in a complex XML
encoding to develop robust collection management tools with minimal
implementation effort.

@conference{GaumontVFWL15,
  author = {Gaumont, No\'e and Viard, Tiphaine and Fournier, Rapha{\"{e}}l and Wang, Quina and Latapy, Matthieu},
  booktitle = {Complex Networks {VII} - Proceedings of the 7th Workshop on Complex Networks CompleNet 2016, Dijon, France, March 23-25, 2016},
  title = {Analysis of the temporal and structural features of threads in a mailing-list},
  year = {2016},
  doi = {https://doi.org/10.1007/978-3-319-30569-1_8},
  file = {/bibliography/files/AnalysisTemporalStructuralFeaturesMLThreads_GaumontViardFournierWangLatapy_CompleNet2016.pdf},
  url = {https://doi.org/10.1007/978-3-319-30569-1_8},
  topic = {Graphes}
}

A link stream is a collection of triplets (t, u, v) indicating
      that an interaction occurred between u and v at time t. Link streams model
      many real-world situations like email exchanges between individuals,
      connections between devices, and others. Much work is currently devoted to
      the generalization of classical graph and network concepts to link
      streams. In this paper, we generalize the existing notions of
      intra-community density and inter-community density. We focus on emails
      exchanges in the Debian mailing-list and show that threads of emails, like
      communities in graphs, are dense subsets loosely connected from a link
      stream perspective.

@conference{Fournier_tenor2016,
  author = {Fournier-S'niehotta, R. and Rigaux, Philippe and Travers, Nicolas},
  booktitle = {Proceedings of the International Conference on Technologies for Music Notation and Representation -- TENOR'16},
  title = {Is There a Data Model in Music Notation?},
  year = {2016},
  address = {Cambridge, UK},
  editor = {Hoadley, Richard and Nash, Chris and Fober, Dominique},
  month = may,
  pages = {85--91},
  publisher = {Anglia Ruskin University},
  file = {/bibliography/files/IsThereDataModelMusicNotation_FournierSniehottaTraversRigaux_Tenor16.pdf},
  isbn = {978-0-9931461-1-4},
  url = {http://tenor2016.tenor-conference.org},
  topic = {Musique}
}

Scores are structured objects, and we can therefore envisage operations that change the structure of a score, combine several scores, and produce new score instances from some pre-existing material. Current score encodings, however, are designed for rendering and exchange purposes, and cannot directly be exploited as instances of a clear data model supporting algebraic manipulations. We propose an approach that leverages a music content model hidden in score notation, and define a set of composable operations to derive new "scores" from a corpus of existing ones. We show that this approach supplies a high-level tool to express common, useful applications, can easily be implemented on top of standard components, and finally gives rise to interesting conceptual issues related to the modeling of music notation.

@conference{FRT16b,
  author = {Fournier-S'niehotta, R. and Rigaux, P. and Travers, N.},
  booktitle = {{(JIM'16) Journées d'Informatique Musicale}},
  title = {{Vers un Traitement Algébrique de la Notation Musicale}},
  year = {2016},
  address = {Albi, France},
  month = mar,
  pages = {1-9},
  volume = {23},
  file = {/bibliography/files/VersTraitementAlgebriqueNotationMusicale_FournierSniehottaTraversRigaux_JIM2016.pdf},
  url = {http://jim2016.gmea.net/actes},
  topic = {Musique}
}

@conference{FRT16,
  author = {Fournier-S'niehotta, R. and Rigaux, P. and Travers, N.},
  booktitle = {{(MEC'16) Music Encoding Conference}},
  title = {{A Digital Score Library Based on MEI}},
  year = {2016},
  address = {Montréal, Canada},
  month = may,
  note = {{\url{https://music-encoding.org/community/conference/}}},
  pages = {1-4},
  topic = {Musique}
}

@conference{DBLP:conf/time/Fournier-Sniehotta16,
  file = {/bibliography/files/QueryingMusicNotation_FournierSniehottaTraversRigaux_TIME16.pdf},
  author = {Fournier-S'niehotta, R. and Rigaux, Philippe and Travers, Nicolas},
  title = {Querying Music Notation},
  booktitle = {23rd International Symposium on Temporal Representation and Reasoning,
                 {TIME} 2016, Kongens Lyngby, Denmark, October 17-19, 2016},
  pages = {51--59},
  year = {2016},
  url = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7774233},
  doi = {10.1109/TIME.2016.13},
  biburl = {https://dblp.org/rec/bib/conf/time/Fournier-Sniehotta16},
  editor = {Dyreson, Curtis E. and Hansen, Michael R. and Hunsberger, Luke},
  publisher = {IEEE},
  isbn = {978-1-5090-3825-1},
  timestamp = {Tue, 13 Dec 2016 11:03:16 +0100},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  topic = {Musique}
}

@conference{DBLP:conf/ismir/Fournier-Sniehotta16,
  file = {/bibliography/files/QueryingXMLScoreDatabasesXQueryNotEnough_FournierSniehottaTraversRigaux_ISMIR16.pdf},
  author = {Fournier-S'niehotta, Raphaël and Rigaux, Philippe and Travers, Nicolas},
  title = {Querying {XML} Score Databases: XQuery is not Enough!},
  booktitle = {Proceedings of the 17th International Society for Music Information
                 Retrieval Conference, {ISMIR} 2016, New York City, United States,
                 August 7-11, 2016},
  pages = {723--729},
  year = {2016},
  url = {https://wp.nyu.edu/ismir2016/wp-content/uploads/sites/2294/2016/07/136\_Paper.pdf},
  timestamp = {Thu, 08 Sep 2016 13:32:51 +0200},
  biburl = {https://dblp.org/rec/bib/conf/ismir/Fournier-Sniehotta16},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  editor = {Mandel, Michael I. and Devaney, Johanna and Turnbull, Douglas and Tzanetakis, George},
  isbn = {978-0-692-75506-8},
  topic = {Musique}
}

@article{FournierL15,
  author = {Fournier, Raphaël and Latapy, Matthieu},
  journal = {International Journal of Internet Science},
  title = {Temporal Patterns of Pedophile Activity in a {P2P} Network: First Insights about User Profiles from Big Data},
  year = {2015},
  issn = {1662-5544},
  number = {1},
  pages = {8--19},
  volume = {10},
  file = {/bibliography/files/TemporalPattersPedoActP2P_Fournier-Latapy_IJIS2015.pdf},
  url = {http://www.ijis.net/ijis_inpress/ijis_inpress_Fournier_and_Latapy_pre.html},
  topic = {Antipedo}
}

Recent studies have shown that child abuse material is shared
    through peer-to-peer (P2P) networks, which allow users to exchange files
    without a central server. Obtaining knowledge on the extent of this
    activity has major consequences for child protection, policy making and
    Internet regulation. Previous works have developed tools and analyses to
    provide overall figures in temporally-limited measurements. Offenders’
    behavior is mostly studied through small-scale interviews and there is few
    information on the times at which they engage in such activity. Here we
    show that the proportion of search-engine queries for pedophile content
    gradually has grown by a factor of almost 3 in three years. We also find
    that during the day, certain hours are, on average, privileged by seekers.
    Our results demonstrate that P2P networks are actively used to search for
    pedophile content and we find new and large-scale results on pedophile
    offenders’ profile, indicating that a substantial proportion is
    well-integrated into family life and professional work activities.

@article{FournierCLCMDF14,
  file = {/bibliography/files/ComparingPaedoActP2P_FournierCholezLatapyMagnienChrismentDaniloffFestor.pdf},
  title = {Comparing paedophile activity in different {P2P} systems},
  author = {Fournier, Raphaël and Cholez, Thibault and Latapy, Matthieu and Chrisment, Isabelle and Magnien, Clémence and Daniloff, Ivan and Festor, Olivier},
  journal = {Social Sciences},
  volume = {3},
  year = {2014},
  number = {3},
  url = {\url{http://www.mdpi.com/2076-0760/3/3/314}},
  issn = {2076-0760},
  doi = {10.3390/socsci3030314},
  topic = {Antipedo,Réseau}
}

Peer-to-peer (P2P) systems are widely used to exchange content
    over the Internet. Knowledge of pedophile activity in such networks remains
    limited, despite having important social consequences. Moreover, though
    there are different P2P systems in use, previous academic works on this
    topic focused on one system at a time and their results are not directly
    comparable. We design a methodology for comparing KAD and eDonkey, two P2P
    systems among the most prominent ones and with different anonymity levels.
    We monitor two eDonkey servers and the KAD network during several days and
    record hundreds of thousands of keyword-based queries. We detect
    pedophile-related queries with a previously validated tool and we propose,
    for the first time, a large-scale comparison of pedophile activity in two
    different P2P systems. We conclude that there are significantly fewer
    pedophile queries in KAD than in eDonkey (approximately 0.09% vs. 0.25%).

@conference{FournierViennet14,
  author = {Fournier, Raphaël and Viennet, Emmanuel},
  booktitle = {Apprentissage Artificiel et Fouille de Donn{\'{e}}es, {AAFD} 2014, Universit{\'{e}} Paris 13, Institut Galil{\'{e}}e, Villetaneuse, France, 29-30 avril 2014},
  title = {AMMICO : recommandation sociale pour la visite de musée},
  year = {2014},
  file = {/bibliography/files/AMMICO-AAFD-FournierViennet.pdf},
  topic = {Recommandation}
}

Nous présentons les techniques de recommandations mises en œuvre pour la plateforme AMMICO qui permet une visite de musées enrichie. Nous proposons diverses techniques de recommandations reposant sur l’analyse de graphes sociaux afin de répondre aux problématiques spécifiques de la visite de musées.

@conference{FournierD14,
  author = {Fournier, Raphaël and Danisch, Maximilien},
  booktitle = {IEEE 8th International Conference on Research Challenges in Information Science, RCIS 2014, Marrakech, Morocco, May 28-30, 2014},
  title = {Mining bipartite graphs to improve semantic paedophile activity detection},
  year = {2014},
  pages = {1--4},
  biburl = {\url{http://dblp.uni-trier.de/rec/bib/conf/rcis/FournierD14}},
  doi = {10.1109/RCIS.2014.6861035},
  file = {/bibliography/files/Mining-RCIS2014-FournierDanisch.pdf},
  url = {\url{http://dx.doi.org/10.1109/RCIS.2014.6861035}},
  topic = {Antipedo}
}

Peer-to-peer (P2P) networks are a popular method to exchange
    large volume of data through the Internet. Pedophile activity is a very
    important topic for our societies and some works have recently attempted
    to gauge the extent of pedophile exchanges on P2P networks. A key issue is
    to obtain an efficient detection tool, which may decide if a sequence of
    keywords is related to the topic or not. 

    We propose to use the analysis of the social network bipartite graph in a
    large dataset from a P2P network to improve a state-of-the-art filter for
    pedophile queries. We obtain queries and thus combinations of words which
    were not tagged by the filter but should be. We also perform some
    experiments to see if the original four categories of paedophile queries
    were observable by topological measures only.

@article{BernardesDFFV14,
  author = {Bernardes, Daniel and Diaby, Mamadou and Fournier, Rapha{\"{e}}l and Fogelman{-}Souli{\'{e}}, Fran{\c{c}}oise and Viennet, Emmanuel},
  journal = {SIGKDD Explorations},
  title = {A Social Formalism and Survey for Recommender Systems},
  year = {2014},
  number = {2},
  pages = {20--37},
  volume = {16},
  bibsource = {dblp computer science bibliography, http://dblp.org},
  biburl = {\url{http://dblp.uni-trier.de/rec/bib/journals/sigkdd/BernardesDFFV14}},
  doi = {10.1145/2783702.2783705},
  file = {/bibliography/files/SocialFormalismSurveyRS-BernardesDiabyFournierViennetFogelman.pdf},
  timestamp = {Tue, 23 Jun 2015 10:19:35 +0200},
  url = {\url{http://doi.acm.org/10.1145/2783702.2783705}},
  topic = {Recommandation}
}

We present a general formalism for Recommender Systems based on
    Social Network Analysis. After introducing the classical categories of
    recommender systems, we present our Social Filtering formalism and show
    that it extends association rules, classical Collaborative Filtering and
    Social Recommendation, while providing additional possibilities. This
    allows us to survey the literature and illustrate the versatility of our
    approach on various publicly available datasets, comparing our results
    with the literature.

@article{LatapyMF13,
  author = {Latapy, Matthieu and Magnien, Cl{\'e}mence and Fournier, Rapha{\"e}l},
  journal = {Information Processing and Management},
  title = {Quantifying paedophile activity in a large P2P system},
  year = {2013},
  number = {1},
  pages = {248--263},
  volume = {49},
  biburl = {\url{http://dblp.uni-trier.de/rec/bib/journals/ipm/LatapyMF13}},
  doi = {10.1016/j.ipm.2012.02.008},
  file = {/bibliography/files/ipm.pdf},
  timestamp = {Fri, 30 Nov 2012 10:28:44 +0100},
  url = {\url{http://dx.doi.org/10.1016/j.ipm.2012.02.008}},
  topic = {Antipedo}
}

Increasing knowledge of paedophile activity in P2P systems is a
    crucial societal concern, with important consequences on child protection,
    policy making, and internet regulation. Because of a lack of traces of P2P
    exchanges and rigorous analysis methodology, however, current knowledge of
    this activity remains very limited. We consider here a widely used P2P
    system, eDonkey, and focus on two key statistics: the fraction of
    paedophile queries entered in the system and the fraction of users who
    entered such queries. We collect hun- dreds of millions of keyword-based
    queries; we design a paedophile query detection tool for which we
    establish false positive and false negative rates using assessment by
    experts; with this tool and these rates, we then estimate the fraction of
    paedophile queries in our data; finally, we design and apply methods for
    quantifying users who entered such queries. We conclude that approximately
    0.25% of queries are paedophile, and that more than 0.2% of users enter
    such queries. These statistics are by far the most precise and reliable
    ever obtained in this domain.

@phdthesis{Fournier-Sniehotta2012,
  file = {/bibliography/files/These_FournierRaphael_vfinale.pdf},
  title = {Détection et analyse d'une thématique rare dans de grands ensembles
      de requêtes : l'activité pédophile dans le {P2P}},
  author = {Fournier-S'niehotta, Raphaël},
  year = {2012},
  school = {UPMC},
  topic = {Antipedo},
  url = {https://tel.archives-ouvertes.fr/tel-02444174}
}

@conference{LatapyMF11,
  author = {Latapy, Matthieu and Magnien, Cl{\'e}mence and Fournier, Rapha{\"e}l},
  booktitle = {INFOCOM 2011. 30th IEEE International Conference on Computer Communications, Joint Conference of the IEEE Computer and Communications Societies, 10-15 April 2011, Shanghai, China},
  title = {Quantifying paedophile queries in a large {P2P} system},
  year = {2011},
  pages = {401--405},
  publisher = {IEEE},
  bibsource = {dblp computer science bibliography, http://dblp.org},
  biburl = {\url{http://dblp.uni-trier.de/rec/bib/conf/infocom/LatapyMF11}},
  doi = {10.1109/INFCOM.2011.5935191},
  file = {/bibliography/files/InfocomMC11_LatapyMagnienFournier_QuantifyingPaedophileQueriesP2P.pdf},
  isbn = {978-1-4244-9921-2},
  timestamp = {Mon, 26 Jan 2015 16:54:55 +0100},
  url = {\url{http://dx.doi.org/10.1109/INFCOM.2011.5935191}},
  topic = {Antipedo}
}

Increasing knowledge of paedophile activity in P2P systems is a
    crucial societal concern, with important consequences on child protection,
    policy making, and internet regulation. Because of a lack of traces of P2P
    exchanges and rigorous analysis methodology, however, current knowledge of
    this activity remains very limited. We consider here a widely used P2P
    system, eDonkey, and focus on two key statistics: the fraction of
    paedophile queries entered in the system and the fraction of users who
    entered such queries. We collect hun- dreds of millions of keyword-based
    queries; we design a paedophile query detection tool for which we
    establish false positive and false negative rates using assessment by
    experts; with this tool and these rates, we then estimate the fraction of
    paedophile queries in our data; finally, we design and apply methods for
    quantifying users who entered such queries. We conclude that approximately
    0.25% of queries are paedophile, and that more than 0.2% of users enter
    such queries. These statistics are by far the most precise and reliable
    ever obtained in this domain.