Analyse a large échelle des comportements des utilisateurs dans les média sociaux

par Koosha Zarei

Projet de thèse en Informatique, données, IA

Sous la direction de Noel Crespi.

Thèses en préparation à l'Institut polytechnique de Paris , dans le cadre de École doctorale de l'Institut polytechnique de Paris , en partenariat avec SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (laboratoire) et de R3S (equipe de recherche) depuis le 20-12-2019 .


  • Résumé

    In general, the Social media provides valuable resources to analyze user behaviours and this thesis will be focused on analyzing user behaviours in social media systems and classification based on different criteria and at the end, we will build a model to detect bots from the human. Latest developments have seen a huge increase in the growth of social networks including Facebook, Twitter and Instagram. Based on recent studies, many users expose private and very personal information on social media, such as email address, job title, hobbies, phone number, relationship status, date of birth, school name, home address, close friends, political view, and also current mood state. If this information put into the wrong hand, further harmful consequences happen which sometimes could be more severe. Growth of social networks has given rise to a high number of fake users which sometimes are considered as Social Bots or generally fake profiles. Many such profiles are performing different activities to gain more benefits with different aims as like as gain popularity, selling products, advertising, etc. The detection of social bots is, therefore, an important research endeavour. Results show that neither Social Networks, nor humans, nor cutting-edge applications are currently capable of accurately detecting the new social fake profiles

  • Titre traduit

    Impersonation in Online Social Networks


  • Résumé

    In general, the Social media provides valuable resources to analyze user behaviours and this thesis will be focused on analyzing user behaviours in social media systems and classification based on different criteria and at the end, we will build a model to detect bots from the human. Latest developments have seen a huge increase in the growth of social networks including Facebook, Twitter and Instagram. Based on recent studies, many users expose private and very personal information on social media, such as email address, job title, hobbies, phone number, relationship status, date of birth, school name, home address, close friends, political view, and also current mood state. If this information put into the wrong hand, further harmful consequences happen which sometimes could be more severe. Growth of social networks has given rise to a high number of fake users which sometimes are considered as Social Bots or generally fake profiles. Many such profiles are performing different activities to gain more benefits with different aims as like as gain popularity, selling products, advertising, etc. The detection of social bots is, therefore, an important research endeavour. Results show that neither Social Networks, nor humans, nor cutting-edge applications are currently capable of accurately detecting the new social fake profiles