[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-608205-105":59,"doc-detail-608205-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","marked-self-exciting-point-process-modelling-of-information-diffusion-on-twitter-maseptide","Marked Self-Exciting Point Process Modelling of Information Diffusion on Twitter - MaSEPTiDE","","Information diffusion on microblogging platforms like Twitter is driven by retweet cascades, where a posted tweet can be retweeted repeatedly in an iterative and potentially infinite process. Retweet counts provide a direct popularity signal, enabling more effective content ranking and better evaluation of marketing and campaigning potential. The paper introduces MaSEPTiDE, a Marked Self-Exciting Process with a Time-Dependent Excitation Function, to model retweet dynamics and forecast future cascade evolution using observed behavior without expensive feature engineering. Experiments on large Twitter data demonstrate substantial improvements over existing approaches in prediction performance.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/marked-self-exciting-point-process-modelling-of-information-diffusion-on-twitter-maseptide/608205/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/marked-self-exciting-point-process-modelling-of-information-diffusion-on-twitter-maseptide/608205.png","ImageObject",300,407,{"name":92,"@type":93},"Muffet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-17",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does the paper aim to predict on Twitter?","Question",{"text":112,"@type":113},"It aims to predict tweet popularity, measured by the future retweet cascade size (i.e., the number of retweets).","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why is popularity prediction useful in the paper?",{"text":117,"@type":113},"Predictions help rank contents more effectively and support assessing the potential of marketing and campaigning strategies.",{"name":119,"@type":110,"acceptedAnswer":120},"What is MaSEPTiDE, according to the abstract?",{"text":121,"@type":113},"MaSEPTiDE is a Marked Self-Exciting Process with a Time-Dependent Excitation Function that models retweet dynamics and forecasts future cascade evolution without expensive feature engineering.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},608205,1792685232,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":81,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},962090768927,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","arXiv : 1802 .09304v2 [ stat .AP] 19 Apr 2018  \nMarked Self-Exciting Point Process Modelling of Information Di􀀋usion on Twitter  \nFeng Chen  \nSchool of Mathematics and Statistics  \nUNSW Sydney, NSW 2052, Australia  \ne-mail: [feng.chen@unsw.edu.au](feng.chen@unsw.edu.au)  \nWai Hong Tan  \nSchool of Mathematics and Statistics  \nUNSW Sydney, NSW 2052, Australia  \ne-mail: [waihong.tan@student.unsw.edu.au](waihong.tan@student.unsw.edu.au)  \nAbstract: Information di􀀋usion occurs on microblogging platforms like Twitter as retweet cascades. When a tweet is posted, it may be retweeted and henceforth further retweeted, and the retweeting process continues iteratively and inde􀀌nitely. A natural measure of the popularity of a tweet is the number of retweets it generates. Accurate predictions of tweet popularity can assist Twitter to rank contents more e􀀋ectively and facilitate the assessment of potential for marketing and campaigning strategies. In this paper, we propose a model called the Marked Self-Exciting Process with Time-Dependent Excitation Function, or MaSEPTiDE for short, to model the retweeting dynamics and to predict the tweet popularity. Our model does not require expensive feature engineering but is capable of leveraging the observed dynamics to accurately predict the future evolution of retweet cascades. We apply our proposed methodology on a large amount of Twitter data and report substantial improvement in prediction  \nperformance over existing approaches in the literature.  \nKeywords and phrases: B-spline, forecast, Hawkes process, integral equation, nonstation  \nary self-exciting point process, popularity prediction, simulation.  \n1. Introduction  \nThe advancement of technology has dramatically changed the ways people connect to each other over the past few years. This contributes to the increasing popularity of microblogging platforms, which integrate the features of instant messaging and blogging, enabling users to conveniently share contents like short sentences, images or videos. Twitter is a microblogging service that allows the users to share information in the form of 140-character messages called tweets. As a tweet is posted by a user, it may be shared by the followers of the original poster through an action known as retweeting, which explicitly refers to the original tweet via its unique identi􀀌cation number, or aretweet. This retweeting process can iterate inde􀀌nitely, resulting in a cascade of retweets.  \nInformation di􀀋usion modelling in Twitter has been an active 􀀌eld of research. [28] considered Twitter as a platform used for political deliberation and analyzed tweet sentiments by machine learning to forecast the results of elections. By learning the features, one can also 􀀌nd the likelihood of retweets based on the interestingness of contents [23] . [21] proposed a model to account for the rise and fall of in􀀍uence propagation whereas [3] recently modelled random series of events prevalent in Twitter by Poissonian and self-feeding processes. These studies, however, do not emphasize on popularity prediction, which is our primary concern.  \nThe popularity of a tweet is naturally measured by the size of the retweet cascade, or the number of retweets it generates. The predictions of tweet popularity are important as they can assist  \nF. CHEN AND W.H. TAN/MaSEPTiDE: A Model of Information Di􀀋usion on Twitter 2  \nTwitter to rank contents more e􀀋ectively and facilitate the assessment of potential for marketing and campaigning strategies. As such, many models have been proposed to capture the retweeting dynamics and to predict the popularity. One noticeable work is by [31], who proposed a Bayesian approach which predicts tweet popularity using network information. Models based on the theory of point processes [16, 32], which do not require network information, were also shown to have good prediction performances. The model proposed by [22], on the other hand, combines the point process models with feature based a","cbCaivRRA6gCTGJU","https://ap.wps.com/l/cbCaivRRA6gCTGJU","pdf",504780,18,"English","# Introduction\n## Information diffusion and retweet cascades on Twitter\n## Prior work on popularity and influence prediction\n## Point-process and related modeling approaches\n## Recent SEISMIC model and excitation dynamics","[{\"question\":\"What does the paper aim to predict on Twitter?\",\"answer\":\"It aims to predict tweet popularity, measured by the future retweet cascade size (i.e., the number of retweets).\"},{\"question\":\"Why is popularity prediction useful in the paper?\",\"answer\":\"Predictions help rank contents more effectively and support assessing the potential of marketing and campaigning strategies.\"},{\"question\":\"What is MaSEPTiDE, according to the abstract?\",\"answer\":\"MaSEPTiDE is a Marked Self-Exciting Process with a Time-Dependent Excitation Function that models retweet dynamics and forecasts future cascade evolution without expensive feature engineering.\"}]","Marked Self-Exciting Point Process Modelling of Information Diffusion on Twitter - MaSEPTiDE | PDF",1792223256,45]