Célina Treuillier
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Célina Treuillier has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Özlem Özgöbek
Norwegian University of Science and Technology
5 shared publications - Armelle Brun
Université de Lorraine, CNRS, LORIA, France
4 shared publications - Sylvain Castagnos
Université de Lorraine, CNRS, LORIA, France
4 shared publications - Andreas Lommatzsch
Berlin Institute of Technology, Berlin, Germany
3 shared publications - Benjamin Kille
Norwegian University of Science and Technology, Trondheim, Norway
3 shared publications - Vandana Yadav
Norwegian University of Science and Technology
3 shared publications
Latest Publications
- Open Access
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 694-697
The 14th International Workshop on News Recommendation and Analytics (INRA 2026)
- 7 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 694-697
Open AccessThe 14th International Workshop on News Recommendation and Analytics (INRA 2026)
- 8 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation individuelle et multi-factorielle du phénomène de polarisation pour une personnalisation de l’apport en diversité dans les recommandations de news
La polarisation est un phénomène complexe exacerbé par les médias sociaux, auquel les systèmes de recommandation contribuent en limitant l'exposition à des opinions diverses. Pour contrer cet enjeu sociétal et favoriser un débat démocratique sain, il est crucial de développer des stratégies de recommandation favorisant une dépolarisation personnalisée. Une compréhension du phénomène de polarisation est néanmoins indispensable au développement de telles stratégies. Dans une première partie, cette thèse propose une modélisation individuelle et multi-factorielle du phénomène de polarisation. Un modèle générique et paramétrable, reposant sur la métrique GRAIL (GeneRalized AddItive poLarization), permet de distinguer des classes de comportement et contribue à une meilleure compréhension de la polarisation. Une modélisation temporelle abordant la polarisation comme un processus dynamique permet ensuite d'identifier des périodes de polarisation, influencées par la maturité des débats et des événements contextuels. Dans une seconde partie, l'approche de diversification personnalisée ADF (Accuracy-Diversity-Fairness) est proposée. Les approches de la littérature peinent à maîtriser la nature de la diversité apportée, et peuvent artificiellement orienter les opinions des utilisateurs. L'approche ADF propose une optimisation tri-objectif permettant de fournir des recommandations répondant aux attentes des utilisateurs, tout en les exposant à un contenu plus diversifié sans influencer leurs opinions. Ces travaux participent à une modélisation plus fine du phénomène de polarisation, permettant d'envisager développement de stratégies dépolarisantes efficaces et éthiques. Ce travail met en lumière le rôle central que joue l'IA pour répondre aux enjeux sociétaux contemporains.
- 8 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation individuelle et multi-factorielle du phénomène de polarisation pour une personnalisation de l’apport en diversité dans les recommandations de news
La polarisation est un phénomène complexe exacerbé par les médias sociaux, auquel les systèmes de recommandation contribuent en limitant l'exposition à des opinions diverses. Pour contrer cet enjeu sociétal et favoriser un débat démocratique sain, il est crucial de développer des stratégies de recommandation favorisant une dépolarisation personnalisée. Une compréhension du phénomène de polarisation est néanmoins indispensable au développement de telles stratégies. Dans une première partie, cette thèse propose une modélisation individuelle et multi-factorielle du phénomène de polarisation. Un modèle générique et paramétrable, reposant sur la métrique GRAIL (GeneRalized AddItive poLarization), permet de distinguer des classes de comportement et contribue à une meilleure compréhension de la polarisation. Une modélisation temporelle abordant la polarisation comme un processus dynamique permet ensuite d'identifier des périodes de polarisation, influencées par la maturité des débats et des événements contextuels. Dans une seconde partie, l'approche de diversification personnalisée ADF (Accuracy-Diversity-Fairness) est proposée. Les approches de la littérature peinent à maîtriser la nature de la diversité apportée, et peuvent artificiellement orienter les opinions des utilisateurs. L'approche ADF propose une optimisation tri-objectif permettant de fournir des recommandations répondant aux attentes des utilisateurs, tout en les exposant à un contenu plus diversifié sans influencer leurs opinions. Ces travaux participent à une modélisation plus fine du phénomène de polarisation, permettant d'envisager développement de stratégies dépolarisantes efficaces et éthiques. Ce travail met en lumière le rôle central que joue l'IA pour répondre aux enjeux sociétaux contemporains.
- Open Access
- 5 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 4 (3) , 1-36
Shift your Focus for the Greater Good: Improving Fairness at no cost for Accuracy and Diversity in News Recommender Systems
In today’s digital landscape, recommender systems assist users in navigating the vast amount of available data. Within the realm of information access, a subset of such systems called News Recommender Systems help users find news content that interests them. However, by prioritizing traditional accuracy-focused optimization, these systems contribute to the formation of filter bubbles, restricting users’ exposure to diverse viewpoints and exacerbating polarization. To address this issue, beyond-accuracy factors like diversity have been integrated into recommendation. Yet, such approaches can be ineffective and even unintentionally influence user opinions. This raises major ethical concerns as systems lack the legitimacy to shape opinions. This article presents the ADF framework, a novel approach designed to optimize accuracy, diversity, and fairness simultaneously. Unlike conventional models that manage fairness in a tradeoff, ADF establishes fairness as a core constraint. The framework relies on an innovative fairness-constrained diversification strategy, ensuring that users are exposed to a broader range of opinions, without being oriented toward specific viewpoints. ADF is adaptable to various diversity metrics and provides personalized diversification, independent of the underlying recommendation algorithms. Through real-world benchmark datasets and multiple recommendation models, experimental evaluation confirmed that ADF limits the impact on accuracy, enhances diversity, and crucially upholds fairness.
- 5 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 4 (3) , 1-36
Open AccessShift your Focus for the Greater Good: Improving Fairness at no cost for Accuracy and Diversity in News Recommender Systems
In today’s digital landscape, recommender systems assist users in navigating the vast amount of available data. Within the realm of information access, a subset of such systems called News Recommender Systems help users find news content that interests them. However, by prioritizing traditional accuracy-focused optimization, these systems contribute to the formation of filter bubbles, restricting users’ exposure to diverse viewpoints and exacerbating polarization. To address this issue, beyond-accuracy factors like diversity have been integrated into recommendation. Yet, such approaches can be ineffective and even unintentionally influence user opinions. This raises major ethical concerns as systems lack the legitimacy to shape opinions. This article presents the ADF framework, a novel approach designed to optimize accuracy, diversity, and fairness simultaneously. Unlike conventional models that manage fairness in a tradeoff, ADF establishes fairness as a core constraint. The framework relies on an innovative fairness-constrained diversification strategy, ensuring that users are exposed to a broader range of opinions, without being oriented toward specific viewpoints. ADF is adaptable to various diversity metrics and provides personalized diversification, independent of the underlying recommendation algorithms. Through real-world benchmark datasets and multiple recommendation models, experimental evaluation confirmed that ADF limits the impact on accuracy, enhances diversity, and crucially upholds fairness.
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1399-1403
The 13th International Workshop on News Recommendation and Analytics (INRA 2025)
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1399-1403
Open AccessThe 13th International Workshop on News Recommendation and Analytics (INRA 2025)
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1258-1261
12th International Workshop on News Recommendation and Analytics (INRA'24)
Personalization has changed how we engage with news. While information has become better accessible, users struggle to find information in the vast amount of news and news commentary published on a daily basis. The INRA workshop provides a forum to researchers, practitioners, and interested parties to discuss recent trends concerning news personalization. This edition of INRA highlights a variety of topics including generative AI, fake news, and multi-modality. Generative AI facilitates creating content at a rapid pace. That includes misleading information that can further erode the trust in media organizations. Texts and still images have dominated the era of printed news. Now, news organizations publish their information also in the form of podcasts and videos.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1258-1261
Open Access12th International Workshop on News Recommendation and Analytics (INRA'24)
Personalization has changed how we engage with news. While information has become better accessible, users struggle to find information in the vast amount of news and news commentary published on a daily basis. The INRA workshop provides a forum to researchers, practitioners, and interested parties to discuss recent trends concerning news personalization. This edition of INRA highlights a variety of topics including generative AI, fake news, and multi-modality. Generative AI facilitates creating content at a rapid pace. That includes misleading information that can further erode the trust in media organizations. Texts and still images have dominated the era of printed news. Now, news organizations publish their information also in the form of podcasts and videos.
- Open Access
- 22 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 143-148
Beyond Trade-offs: Unveiling Fairness-Constrained Diversity in News Recommender Systems
Recommender Systems have played an important role in our daily lives for many years. However, it is only recently that their social impact has raised ethical issues and has thus been considered in the design of such systems. Particularly, News Recommender Systems (NRS) have a critical influence on individuals. NRS can provide overspecialized recommendations and enclose users into filter bubbles. Besides, NRS can influence users and make their original opinions diverge. Worse, they can orient users’ opinions towards more radical views. The literature has worked on these issues by leveraging diversity and fairness in the recommendation algorithms, but generally only one of these dimensions at a time. We propose to consider both diversity and fairness simultaneously to provide recommendations that are fair, diverse, and obviously accurate. To this end, we propose a novel recommendation framework, Accuracy-Diversity-Fairness (ADF), which considers that fairness is not at the expense of diversity. Concretely, fairness is approached as a constraint on diversity. Experiments highlight that constraining diversity by fairness remarkably contributes to providing recommendations 5 times more diverse than models of the literature, without any loss in accuracy.
- 22 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 143-148
Open AccessBeyond Trade-offs: Unveiling Fairness-Constrained Diversity in News Recommender Systems
Recommender Systems have played an important role in our daily lives for many years. However, it is only recently that their social impact has raised ethical issues and has thus been considered in the design of such systems. Particularly, News Recommender Systems (NRS) have a critical influence on individuals. NRS can provide overspecialized recommendations and enclose users into filter bubbles. Besides, NRS can influence users and make their original opinions diverge. Worse, they can orient users’ opinions towards more radical views. The literature has worked on these issues by leveraging diversity and fairness in the recommendation algorithms, but generally only one of these dimensions at a time. We propose to consider both diversity and fairness simultaneously to provide recommendations that are fair, diverse, and obviously accurate. To this end, we propose a novel recommendation framework, Accuracy-Diversity-Fairness (ADF), which considers that fairness is not at the expense of diversity. Concretely, fairness is approached as a constraint on diversity. Experiments highlight that constraining diversity by fairness remarkably contributes to providing recommendations 5 times more diverse than models of the literature, without any loss in accuracy.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1469-1478
All Polarized but Still Different: a Multi-factorial Metric to Discriminate between Polarization Behaviors on Social Media
Online polarization has attracted the attention of researchers for many years. Its effects on society are a cause for concern, and the design of personalized depolarization strategies appears to be a key solution. Such strategies should rely on a fine and accurate measurement, and a clear understanding of polarization behaviors. However, the literature still lacks ways to characterize them finely. We propose GRAIL, the first individual polarization metric, relying on multiple factors. GRAIL assesses these factors through entropy and is based on an adaptable Generalized Additive Model. We evaluate the proposed metric on a Twitter dataset related to the highly controversial debate about the COVID-19 vaccine. Experiments confirm the ability of GRAIL to discriminate between polarization behaviors. To go further, we provide a finer characterization and explanation of the identified behaviors through an innovative evaluation framework.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1469-1478
Open AccessAll Polarized but Still Different: a Multi-factorial Metric to Discriminate between Polarization Behaviors on Social Media
Online polarization has attracted the attention of researchers for many years. Its effects on society are a cause for concern, and the design of personalized depolarization strategies appears to be a key solution. Such strategies should rely on a fine and accurate measurement, and a clear understanding of polarization behaviors. However, the literature still lacks ways to characterize them finely. We propose GRAIL, the first individual polarization metric, relying on multiple factors. GRAIL assesses these factors through entropy and is based on an adaptable Generalized Additive Model. We evaluate the proposed metric on a Twitter dataset related to the highly controversial debate about the COVID-19 vaccine. Experiments confirm the ability of GRAIL to discriminate between polarization behaviors. To go further, we provide a finer characterization and explanation of the identified behaviors through an innovative evaluation framework.
- Open Access
- 16 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
A Multi-factorial Analysis of Polarization on Social Media
Polarization is an increasingly worrying phenomenon within social media. Recent work has made it possible to detect and even quantify polarization. Nevertheless, the few existing metrics, although defined in a continuous space, often lead to a unimodal distribution of data once applied to users’ interactions, making the distinction between polarized and non-polarized users difficult to draw. Furthermore, each metric relies on a single factor and does not reflect the overall user behavior. Modeling polarization in a single form runs the risk of obscuring inter-individual differences. In this paper, we propose to have a deeper look at polarized online behaviors and to compare individual metrics. We collected about 300K retweets from 1K French users between January and July 2022 on Twitter. Each retweet is related to the highly controversial vaccine debate. Results show that a multi-factorial analysis leads to the identification of distinct and potentially explainable behavioral classes. This finer understanding of behaviors is an essential step to adapt news recommendation strategies so that no user gets locked into an echo chamber or filter bubble.
- 16 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessA Multi-factorial Analysis of Polarization on Social Media
Polarization is an increasingly worrying phenomenon within social media. Recent work has made it possible to detect and even quantify polarization. Nevertheless, the few existing metrics, although defined in a continuous space, often lead to a unimodal distribution of data once applied to users’ interactions, making the distinction between polarized and non-polarized users difficult to draw. Furthermore, each metric relies on a single factor and does not reflect the overall user behavior. Modeling polarization in a single form runs the risk of obscuring inter-individual differences. In this paper, we propose to have a deeper look at polarized online behaviors and to compare individual metrics. We collected about 300K retweets from 1K French users between January and July 2022 on Twitter. Each retweet is related to the highly controversial vaccine debate. Results show that a multi-factorial analysis leads to the identification of distinct and potentially explainable behavioral classes. This finer understanding of behaviors is an essential step to adapt news recommendation strategies so that no user gets locked into an echo chamber or filter bubble.