Sébastien Fournier, Ph.D.

Full Professor in Computer Science

Aix-Marseille University • Faculty of Economics and Management (FEG)
Computer Science and Systems Laboratory (LIS • UMR 7020 CNRS)
Head of the R2I Research Team (Information Retrieval & Interaction)

See my work Sébastien Fournier

Publications

Below is the comprehensive list of my academic publications, organized by category and chronologically. Supervised doctoral students are underlined.

International Journal Papers

  • Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, and Sébastien Fournier.
    "Classification with Uncertainty-Aware Multimodal Deep Learning: A Survey".
    ACM SIGKDD Explorations Newsletter, Vol. 28, No. 1, pp. 41–62, June 2026.
    DOI: 10.1145/3820356.3820360
  • Alaeddine Moussa, Sébastien Fournier, Khaoula Mahmoudi, Bernard Espinasse, and Sami Faiz.
    "Spatial Role Labeling Based on Dependency Guided Word Embeddings".
    ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 25, No. 5, pp. 1–17, April 2026.
    DOI: 10.1145/3795776
  • Liana Ermakova, Philippe Mulhem, Antoine Doucet, Carlos-Emiliano Gonzalez-Gallardo, and Sébastien Fournier.
    "Report on the 19th French Conference on Information Retrieval and Applications (CORIA 2024)".
    ACM SIGIR Forum, Vol. 58, No. 1, pp. 1–4, June 2024.
    DOI: 10.1145/3687273.3687291
  • Adrian-Gabriel Chifu and Sébastien Fournier.
    "Sentiment Difficulty in Aspect-Based Sentiment Analysis".
    Mathematics, Vol. 11, No. 22: 4647, 2023.
    DOI: 10.3390/math11224647
  • Ismail Badache, Adrian-Gabriel Chifu, and Sébastien Fournier.
    "Unsupervised and Supervised Methods to Estimate Temporal-Aware Contradictions in Online Course Reviews".
    Mathematics, Vol. 10, No. 5: 809, 2022.
    DOI: 10.3390/math10050809
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "Unsupervised Creation of Normalization Dictionaries for Micro-Blogs in Arabic, French and English".
    Computación y Sistemas, Vol. 22, No. 3, 2018.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "A MultiAgent Architecture for Collaborative Serious Game applied to Crisis Management Training: Improving Adaptability of Non Played Characters".
    EAI Endorsed Transactions on Serious Games, Vol. 2, pp. 11, May 2014.
  • Bernard Espinasse, Sébastien Fournier, and Frederico Freitas.
    "AGATHE: An Agent- and Ontology-Based System for Gathering Information about Restricted Web Domains".
    International Journal of E-Business Research (IJEBR), Vol. 5, No. 2, pp. 14–34, 2009.
  • Frederico Freitas, Luciano Cabral, Rinaldo Lima, Bernard Espinasse, Eunice Palmeira, Sébastien Fournier, and Guilhem Bittencourt.
    "From MASTER-Web to AGATHE: the evolution of an architecture for manipulating information over the Web using ontologies".
    RECIIS - Electronic Journal of Communication, Information and Innovation in Health, Vol. 2, No. 1, pp. 73–84, 2008.
  • Cyril Ray, Thomas Devogele, Mathieu Petit, Sébastien Fournier, and Christophe Claramunt.
    "GIS Technology for Maritime Traffic Systems".
    ERCIM News (Special Theme on Traffic Planning and Logistics), Vol. 68, pp. 41–42, 2007.

National Journal Papers (Peer-Reviewed)

  • Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot.
    "Analyse en dépendance et classification de requêtes en langue naturelle. Application à la recommandation de livres".
    Revue Traitement Automatique des Langues (TAL), 2016.
  • Bernard Espinasse, Rinaldo Lima, Shereen Albitar, Sébastien Fournier, and Frederico Freitas.
    "Extraction adaptative d'information de pages web par règles d'extraction induites par apprentissage".
    Revue d'Intelligence Artificielle (RIA), Vol. 26, No. 6, pp. 643–678, 2012.
  • Bernard Espinasse, Sébastien Fournier, and Frederico Freitas.
    "Collecte d'information sur domaines restreints du Web à base d'agents et d'ontologies : le système AGATHE".
    Revue d'Intelligence Artificielle (RIA), Vol. 23, No. 1, pp. 81–112, 2009.
  • Eric Maillé, Bernard Espinasse, and Sébastien Fournier.
    "Des agents spatiaux pour l'intégration multi-échelle de modèles de dynamiques spatiales : Application à la modélisation et la simulation de la dynamique du risque d'incendie de forêt".
    Revue Internationale de Géomatique, Vol. 19, No. 4, pp. 523–549, 2009.
  • Sébastien Fournier, Thomas Devogele, and Christophe Claramunt.
    "Un système d'aide à la décision alliant agents et raisonnement spatial qualitatif".
    Revue Génie Logiciel, Vol. 86, pp. 37–44, 2008 (Invited paper).
  • Sébastien Fournier, Christophe Claramunt, and Thomas Devogele.
    "Un modèle de raisonnement spatial contextuel pour la navigation maritime".
    Revue Internationale de Géomatique, Vol. 17, No. 1, pp. 63–89, 2007.

Book Chapters & Edited Volumes

  • Alaeddine Moussa, Sébastien Fournier, and Bernard Espinasse.
    "On the Use of Deep Learning for Geodata Enrichments".
    In Interdisciplinary Approaches to Spatial Optimization Issues, edited by Sami Faiz and Soumaya Elhosni, pp. 182–192, IGI Global, 2021.
    DOI: 10.4018/978-1-7998-1954-7.ch010
  • Bernard Espinasse, Sébastien Fournier, Frederico Freitas, Shereen Albitar, and Rinaldo Lima.
    "AGATHE-2: An Adaptive, Ontology-based Information Gathering Multi-agent System for Restricted Web Domains".
    In E-Business Applications for Product Development and Competitive Growth: Emerging Technologies, IGI Global.
  • Sébastien Fournier (Editor).
    "Actes des septièmes Journées des Doctorants du LSIS (JDL6'10)".
    A2DL, Vol. 7, Giens, France, 2010.
  • Sébastien Fournier, Aline Cauvin, and Nicolas Faessel (Editors).
    "Traitement de données complexes".
    Hermes-Lavoisier, Vol. 152, ISI, 2010.
  • Nicolas Faessel and Sébastien Fournier (Editors).
    "Actes des Sixièmes Journées des Doctorants du LSIS (JDL6'09)".
    A2DL, Vol. 6, Giens, France, 2009.
  • Aline Cauvin, Abbas Chamseddine, Nicolas Faessel, Sébastien Fournier, and Yacine Sam (Editors).
    "Actes de la Sixième Manifestation des Jeunes Chercheurs en Sciences et Technologies de l’Information et de la Communication (MajecSTIC'08)".
    Vol. 6, 2008.

International Conference Papers

2026

  • Asmaa Lagrid, Sébastien Fournier, and Bénédicte Aldebert.
    "LegitimNarrate: A Dataset for Analyzing Legitimation Mechanisms in Crowdfunding Narratives".
    In Proceedings of the 15th Language Resources and Evaluation Conference (LREC 2026), pp. 1361–1371, May 2026.
    DOI: 10.63317/3adcqvpnznxt

2025

  • Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, and Sébastien Fournier.
    "EM-SEC: Efficient Multi-head Set-Valued Evidential Classification".
    In Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2025), Lecture Notes in Computer Science, Vol. 16014, Springer, Cham. Acceptance Rate: 25%
    DOI: 10.1007/978-3-032-05981-9_16
  • Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, and Sébastien Fournier.
    "LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data".
    In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '25), Resource Track, pp. 3782–3791. ACM.
    DOI: 10.1145/3726302.3730302 • GitHub Dataset
  • Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, and Sébastien Fournier.
    "Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion".
    In Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), PMLR 258:3142–3150. Acceptance Rate: 30%
    PMLR Proceedings

2024

  • Abdelmadjid Chergui, Grigor Bezirganyan, Sana Sellami, Laure Berti-Equille, and Sébastien Fournier.
    "MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning".
    In 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, pp. 3254–3257, 2024.
    DOI: 10.1109/BigData62323.2024.10825593
  • Adrian-Gabriel Chifu and Sébastien Fournier.
    "Linguistic Features for Sentence Difficulty Prediction in Aspect-Based Sentiment Analysis".
    In International Conference on Information Retrieval and Applications (ICIRA 2024).

2023

  • Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille, and Sébastien Fournier.
    "M2-Mixer: A Multimodal Mixer with Multi-head Loss for Classification from Multimodal Data".
    In 2023 IEEE International Conference on Big Data (BigData), pp. 1052–1058, 2023.

2022

  • Igor Nascimento, Rinaldo Lima, Adrian-Gabriel Chifu, Bernard Espinasse, and Sébastien Fournier.
    "DeepREF: A Framework for Optimized Deep Learning-based Relation Classification".
    In Language Resources and Evaluation Conference (LREC 2022).
  • Maha Mallek, Ramzi Guetari, Sébastien Fournier, Wided Lejouad Chaari, and Bernard Espinasse.
    "Accurate Context Extraction from Unstructured Text Based on Deep Learning".
    In IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI/IAT 2022), pp. 309–314.
  • Alaeddine Moussa, Sébastien Fournier, Khaoula Mahmoudi, Bernard Espinasse, and Sami Faïz.
    "Mixing Static Word Embeddings and RoBERTa for Spatial Role Labeling".
    In Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022), pp. 2950–2957.
  • Maha Mallek, Ramzi Guetari, Sébastien Fournier, Wided Lejouad Chaari, and Bernard Espinasse.
    "Context-aware Relation Classification based on Deep Learning".
    In IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2022), pp. 182–189.
  • Yann Duperis, Adrian-Gabriel Chifu, Bernard Espinasse, Sébastien Fournier, and Arthur Kuehn.
    "Deep Unordered Composition for Multi-label Classification Applied to Skill Prediction".
    In Joint Conference of the Information Retrieval Communities (CIRCLE 2022).

2021

  • Alaeddine Moussa, Sébastien Fournier, Khaoula Mahmoudi, Bernard Espinasse, and Sami Faïz.
    "Spatial Role Labeling System Capturing Both Characters and Word Information Using BiLSTM and CRF".
    In Modeling Decisions for Artificial Intelligence (MDAI 2021).
  • Alaeddine Moussa, Sébastien Fournier, Khaoula Mahmoudi, Bernard Espinasse, and Sami Faïz.
    "Spatial Role Labeling based on Improved Pre-trained Word Embeddings and Transfer Learning".
    In Knowledge-Based and Intelligent Information & Engineering Systems (KES 2021).

2020

  • Maha Mallek, Sébastien Fournier, and Bernard Espinasse.
    "A new Approach for Precise Context Identification from Unstructured Text Documents".
    In IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2020).
  • Amal Htait, Sébastien Fournier, Patrice Bellot, Leif Azzopardi, and Gabriella Pasi.
    "Using sentiment analysis for pseudo-relevance feedback in social book search".
    In ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR 2020), pp. 29–32. Acceptance Rate: 57%
  • Francisco Rodrigues, Rinaldo Lima, William Domingues, Robson Fidalgo, Adrian Chifu, Bernard Espinasse, and Sébastien Fournier.
    "DeepNLPF: A Framework for Integrating Third Party NLP Tools".
    In Language Resources and Evaluation Conference (LREC 2020), pp. 7244–7251. Acceptance Rate: 60%

2019

  • Bernard Espinasse, Sébastien Fournier, Adrian Chifu, Gaël Guibon, and René Azcurra.
    "On the Use of Dependencies in Relation Classification of Text with Deep Learning".
    In 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2019), pp. 1–12, La Rochelle, France. Acceptance Rate: 28%
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "Sentiment Analysis and Sentence Classification in Long Book-Search Queries".
    In 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2019), pp. 1–12. Acceptance Rate: 28%

2018

  • N. Andrianasolo, A.-G. Chifu, Sébastien Fournier, and F. Ibekwe-SanJuan.
    "Challenges to Knowledge Organization in the era of social media: the case of social controversies".
    In Challenges and Opportunities for Knowledge Organization in the Digital Age (ISKO 2018), pp. 1–8.
  • Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot.
    "Measuring the Centrality of the References in Scientific Papers".
    In Proceedings of the ACM Symposium on Document Engineering (DocEng 2018), pp. 1–4. Acceptance Rate: 35%
  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Predicting Contradiction Intensity: Low, Strong or Very Strong?".
    In 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018), pp. 1125–1128. Acceptance Rate: 30%

2017

  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity in Temporal-Related Reviews".
    In Knowledge-Based and Intelligent Information & Engineering Systems (KES 2017), Procedia Computer Science, Vol. 112, pp. 1711–1720.
  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Finding and quantifying temporal-aware contradiction in reviews".
    In Asia Information Retrieval Symposium (AIRS 2017), pp. 167–180.

2016

  • Adrian-Gabriel Chifu and Sébastien Fournier.
    "SegChainW2V: Towards a generic automatic video segmentation framework, based on lexical chains of audio transcriptions and word embeddings".
    In Proceedings of KES 2016, pp. 1371–1380.
  • Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot.
    "Machine Learning approach for detecting diffuse bibliographical references in scientific articles".
    In 6th International Conference on Web Intelligence, Mining and Semantics (WIMS 2016), pp. 1–4, Nîmes, France.
  • Adrian-Gabriel Chifu and Sébastien Fournier.
    "SegChain: Towards a generic automatic video segmentation framework, based on lexical chains of audio transcriptions".
    In Proceedings of the 6th International Conference on Web Intelligence, Mining and Semantics (ACM WIMS '16), pp. 21:1–21:8.
  • Alain Ferrarini, Aline Cauvin, and Sébastien Fournier.
    "Assessment of re-planning solutions: distance measurement between schedules".
    In International Conference on Information Systems, Logistics and Supply Chain (ILS 2016), Bordeaux, France.
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "Bilbo-Val: Automatic Identification of Bibliographical Zone in Papers".
    In 10th edition of the Language Resources and Evaluation Conference (LREC 2016), ELRA, pp. 1–5, Portorož, Slovenia.

2015

  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "Improving Players’ Assessment in Crisis Management Serious Games: The SIMFOR Project".
    In Information Systems for Crisis Response and Management in Mediterranean Countries (ISCRAM-med 2015), Springer, Vol. 233, pp. 85.
  • Chahinez Benkoussas, Patrice Bellot, Anaïs Ollagnier, and Sébastien Fournier.
    "Book Recommendation Using Information Retrieval Methods and Graph Analysis".
    In CLEF 2015 Conference and Labs of the Evaluation Forum, pp. 1–8, Toulouse, France.

2014 & Earlier

  • Shereen Albitar, Sébastien Fournier, and Bernard Espinasse.
    "An Effective TF/IDF-Based Text-to-Text Semantic Similarity Measure for Text Classification".
    In The 15th International Conference on Web Information Systems Engineering (WISE 2014), Springer LNCS 8786, pp. 105–114.
  • Shereen Albitar, Bernard Espinasse, and Sébastien Fournier.
    "Semantic Enrichments in Text Supervised Classification: Application to Medical Domain".
    In Proceedings of the Twenty-Seventh International Florida Artificial Intelligence Research Society Conference (FLAIRS 2014), pp. 1–6.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "A Multi-Agent Architecture for collaborative Serious Game applied to Crisis Management training: improving adaptability of Non Played Characters".
    In The 7th European Conference on Games Based Learning (ECGBL 2013), pp. 1–10.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "Intelligent Tutoring Systems and Serious Game for Crisis Management: a Multi-Agents Integration Architecture".
    In 22nd WETICE IEEE Conference (Track on Collaborative Technology for Coordinating Crisis Management), pp. 253–258, 2013.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "A Multi-Agent System for Learner Assessment in Serious Games: application to learning processes in Crisis Management".
    In Seventh IEEE International Conference on Research Challenges in Information Science (RCIS 2013), pp. 1–12.
  • Shereen Albitar, Sébastien Fournier, and Bernard Espinasse.
    "Conceptualization Effects on MEDLINE Documents Classification Using Rocchio Method".
    In IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology (WI-IAT 2012), pp. 462–466.
  • Shereen Albitar, Sébastien Fournier, and Bernard Espinasse.
    "The Impact of Conceptualization on Text Classification".
    In The 13th International Conference on Web Information Systems Engineering (WISE 2012), Springer LNCS 7651, pp. 326–339.
  • Shereen Albitar, Bernard Espinasse, and Sébastien Fournier.
    "Towards a Supervised Rocchio-based Semantic Classification of Web Pages".
    In Advances in Knowledge-Based and Intelligent Information and Engineering Systems (KES 2012), IOS Press FAIA 243, pp. 460–469.
  • Shereen Albitar, Sébastien Fournier, and Bernard Espinasse.
    "Towards a Semantic Classifier Committee based on Rocchio".
    In STAIRS 2012 - Proceedings of the Sixth Starting AI Researchers' Symposium (ECAI), IOS Press FAIA 241, pp. 1–10.
  • Alain Ferrarini, Aline Cauvin, and Sébastien Fournier.
    "Toward a methodology for disruption management – Reactive planning and scheduling based on a repair approach".
    In 16th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2011), pp. 1–4.
  • Sébastien Fournier, Alain Ferrarini, and Aline Cauvin.
    "A cooperative agent-based scheduling repair method for managing disruptions in complex organisations".
    In 20th IEEE International Conference on Collaboration Technologies and Infrastructures (WETICE 2011), pp. 47–52.
  • Sébastien Fournier and Alain Ferrarini.
    "A MultiAgent scheduling repair method for disruption management in complex socio-technical organizations".
    In Trends in Practical Applications of Agents and Multiagent Systems (PAAMS 2010), Springer AISC 71, pp. 191–199.
  • Shereen Albitar, Bernard Espinasse, and Sébastien Fournier.
    "Combining agents and Wrapper Induction for information gathering on restricted web domains".
    In Fourth International Conference on Research Challenges in Information Science (IEEE RCIS 2010), pp. 343–352.
  • Sébastien Fournier, Alain Ferrarini, and Erwan Tranvouez.
    "A multiagent decision support system for scheduling repair, application to socio-technical organizations".
    In Fourth International Conference on Research Challenges in Information Science (IEEE RCIS 2010), pp. 365–374.
  • Alain Ferrarini, Sébastien Fournier, Erwan Tranvouez, and Aline Cauvin.
    "Decision aid using multiagent models and simulation - Disruption Management in Building Site organization".
    In 20th International Conference on Production Research (ICPR20), China, 2009.
  • Bernard Espinasse, Sébastien Fournier, and Frederico Freitas.
    "Agent and Ontology based Information Gathering on Restricted Web Domains with AGATHE".
    In Proceedings of the 2008 ACM Symposium on Applied Computing (SAC 2008), pp. 2381–2386.
  • Bernard Espinasse, Frederico Freitas, and Sébastien Fournier.
    "AGATHE: an Agent and Ontology based System for Restricted-Domain Information Gathering on the Web".
    In Proceedings of The First IEEE International Conference on Research Challenges in Information Science (RCIS 2007), pp. 177–183.
  • Christophe Claramunt, Thomas Devogele, Sébastien Fournier, Valérie Noyon, Mathieu Petit, and Cyril Ray.
    "Maritime GIS: From Monitoring to Simulation Systems".
    In Information Fusion and Geographic Information Systems (IF&GIS’07), Springer-Verlag, pp. 34–44, 2007.

Evaluation Campaigns & Benchmark Tracks

  • Arina Gepalova, Adrian-Gabriel Chifu, and Sébastien Fournier.
    "CLEF 2024 Joker Task 1: Exploring Pun Detection Using the T5 Transformer Model".
    CLEF 2024 Working Notes, CEUR Workshop Proceedings, pp. 1857–1861, 2024.
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "LSIS at SemEval-2017 Task 4: Using Adapted Sentiment Similarity Seed Words For English and Arabic Tweet Polarity Classification".
    Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 718–722, 2017.
  • Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot.
    "Linking Task: Identifying authors and book titles in verbose queries".
    7th Conference and Labs of the Evaluation Forum (CLEF 2016), Working Notes, Evora, Portugal, 2016.
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "SBS 2016: Combining Query Expansion Result and Books Information Score for Book Recommendation".
    CLEF 2016 Conference and Labs of the Evaluation Forum (Social Book Search), Evora, Portugal, 2016. 2nd place linking task
  • Amal Htait, Sébastien Fournier, and Patrice Bellot.
    "LSIS at SemEval-2016 Task 7: Using Web Search Engines for English and Arabic Unsupervised Sentiment Intensity Prediction".
    10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 1–4, NAACL-HLT, San Diego, California, 2016.
  • Hussam Hamdan, Shereen Albitar, Patrice Bellot, Bernard Espinasse, and Sébastien Fournier.
    "LSIS at TREC 2012 Medical Track: Experiments with conceptualization, a DFR model and a semantic measure".
    NIST Text REtrieval Conference (TREC 2012) Notebook, Gaithersburg, MD, USA, 2012.

Workshop Papers

  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Contradiction in Reviews: is it Strong or Low?".
    In BroDyn 2018: Workshop on Analysis of Broad Dynamic Topics over Social Media, 40th European Conference on Information Retrieval (ECIR 2018).
  • Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot.
    "BIBLME RecSys: Harnessing bibliometric measures for a scholarly paper recommender system".
    In BIR 2018: 7th International Workshop on Bibliometric-enhanced Information Retrieval, ECIR 2018.

National French Conferences

  • Romain Bourgeois, Adrian Chifu, and Sébastien Fournier.
    "Représentations conditionnelles entité-centrées pour le raisonnement multi-saut dans les systèmes de question-réponse multi-document".
    Actes de l'atelier Accès à l’information basé sur le dialogue et grands modèles de langage (DIAG-LLM 2025), pp. 7–7, Marseille, France, ATALA & ARIA.
  • Alae Bouchiba, Adrian-Gabriel Chifu, Sébastien Fournier, Lorraine Goeuriot, and Philippe Mulhem.
    "Vers des RAGs intégrant véracité, subjectivité et explicabilité".
    Actes de l'atelier Intelligence Artificielle générative et ÉDUcation : Enjeux, Défis et Perspectives de Recherche (IA-ÉDU 2025), pp. 149–155, Marseille, France, ATALA & ARIA.
  • Abdelbassat Labeche and Sébastien Fournier.
    "Stimuler la Pensée Étudiante avec l’AQG : Vers une Génération Automatique de Questions de Type Étudiant".
    Actes de l'atelier Intelligence Artificielle générative et ÉDUcation (IA-ÉDU 2025), pp. 126–132, Marseille, France, ATALA & ARIA.
  • Adrian-Gabriel Chifu and Sébastien Fournier.
    "Caractéristiques linguistiques pour la prédiction de la difficulté des phrases dans l'analyse de sentiment basée sur les aspects".
    COnférence en Recherche d'Informations et Applications (CORIA 2024), La Rochelle, France.
  • Yann Duperis, Adrian Chifu, Bernard Espinasse, Sébastien Fournier, and Arthur Kuehn.
    "Vers un système de recommandation de profils experts dans l’industrie des procédés".
    17ème Conférence en Recherche d’Information et Applications (CORIA 2021).
  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Prédire l'intensité de contradiction dans les commentaires: faible, forte ou très forte?".
    29es Journées Francophones d'Ingénierie des Connaissances (IC 2018).
  • Amélie Bohas, Marie-Aude Abid-Dupont, Tarek Abid, Adrian Chifu, and Sébastien Fournier.
    "Les réactions des stakeholders aux allégations d'irresponsabilité organisationnelle: le cas du scandale Volkswagen".
    12ème Congrès du RIODD, 2017.
  • Ismail Badache, Sébastien Fournier, and Adrian-Gabriel Chifu.
    "Détection de contradiction dans les commentaires".
    Association Francophone de Recherche d'Information et Applications (ARIA), 2017.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "Simulation et Evaluation Multi-Agents dans les Jeux Sérieux".
    Plate-forme Intelligence Artificielle (APIA 2015).
  • Anaïs Ollagnier, Sébastien Fournier, Patrice Bellot, and Frédéric Béchet.
    "Impact de la nature et de la taille des corpus d’apprentissage sur les performances dans la détection automatique des entités nommées".
    Traitement Automatique du Langage Naturel (TALN 2014), pp. 517–523.
  • Shereen Albitar, Sébastien Fournier, and Bernard Espinasse.
    "L’impact de l’enrichissement sémantique sur la classification de textes: Application au domaine médical".
    6ème Atelier Recherche d'Information SEmantique (RISE 2014).
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "Evaluation Multi-critères et Distribuée pour l'Apprentissage Collectif de Procédures dans un Jeux Sérieux pour la Gestion de Crise".
    Conférence Environnements Informatiques pour l'Apprentissage Humain (EIAH 2013), Toulouse, France.
  • Ali Oulhaci, Erwan Tranvouez, Sébastien Fournier, and Bernard Espinasse.
    "SIMFOR: un jeu sérieux pour la gestion de crise".
    1ère Conférence francophone sur les Systèmes Collaboratifs (SYSCO 2012).
  • Eric Maillé, Bernard Espinasse, and Sébastien Fournier.
    "Pyroxène: un système d'aide à la décision territoriale par intégration de simulateurs spatiaux. Application à l'évolution de la carte du risque d'incendie de forêt".
    27ième Congrès INFORSID (Atelier SIDE : Systèmes d'Information et de Décision pour l'Environnement), 2009.
  • Alain Ferrarini and Sébastien Fournier.
    "Gestion des perturbations dans l'organisation de chantiers : aide à la décision par modélisation et simulation orientée agent".
    8ème Congrès International de Génie Industriel (CIGI 2009), Tarbes, France.
  • Bernard Espinasse, Sébastien Fournier, and Frederico Freitas.
    "AGATHE : une architecture générique à base d’agents et d’ontologies pour la collecte d’information sur domaines restreints du Web".
    Actes de la 4ème Conférence francophone en Recherche d'Information et Applications (CORIA 2007), pp. 367–385.
  • Sébastien Fournier.
    "Aide à la navigation alliant agents et information géographique".
    Forum Systèmes & Logiciels pour les NTIC dans le transport, 2008 (Invited talk).

Research Activities

My research focuses on understanding and modeling the influence of implicit and explicit knowledge on information retrieval, text classification, and recommendation systems. A central focus is the processing of subjective textual information, such as sentiments, opinions, contradictions, and organizational perceptions.

My methodological framework integrates subjective and non-subjective corpus linguistics, machine learning and deep learning (including evidential deep learning and transformer-based architectures), and probabilistic and symbolic modeling. I strongly favor interdisciplinary research collaborations, notably with researchers in social sciences, management, and biophysics, as well as international partnerships (Tunisia, Italy, Switzerland, Brazil).

Research Axes

Axis 1: Document Interlinking & Multi-modal Connectivity

This axis investigates the establishment and qualification of semantic connections across document collections. These collections are primarily textual but frequently include multi-modal components (images, audio, video). Connections are uncovered through citations, allusions, repetitions, shared content, and hyperlink graphs.

Beyond raw connectivity, this research qualifies links by analyzing surrounding sentiments and user perceptions, and by identifying contradictions when multiple individuals cite or interpret identical links across different contexts. Practical applications include content aggregation, automated document restructuring, recommendation systems, and cross-linking for scientific literature, digital books, and massive open online courses (MOOCs). This axis also explores interaction assessment and social links in serious crisis-management games.

Axis 2: Subjectivity, Sentiment Analysis & Contradiction Detection

This axis is dedicated to detecting, quantifying, and exploiting subjectivity in textual data. The challenge is moving beyond conventional polarity classification towards detecting fine-grained semantic phenomena such as contradictions and opinion divergence.

Ongoing investigations address the automated evaluation of startup and corporate legitimacy. This requires disentangling factual statements from subtle subjective signals expressed by diverse stakeholders (the general public, institutional mentors, specialized economic journalists). This axis closely interacts with entity and event extraction to ground opinions in concrete real-world contexts.

Axis 3: Entity, Event & Spatial Relation Detection

This axis explores information extraction, focusing on named entities, spatial role labeling, and relation extraction from unstructured documents.

The overarching ambition is the design of hybrid models that synthesize structured symbolic knowledge (ontologies, syntactic dependency trees, knowledge graphs) with stochastic and deep neural representations (pre-trained language models, transformers, evidential classification). This enables higher robustness, explainability, and uncertainty awareness in downstream decision-support systems.

Research Projects & Technology Transfer

Overview of funded national and regional research initiatives, industrial technology transfer, and open-source scientific software.

Funded Research Projects

ANR GUIDANCE (2024–2028) • Site PI & Work Package 3 Leader

The GUIDANCE project investigates general dialogue-assisted access to digital information. Its objective is to allow intuitive, conversational digital exploration while overcoming fundamental limitations of current Large Language Models (LLMs) such as hallucinations, lack of explainability, and context drift.

Budget: €755,000 total (€175,000 allocated to LIS). Supported by the French National Research Agency (ANR).

ANR CoPains (2019–2022) • Partner Investigator

CoPains focused on designing persuasive artificial agents capable of motivating human users toward adopting healthy lifestyles and sustaining behavioral change. The primary application was persuasive health technologies, where an Embodied Conversational Agent (ECA) interacts multimodally with users to support daily well-being.

Budget: €544,680. Funded by the French National Research Agency (ANR).

A*MIDEX Physocial (2018–2021) • Partner Investigator

An interdisciplinary project combining behavioral science, neurosciences, and computational linguistics to characterize the psychophysiological foundations of human social behavior and evaluate whether artificial agents (robots or virtual assistants) elicit genuine social attribution.

Budget: €164,070. Funded by the A*MIDEX Foundation (Aix-Marseille University).

Equipex DILOH (2012–2020) • Doctoral Supervisor & Research Contributor

A major national infrastructure initiative to construct an international digital library for open-access publishing and digital humanities. Contributions through the supervision of doctoral research (A. Ollagnier and A. Htait) and active collaboration with OpenEdition Lab.

Budget: €7,000,000. French "Investissements d'Avenir" program.

INCIAM Legitimacy (2020–2022) • Partner Investigator

Investigation into entrepreneurial legitimacy assessment during early firm creation. The project developed automated text mining techniques to analyze regularities in legitimacy dimensions across industries and quantify their correlation with corporate growth.

Funded by: INCIAM Institute (Creativity & Innovation Aix-Marseille).

A*MIDEX ADNvideo (2014–2016) • Principal Investigator (PI)

Construction of multimodal video fingerprints for video recommendation, semantic linking with external resources, and dialogue transcription-based video segmentation. Collaboration involving LSIS, LIF, and Kalyzee.

Budget: €236,327. Supported 3 postdoctoral researchers and resulted in successful industrial technology transfer.

A*MIDEX Appropriation (2018–2019) • Work Package Leader

Analyzed mechanisms of digital content appropriation (query paths, browsing, reading, downloading) and written forms of appropriation across academic publications and public web spheres (social media, Wikipedia).

Inter-Textes (2013–2016) • Research Partner

Text mining R&D program dedicated to interlinking and enhancing scholarly corpora via citation networks, allusions, cross-referencing, and intelligent content recommendation. Carried out with OpenEdition, QWAM, and Demain un autre jour.

PERICLES & Clic&Go

PERICLES: Academic framework agreement in healthcare informatics connecting Aix-Marseille University, AP-HM, LIMOS, CHU Clermont-Ferrand, and LIRMM (led to funding 3 doctoral dissertations).
Clic&Go (2008): E-commerce proximity platform accredited by the SCS Competitiveness Cluster (CARNOT STAR).

Industrial Technology Transfer & Software

Industrial Technology Transfer: Kalyzee (2015–2017)

Transferred automatic video segmentation algorithms based on speech transcription lexical chains and word embeddings (SegChain and SegChainW2V) to the video solutions company Kalyzee.

Datasets, Corpora & Open Software

  • LegitimNarrate Dataset (2026): Expert-annotated dataset specifically designed to analyze legitimation mechanisms in crowdfunding campaign narratives, published at LREC 2026.
  • LUMA Benchmark (2025): Benchmark dataset for learning from uncertain and multimodal data, published in the Resource Track at ACM SIGIR 2025 (github.com/bezirganyan/LUMA).
  • Bilbo: Automatic bibliographic reference parser and annotator for OpenEdition (github.com/OpenEdition/bilbo).
  • Echo & Grapher: Automated sentiment analysis and book review graph explorer for OpenEdition Lab.

Student Supervision & Mentoring

I actively mentor post-doctoral fellows, doctoral researchers, and graduate master's students in natural language processing, information retrieval, and machine learning.

Post-Doctoral Researchers

  • Dr. Ismail Badache (Sep 2017 – Jun 2018)
    "Leveraging Ratings and Aspect-Sentiment to Estimate Contradiction Intensity in Reviews"
    Current Position: Associate Professor (Maître de Conférences)
  • Dr. Adrian-Gabriel Chifu (Oct 2015 – Jun 2017)
    "A generic automatic video segmentation framework, based on lexical chains of audio transcriptions"
    Current Position: Associate Professor (Maître de Conférences)

Ph.D. Dissertations Defended (10)

  • Ali Oulhaci (Defended June 20, 2014)
    "Modélisation et Simulation Orienté Agent de Comportements Humains dans un Jeu Sérieux : application à l'apprentissage de procédures en Gestion de Crises"
    Co-supervised with Pr. Bernard Espinasse (20%) and Erwan Tranvouez (50%). Current: Senior Computer Engineer
  • Shereen Albitar (Defended December 12, 2013)
    "Collecte d'information coopérative sur domaines restreints du web combinant ontologies et apprentissage"
    Co-supervised at 50% with Pr. Bernard Espinasse. Current: Senior Computer Engineer
  • Anaïs Ollagnier (Defended March 30, 2017)
    "Utilisation des entités nommées comme apport d'information pour une recherche de livre orientée contenu efficace"
    Co-supervised at 50% with Pr. Patrice Bellot. Current: Associate Professor, Université Côte d'Azur (Nice)
  • Amal Htait (Defended June 30, 2019)
    "Modèles probabilistes de recommandation de livres par analyse de contenus et de sentiments"
    Co-supervised at 50% with Pr. Patrice Bellot. Current: Lecturer, Aston University, UK
  • Alaeddine Moussa (Defended December 5, 2023)
    "Etiquetage de rôles spatiaux par apprentissage profond basé sur une représentation vectorielle enrichie"
    Co-supervised at 50% with Pr. Bernard Espinasse (co-tutelle with Tunisia). Current: Assistant Professor / Lecturer, ESPRIT (Tunisia)
  • Maha Mallek (Defended December 20, 2023)
    "Extraction et classification selon le contexte de relations entre entités dans des documents textuels non structurés"
    Co-supervised at 50% with Pr. Bernard Espinasse (co-tutelle with Tunisia). Current: Associate Professor / Lecturer (Tunisia)
  • Yann Duperis (Defended February 24, 2024)
    "Un Système d’aide à la constitution de consortiums d’entreprises compétents pour un appel d’offre : une approche basée sur le traitement des langues et les ontologies"
    Co-supervised at 33% with Pr. Bernard Espinasse and Adrian-Gabriel Chifu. Current: R&D Engineer (Switzerland)
  • Grigor Bezirganyan (Defended November 2025)
    "Fusion des données/décisions et quantification des incertitudes pour l’aide à la décision médicale"
    Co-supervised at 33% with Sana Sellami and Laure Berti-Équille. Current: Machine Learning Engineer (Armenia)

Current Ph.D. Students

  • Asmaa Lagrid (2022–Present)
    "Détection et analyse de la légitimité des startups basée sur le traitement automatique de documents"
    Co-direction at 50% with Antonin Ricard (CERGAM laboratory, Aix-Marseille University).
  • Alae Bouchiba (2025–Present)
    "Explainable Retrieval Augmented Generation that supports Veracity and Subjectivity: X-RAG-VS"
    Co-direction at 33% with Lorraine Goeuriot and Philippe Mulhem (LIG laboratory, Grenoble).

Master's Thesis & Research Interns

  • Hassan Sarwat (2025) — Multimodal Deep Learning with Uncertainty Quantification (Co-supervised with S. Sellami and L. Berti-Équille).
  • Labeche Abdelbassat (2025) — Stimuler la Pensée Étudiante avec l'AQG : Vers une Génération Automatique de Questions de Type Étudiant.
  • Arina Gepalova (2024) — Définition d'un RAG pour la recherche de livres (Co-supervised with A.-G. Chifu).
  • Madjid Chergui (2024) — MixMAS : un cadre pour l'architecture d'un mélangeur basé sur l'échantillonnage pour la fusion et l'apprentissage multimodal (Co-supervised with S. Sellami and L. Berti-Équille).
  • René Azcurra (2018) — Extraction automatique de relations d’un document par apprentissage profond avec prise en compte des dépendances syntaxiques (Co-supervised with B. Espinasse and A.-G. Chifu).
  • Amine Medhad (2017) — De l’usage de l’apprentissage profond au traitement automatique des langues : application à l’extraction de relations (Co-supervised with B. Espinasse and A.-G. Chifu).
  • Amal Htait (2015) — Recherche de livres et recommandation de lectures en combinant fouille du Web social et analyse d’opinion automatique (Co-supervised with P. Bellot).
  • Wael Belhassen (2015) — Modélisation, Vérification et Validation d’une méthode réparation de planning à base d’agents (Co-supervised with A. Ferrarini).
  • Imène Boutahar (2013) — Recherche d'information sémantique et probabiliste (Supervised at 100%).
  • Hichem Kerkour (2010) — Formalisation de la notion de proximité pour un moteur de géo-localisation sous Android (Co-supervised with A. Ferrarini).
  • David Gherardi (2009) — Caractérisation et formalisation de la notion de proximité pour un moteur de géo-localisation en e-business (Co-supervised with A. Ferrarini).
  • Shereen Albitar (2009) — Extraction d’information adaptative et distribuée en collecte d’information sur des domaines restreints du web (Co-supervised with B. Espinasse).
  • Kettabi Anouar (2008) — Stockage et exploitation d’information extraite du Web par le système AGATHE (Co-supervised with B. Espinasse).
  • Hung Nguyen (2007) — Collecte d’information sur le Web relatif à des domaines restreints, à base d’agents et d’ontologies (Co-supervised with B. Espinasse).

Teaching & Academic Programs

Program Director: Master 1 MIAGE

Since 2010, I have served as the Program Director of the Master 1 MIAGE (Methods in Informatics Applied to Business Management) at Aix-Marseille University. The program welcomes approximately 60 graduate students each year, with 40 to 60 students enrolled in dual work-study apprenticeships spread across two campuses (Aix-en-Provence and Marseille).

The MIAGE curriculum is ISO 9001 certified, ensuring continuous quality improvement and rigorous pedagogical standards. My pedagogical philosophy emphasizes:

  • Project-Based Learning: Semester-long integrated projects mimicking realistic enterprise environments, including rapid 48-hour collaborative team hackathons.
  • Research-Led Teaching: Engaging advanced graduate students with state-of-the-art research literature (e.g. reading and presenting recent papers from top ACM/IEEE venues such as CIKM).
  • Curriculum Innovation: Creator of 5 cutting-edge master's courses connecting curricula with active research (Prompt Engineering, Big Data Architectures, Machine Learning, and Sentiment Analysis).
5,550+ Total Teaching Hours
1,320+ Apprenticeship Mentoring Hours
~7 / year Corporate Apprentices Supervised
ISO 9001 Certified Quality Program

Courses Portfolio

Overview of courses taught across undergraduate (B.Sc. / Licence) and graduate (M.Sc. / Master) degree programs:

Course Title Academic Level & Track Format Total Hours Class Size
Data Analysis & Machine Learning Master 1 MIAGE Lectures & Labs (CM, TD) 180 h 60
Architectures for Big Data Master 2 MIAGE Lectures & Labs (CM, TD) 160 h 30
Text Analysis & Behavior Recognition Master 2 MIAGE Lectures & Labs (CM, TD) 100 h 30
Big Data Frameworks Master 1 MIAGE Lectures & Labs (CM, TD) 84 h 30
Human-Computer Interaction (HCI) Master 1 MIAGE & M1 Computer Science Lectures & Labs (CM, TD) 735 h 60 / 30
Prompt Engineering Master 1 MIAGE Lectures & Labs (CM, TD) 24 h 30
Computer Networking Master 1 MIAGE Labs (TD) 330 h 60
Object-Oriented Modeling with UML Master 2 Dual-Competence in CS Lectures & Labs (CM, TD) 270 h 20
RDF & Semantic Web Master 2 Research in Computer Science Lectures & Labs (CM, TD) 24 h 10
Event-Driven Programming L3 Computer Science (MIAGE Track) Lectures & Labs (CM, TD) 853 h 30 / 15
Web Engineering & PHP L2 & L3 Computer Science Lectures & Labs (CM, TD) 135 h 25
Spreadsheet Modeling & Business Analytics (Excel) L2 Economics and Management Labs (TD) 1,268 h 90

Executive & Continuing Education

Corporate Training for STMicroelectronics

Delivered specialized professional training modules in partnership with Pr. Patrice Bellot for engineering personnel at STMicroelectronics. The program focused on practical data analysis in Python leveraging the Pandas library and modern data science pipelines.

Contact Information

Feel free to get in touch regarding research collaborations, student supervision, or academic inquiries.

Affiliation & Office

  • Aix-Marseille Université
    Faculté d'Économie et de Gestion (FEG)
  • Laboratoire d'Informatique et des Systèmes (LIS)
    UMR 7020 CNRS / Aix-Marseille Université
  • pageperso.lis-lab.fr/sebastien.fournier