My name is Jean-Valère Cossu coming from Corsica. Since 2017 January, I work at My Local Influence as Data Product Owner after 3 years as a Research Engineer. My main concerns deal with Online Reputation Management for businesses. Before, for about 1 year, I left my Research Engineer position at Vodkaster where I mainly worked on recommender systems within the ANR (French National Research Agency) funded project ALICIA. I also had interets in Data Science, Networking (Streaming) and Multimedia encoding. I obtained my Ph.D in Computer Science on E-Reputation Monitoring in the Computer Science Laboratory (LIA) at Avignon University (France) under the supervision of Professor Marc El-Bèze, Dr. Juan-Manuel Torres-Moreno and Dr. Eric SanJuan. My research interests lie in online reputation management (ORM) for companies and politics in both Natural Language Processing (NLP), Information Retrieval (IR) and Social Network Analysis (SNA) fields. I am also interested in digital humanities and links between data and ethics. My work was mainly focused on the border of Machine Learning (ML) between classification and clustering using documents shared on the Web 2.0 (Blogs and Twitter) and their associated metadata. Before I came to the NLP and Speech team of the LIA, I received my master degree in Computer Science with networks specializing at the University of Avignon (2010 - 2012). During my internship at the Lab I worked on opinion mining in recommender systems with Professor Marc El-Bèze. Based on a "cinema" social network (Vodkaster) the issues were to analyse the (dis)likes of users in order to predict their opinion on new-coming movies. I also got a background in Networking management. I gave various courses in computer science at the University of Avignon: Networking, C/C++ and Java (Networking) programming, Internet Engineering. I was associate supervisor for master students' project over deep neural networks in reputation analysis. I also was associate supervisor for master student internship over Partial Mean Square Path Modelling (PLS-PM) in football betting. |
|
Tweets by jvcossu |
Research Topics Vodkaster/ALICIA Project Imagiweb Evaluation Campaigns Ph.D. thesis Master thesis Research Topics
Vodkaster/ALICIAAt Vodkaster I was mainly working on movies recommender systems within the ALICIA (ANR-13-CORD-0020) project. My work mainly consisted in studying features to improves recommendation. It also included modelling and analysis dynamics of movies reputation on the website. My research area also included Network broadcasting and Video coding. I am also interested in modellig and improving customers' satisfaction within network analysis. Ph.D. ThesisSubject: Analysing entities web representation over Web 2.0 PhD Supervisor: Marc El-Bèze, Juan-Manuel Torres-Moreno and Eric Sanjuan My main work consists in is about entities reputation representation identification. There are two major intentions: analyse and visualisation. The web and politics context add difficulties to the analyse side. On the web there many bias, the first one could be that the web is offering more coverage to negative messages. Politics is like shifting and people can easily change their opinion and each new fact become an emerging concept. When it comes to modeling of the reputation the contexts add other difficulties such as the point-of-view and how to estimate the right (temporal) window. The project includes different working parts, from manual annotation with domain experts to machine learning with automatic annotation and clustering. Imagiweb ProjectThis project is highly related to the domain of Sentiment Analysis, and more specifically to Opinion Mining. The main idea is to detect “what people think about a given entity” from documents content. This idea is usually implemented within a more realistic task: classifying the opinion expressed about something into a set of predefined polarities (e.g., positive vs. negative or neutral). The nature of vocabulary used in tweets limits the use of existing Sentiment Lexicon. This project also aims to study on which aspect of the entity the opinion was expressed. Although it could be seen as Topic Detection it is harder since the topic set has been defined by experts as a concept level which may never be seen in the contents. Politics has already been addressed in previous works but mostly in English that deals with the US politics and rarely with the precision expected in the project. Furthermore, a dataset built with the involvement of specialists in political science will be provided to the community. Within the Imagiweb project my work consists in modelling and analysis dynamics of web reputation. Our objectives aim to help politics researchers and communication-team of the French main electric utility company (EDF) by proposing them tools that can provide automatic topic and opinion annotation on documents dealing with their reputation (tweets about politicians and about the “EDF” entity). The project covers several issue such as Active Learning, Natural Language Processing in Big Data Mining. My research activities cover document clustering and categorization using several Machine Learning methods. I also studies the impact of external features in the retweet behaviour. Evaluation CampaignsRepLab'2014 RepLab 2014 provides a extension to RepLab 2013 tasks. It focused on stress categorization task (using Reputation Standards from the RepTrack Framework) and the characterization of Twitter profiles (Author Profiling) as a complement to CLEF PAN challenge. We tried to tackle both problems with statistical NLP-based classifiers with the simplicity and re-usability philosophy considering a matching dogma as mainstream process. We obtained competitive results in Author Profiling subtasks. The Reputation Dimensions classification task looks like the Topic Categorization aspect of the Imagiweb project that's why we made further experiments My work consisted in team management and participation to all subtasks. RepLab'2013 RepLab 2013 is an evaluation challenge focusing on the problem of monitoring the reputation of entities in Twitter. It consists in several tasks such as entity name disambiguation (Is the tweet about the entity?), reputation's polarity detection (Does the tweet have positive or negative implications for the entity’s reputation?), topic detection (What is the issue relative to the entity is discussed in the tweet?) and topic ranking (Is the topic a reputation alert that deserves immediate attention?). The provided dataset contained tweets in two languages: English and Spanish. We mainly tried to investigate how much Speech Recognition and Information Retrieval systems can answer the issues in a reputation management context (filtering and polarity tasks 1 and 2) and how simple NLP-based classifiers can perform over ranking and clustering tasks (task 3 and 4). We obtained competitive results in each subtasks. My work consisted in team management, merging all systems and of course participation to several subtasks with my own ideas. Deft’2013 Deft 2013 edition addressed a new application domain on a theme that has been studied in an evaluation campaign in the past (Computer Cooking Contest): cooking recipes. We focused on two analysis functions in DEFT2013, document classification (task 1 to 3) and information extraction (task 4), in a speciality domain. My participation consisted to be a expert annotator to evaluate subsets of systems submission as if we were in an active learning process. Master ThesisSubject: Opinion mining in a movie recommender system This Master thesis studies an opinion mining system over a movies social network. This method relies on Natural Language Processing over the users reviews. Several aspects were covered, from the user point-of-view: what does he like or dislike in movies and from the movie side: what the main target of the movie. This analyse is used to propose an argued movie recommendation for each user. |
CLEF MC2 2018 lab overview
Journal
Hajjem M., Cossu J-V., Latiri C., SanJuan E. 9th International Conference of the CLEF initiative, Avignon (France) September 10-14 2018 Lexical Context for Profiling Reputation of Corporate EntitiesCossu J-V. and Ermakova L. 19th International Conference on Enterprise Information Systems (ICEIS), Porto (Portugal) April 26-29 2017 Multi-Dimensional Reputation Modeling using Micro Blog contentsCossu J-V., San-Juan E., Torres-Moreno, J. M and El-Bèze M. 22nd International Symposium on Methodologies for Intelligent Systems, Lyon (France) October 21-23 2015 Detecting Real-World Influence Through TwitterCossu J-V., Dugue N. and Labatut V. The Second European Network Intelligence Conference, Karlskrona (Sweden) September 21-22 2015 NLP-based classifiers to generalize experts assessments in E-ReputationCossu J-V., Ferreira E., Gaillard J., Janod K. and El-Bèze M. Sixth International Conference of the CLEF initiative, Toulouse (France) September 8-11 2015 Automatic Classification and PLS-PM Modeling for Profiling Reputation of Corporate Entities on TwitterCossu J-V., San-Juan E., Torres-Moreno, J. M and El-Bèze M. 20th International Conference on Application of Natural Language to Information Systems (NLDB 2015), Passau (Germany) June 17-19 2015 An opinion mining Partial Least Square Path Modeling for football bettingEl Hamdaoui M. and Cossu J-V. PhD Session of the 7th European Conference on Machine Learning and Practice of Knowledge Discovery in Databases, Nancy (France) September 15-19 2014 Towards the improvement of topic priority assignment using various topic detection methods for e-reputation monitoring on TwitterCossu J-V., Bigot B., Bonnefoy L. and Senay G. 19th International Conference on Application of Natural Language to Information Systems (NLDB 2014), Montpellier (France) June 18-20 2014 A survey on evaluation of summarization methods Ermakova L., Cossu J-V. and Mothe J. Information Processing & Management Information Processing & Management 56 (5) Un modèle éditorial du troisième typeSire G., JV Cossu J-V. and Sonet V. Questions de communication Questions de communication 2018 (1) Active learning in annotating micro-blogs dealing with e-reputation on TwitterCossu J.-V, Molina A. and Tello-Signoret M. Journal of Interdisciplinary Methodologies and Issues in Science A review of features for the discrimination of twitter users: application to the prediction of offline influenceCossu J-V., Labatut V. and Dugue N. Social Network Analysis and Mining : SI Diffusion of Information and Influence in Social Networks Special Issue on Diffusion of Information and Influence in Social Networks (2016), 10.1007/s13278-016-0329-x Intweetive Text SummarizationCossu J-V., Torres-Moreno, J. M, San-Juan E. and El-Bèze M. International Journal of Computational Linguistics and Applications Vol. 7 No. 1, 2016 Bilingual and Cross Domain Politics AnalysisCossu J.-V, Abascal R., Molina A., Torres-Moreno, J. M. and SanJuan, E. Research in Computing Science (ISSN 1870-4069) Issue 85 (2014), page 9–19 Machine Learned Annotation of tweets about politicians' reputation during Presidential Elections: the cases of Mexico and France Cossu J.-V, Abascal R., Molina A., Torres-Moreno, J. M. and SanJuan, E. Bilingual and Cross Domain Politics AnalysisCossu J.-V, Abascal R., Molina A., Torres-Moreno, J. M. and SanJuan, E. Avances en la Ingeniería del Lenguaje y del Conocimiento 2nd International Symposium on Language & Knowledge Engineering, Puebla (Mexico) 4-5 December 2014 CLEF MC2 Lab: Évaluation, Résultats, et Perspectives. Hajjem M., Cossu J-V., Latiri C., SanJuan E. CORIA 2019 , Lyon (France) March 25-27 2019 Pour tout (sa) voir, cliquez ici!” Cinéphilie de niche, forums spécialisés, et stratégies de prescription des films sur InternetMoschenross A., F Gimello-Mesplomb F. and Cossu J-V colloque" La prescription culturelle en question", , Dijon (France) April 5-7 2017 Etude de l'image de marque d'entités dans le cadre d'une plateforme de veille sur le Web socialKhouas L., Brun C., Peradotto A., Cossu J-V., Boyadjian J. and Velcin J. 22ème Conférence sur le Traitement Automatique des Langues Naturelles, (DEFT/TALN 2013), Caen (France) June 22-25 2015 Recherche et utilisation d'entités nommées conceptuelles dans une tâche de catégorisationCossu J-V., Torres-Moreno J-M. and El-Bèze M. 20ème Conférence sur le Traitement Automatique des Langues Naturelles, (DEFT/TALN 2013), Sables d’Olonne (France) June 17-21 2013 LIA@RepLab 2014 : 10 systems for 3 tasks Cossu J.-V., Janod K., Ferreira E., Gaillard J. and El-Bèze M. Replab : An evaluation campaign for Online Reputation Management Systems Fifth International Conference of the CLEF initiative, Sheffield (UK) 15-18 September 2014 LIA@RepLab 2013Cossu J.-V., Bigot B., Bonnefoy L., Morchid M., Bost X., Senay G., Dufour R., Bouvier V., Torres-Moreno J.-M. and El-Bèze M. Replab : An evaluation campaign for Online Reputation Management Systems Fourth International Conference of the CLEF initiative, Valencia (Spain) September 23-26 2013 Systèmes du LIA à DEFT'13Bost X., Brunetti I., Cabrera-Diego L-A., Cossu J-V., Linhares A., Morchid M., Torres-Moreno J-M., El-Bèze M. and Dufour R. Défi Fouille de Texte (DEFT/TALN 2013), Sables d’Olonne (France) June 17-21 2013 Contextualisation de messages courts: l’importance des métadonnées Cossu J-V., Gaillard J., Torres-Moreno J-M. and El-Bèze M. Conférence Francophone sur l'Extraction et la Gestion des Connaissances (EGC 2013), Toulouse (France) January 28 2013 Analyser l'image de marque d'entités sur le web. Revue du projet ImagiWeb. Velcin J., Peradotto A., Khouas L., Cossu J-V., Dormagen J-Y. and Brun C. Ingénierie des Systèmes d'Information 19(3): 159-162 (2014) (poster) LIA@Replab2014 (poster) LIA@Replab2013 (poster) Recherche et utilisation d'entités nommées conceptuelles dans une tâche de catégorisation (slides) LDetecting Real-World Influence Through Twitter (slides) Best of RepLab - Content based classifier to generalize experts assements in E-Reputation (slides) NLDB2015 Reputation Modeling with PLS-PM (slides) LIA@Replab2014 : Author Profiling (slides) 3 statistical summarizers at INEX2014, Contextualization applied to ORM (slides) NLDB2014 Improving Topic Priority detection with Topic Detection Methods (slides) LIA@Replab2013 : Topic Detection (slides) Contextualisation de messages courts: l’importance des métadonnées |
Year 2018-2020 Teaching
Year 2014/2015 Teaching
Year 2013/2014 Teaching
Year 2012/2013 Teaching
|
Since 2017 January, I work at My Local Influence as Research Engineer. My main concerns deal with Online Reputation Management.
After about 1 year, I left my Research Engineer position at Vodkaster where I mainly worked on recommender systems within the ANR (French National Research Agency) founded project ALICIA.
I used to collaborate at the University of Avignon within the context of the ANR project : Imagiweb about entities' (individuals and companies) reputation analysis over Web 2.0
Resume
Thesis
Research Keyworks
Natural Language Processing Information Retrieval Online Reputation Management and Monitoring Machine Learning Social Media Analysis Contents Ranking and Selection (Summarization) User-generated contents Mining and Categorization User Profiling (Influence, SCC, Age, Gender, Personality, Political Orientation) Item Modeling from reviews Recomender system (or other cultural products) Artificial Intelligence Education09-2012 -- 08-2015 Ph.D. in Computer Science Specialized in Natural Language Processing applied to Online Reputation Analysis, LIA - University of Avignon (France). 09-2010 -- 08-2012 Master of Science, Specialized Networking and Natural Language ProcessingCERI - University of Avignon (France). Employment Experience 10-2015 -- 10-2016 Research Engineer at Vodkaster - Paris (France). 09-2012 -- 08-2015 Lecturer at CERI - University of Avignon (France). Various courses in Computer Science: Networking, C/C++ and Java (Networking) programmingIntroduction to Social Network Analysis. 11-2011 -- 08-2012 Junior Research Assistant at LIA - University of Avignon (France). LanguagesFrench (Native), English, notions of Italian and Spanish. TeachingC++ Base ProgrammingC/C++ and Java (Networking)Network and TelecommunicationsSocial Network Analysis References
Philippe Fillinger i-Roe Consulting
Phone: +33 6 16 55 68 15
Email:
[email protected]
|
45 Rue Frédéric Joliot Curie MYLI 13013 Marseille FRANCE +33 665 630 728 |