{"id":1127,"date":"2018-12-11T14:56:57","date_gmt":"2018-12-11T13:56:57","guid":{"rendered":"https:\/\/samovar2022.int-evry.fr\/index.php\/2018\/12\/11\/analyse-du-modele-de-popularite-de-lutilisateur-et-de-la-prediction-dengagement-sur-les-reseaux-sociaux-en-ligne\/"},"modified":"2020-09-04T18:45:44","modified_gmt":"2020-09-04T16:45:44","slug":"analyse-du-modele-de-popularite-de-lutilisateur-et-de-la-prediction-dengagement-sur-les-reseaux-sociaux-en-ligne","status":"publish","type":"post","link":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/2018\/12\/11\/analyse-du-modele-de-popularite-de-lutilisateur-et-de-la-prediction-dengagement-sur-les-reseaux-sociaux-en-ligne\/","title":{"rendered":"\u00abAnalyse du mod\u00e8le de popularit\u00e9 de l’utilisateur et de la pr\u00e9diction d’engagement sur les r\u00e9seaux sociaux en ligne\u00bb"},"content":{"rendered":"

Ecole doctorale EDITE – Ecole doctorale informatique, t\u00e9l\u00e9communications et \u00e9lectronique et T\u00e9l\u00e9com SudParis avec le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Madame Samin KARBALAY MOHAMMADI DASTJERDI<\/strong> Autoris\u00e9e \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de T\u00e9l\u00e9com SudParis avec l’Universit\u00e9 Paris 6 en Informatique \u00abAnalyse du mod\u00e8le de popularit\u00e9 de l’utilisateur et de la pr\u00e9diction d’engagement sur les r\u00e9seaux sociaux en ligne\u00bb<\/p>\n

le 4 d\u00e9cembre 2018 \u00e0 9:00- Salle A003<\/strong>
\nAdresse : T\u00e9l\u00e9com SudParis – 9 Rue Charles Fourier, 91000 \u00c9vry<\/p>\n

Membres du jury :<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n
Directeur de th\u00e8se <\/td>\n No\u00ebl CRESPI- Professeur<\/td>\n<\/tr>\n
Encadrant <\/td>\n Reza FARAHBAKHSH – Chercheur – T\u00e9l\u00e9com SudParis<\/td>\n<\/tr>\n
Rapporteurs<\/td>\nMarkus FIEDLER – Professeur – Blekinge Tekniska H\u00f6gskola University – Karlskrona, Su\u00e8de<\/td>\n<\/tr>\n
Rapporteurs<\/td>\nAgata FILIPOWSKA – Assistant Professor – Universit\u00e9 de Poznan – Pologne<\/td>\n<\/tr>\n
Examinateurs<\/td>\n Ioan Marius BILASCO – Ma\u00eetre de conf\u00e9rences – Universit\u00e9 de Lille 1<\/td>\n<\/tr>\n
Examinateurs<\/td>\n Marie-Jeanne LESOT – Ma\u00eetre de conf\u00e9rences HDR – Sorbonne Universit\u00e9 – Paris<\/td>\n<\/tr>\n
Examinateurs<\/td>\n Daqing ZHANG – Professeur – T\u00e9l\u00e9com SudParis<\/td>\n<\/tr>\n
Examinateurs<\/td>\n Yacine GHAMRI-DOUDANE – Professeur – Universit\u00e9 de La Rochelle – France<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

R\u00e9sum\u00e9 :<\/strong><\/p>\n

De nos jours, les m\u00e9dias sociaux ont largement affect\u00e9 tous les aspects de la vie humaine. Le changement le plus significatif dans le comportement des gens apr\u00e8s l\u2019\u00e9mergence des r\u00e9seaux sociaux en ligne (OSNs) est leur m\u00e9thode de communication et sa port\u00e9e. Avoir plus de connexions sur les OSNs apporte plus d\u2019attention et de visibilit\u00e9 aux gens, ou` cela s\u2019appelle la popularit\u00e9 sur les m\u00e9dias sociaux. Selon le type de r\u00e9seau social, la popularit\u00e9 se mesure par le nombre d\u2019adeptes, d\u2019amis, de retweets, de go\u00fbts et toutes les autres mesures qui servaient `a calculer l\u2019engagement.<\/p>\n

L\u2019\u00e9tude du comportement de popularit\u00e9 des utilisateurs et des contenus publi\u00e9s sur les m\u00e9dias sociaux et la pr\u00e9diction de leur statut futur sont des axes de recherche importants qui b\u00e9n\u00e9ficient `a diff\u00e9rentes applications telles que les syst\u00e8mes de recommandation, les r\u00e9seaux de diffusion de contenu, les campagnes publicitaires, la pr\u00e9vision des r\u00e9sultats d\u00e9s\u00e9lections, etc. Cette th\u00e8se porte sur l\u2019analyse du comportement de popularit\u00e9 des utilisateurs d\u2019OSN et de leurs messages publi\u00e9s afin, d\u2019une part, d\u2019identifier les tendances de popularit\u00e9 des utilisateurs et des messages et, d\u2019autre part, de pr\u00e9voir leur popularit\u00e9 future et leur niveau d\u2019engagement pour les messages publi\u00e9s par les utilisateurs.<\/p>\n

A cette fin, i) l\u2019\u00e9volution de la popularit\u00e9 des utilisateurs de l\u2019ONS est \u00e9tudi\u00e9e \u00e0 l\u2019aide d\u2019un ensemble de donn\u00e9es d\u2019utilisateurs professionnels 8K Facebook collect\u00e9es par un crawler avanc\u00e9. L\u2019ensemble de donn\u00e9es collect\u00e9es comprend environ 32 millions d\u2019instantan\u00e9s des valeurs de popularit\u00e9 des utilisateurs et 19 millions de messages publi\u00e9s sur une p\u00e9riode de 4 ans. Le regroupement des s\u00e9quences temporelles des valeurs de popularit\u00e9 des utilisateurs a permis d\u2019identifier des mod\u00e8les d\u2019\u00e9volution de popularit\u00e9 diff\u00e9rents et int\u00e9ressants. Les grappes identifi\u00e9es sont caract\u00e9ris\u00e9es par l\u2019analyse du secteur d\u2019activit\u00e9 des utilisateurs, appel\u00e9 cat\u00e9gorie, leur niveau d\u2019activit\u00e9, ainsi que l\u2019effet des \u00e9v\u00e9nements externes.<\/p>\n

Ensuite ii) la th\u00e8se se concentre sur la popularit\u00e9 des contenus publi\u00e9s par les utilisateurs sur les OSNs. Un nouveau mod\u00e8le de pr\u00e9diction est propos\u00e9 qui tire parti de l\u2019information mutuelle par points (PMI) et pr\u00e9dit la r\u00e9action future des utilisateurs aux messages nouvellement publi\u00e9s. Enfin, iii) le mod\u00e8le propos\u00e9 est \u00e9largi pour tirer profit de l\u2019apprentissage de la repr\u00e9sentation et pr\u00e9voir l\u2019engagement futur des utilisateurs sur leurs postes respectifs. L\u2019approche de pr\u00e9diction propos\u00e9e extrait l\u2019int\u00e9gration de l\u2019utilisateur de son historique de r\u00e9action au lieu d\u2019utiliser les m\u00e9thodes conventionnelles d\u2019extraction de caract\u00e9ristiques. La performance du mod\u00e8le propos\u00e9 prouve qu\u2019il surpasse les m\u00e9thodes d\u2019apprentissage conventionnelles disponibles dans la litt\u00e9rature.
\n Les mod\u00e8les propos\u00e9s dans cette th\u00e8se, non seulement d\u00e9placent les mod\u00e8les de pr\u00e9diction de r\u00e9action vers le haut pour exploiter les fonctions d\u2019apprentissage de la repr\u00e9sentation au lieu de celles qui sont faites `a la main, mais pourraient \u00e9galement aider les nouvelles agences, les campagnes publicitaires, les fournisseurs de contenu dans les CDN et les syst\u00e8mes de recommandation `a tirer parti de r\u00e9sultats de pr\u00e9diction plus pr\u00e9cis afin d\u2019am\u00e9liorer leurs services aux utilisateurs.<\/p>\n

ABSTRACT:<\/strong><\/p>\n

Nowadays, social media has widely affected every aspect of human life. The most significant change in people\u2019s behavior after emerging Online Social Networks (OSNs) is their communication method and its range. Having more connections on OSNs brings more attention and visibility to people, where it is called popularity on social media. Depends on the type of social network, popularity is measured by the number of followers, friends, retweets, likes, and all those other metrics that used to calculate engagement. Studying the popularity behavior of users and published contents on social media and predicting its future status are the important research directions which benefit different applications such as recommender systems, content delivery networks, advertising campaign, election results prediction and so on. This thesis addresses analyzing the popularity behavior of OSN users and their published posts in order to first, identify the popularity trends of users and posts and second, predict their future popularity and engagement level for published posts by users.<\/p>\n

To this end, i) the popularity evolution of ONS users is studied using a dataset of 8K Face- book professional users collected by an advanced crawler. The collected dataset includes around 32 million snapshots of users\u2019 popularity values and 19 million published posts over a period of 4 years. Clustering temporal sequences of users\u2019 popularity values led to identifying different and interesting popularity evolution patterns. The identified clusters are characterized by analyzing the users\u2019 business sector, called category, their activity level, and also the effect of external events.<\/p>\n

Then ii) the thesis focuses on the popularity of contents published by users on OSNs. A novel prediction model is proposed which takes advantage of Point-wise Mutual Information (PMI) and predicts users\u2019 future reaction to newly published posts. Finally, iii) the proposed model is extended to get benefits of representation learning and predict users\u2019 future engagement on each other\u2019s posts. The proposed prediction approach extracts user embedding from their reaction history instead of using conventional feature extraction methods. The performance of the proposed model proves that it outperforms conventional learning methods available in the literature.
\n The models proposed in this thesis, not only move the reaction prediction models up to exploit representation learning features instead of hand-crafted ones but also could help new agencies, advertising campaigns, content providers in CDNs, and recommender systems to take advantage of more accurate prediction results in order to improve their user services.<\/p>\n","protected":false},"excerpt":{"rendered":"

Ecole doctorale EDITE – Ecole doctorale informatique, t\u00e9l\u00e9communications et \u00e9lectronique et T\u00e9l\u00e9com SudParis avec le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, MOd\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Madame Samin KARBALAY MOHAMMADI DASTJERDI Autoris\u00e9e \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de T\u00e9l\u00e9com SudParis avec l’Universit\u00e9 Paris […]<\/p>\n","protected":false},"author":1,"featured_media":1126,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[314],"tags":[],"class_list":["post-1127","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-theses-2018-fr","entry","has-media"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/1127","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=1127"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/1127\/revisions"}],"predecessor-version":[{"id":1494,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/1127\/revisions\/1494"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media\/1126"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=1127"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=1127"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=1127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}