[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-253859-105":53,"doc-detail-253859-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","a-survey-of-recommender-systems-in-twitter","A Survey of Recommender Systems in Twitter","","Twitter is a social information network where users share short tweets, yet the scale of activity—over 100M users and hundreds of millions of tweets daily—creates severe information overload. To support users in selecting relevant content and interactions, recommender systems are introduced, but prior studies typically focus on isolated tasks. This paper addresses the gap by proposing a taxonomy of Twitter recommendation tasks, mapping recent works, summarizing datasets and techniques, and outlining future research directions.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":31,"@type":70,"position":76},"https://docshare.wps.com/template/social-media/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/a-survey-of-recommender-systems-in-twitter/253859/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/a-survey-of-recommender-systems-in-twitter/253859.png","ImageObject",442,249,{"name":88,"@type":89},"Pentious","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-14","2026-09-13",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",8,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"Why is a recommender system important for Twitter?","Question",{"text":109,"@type":110},"Twitter users face information overload due to the massive volume of tweets and many potential interactions. Recommender systems help users choose relevant content and actions.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"What problem does the paper aim to solve?",{"text":114,"@type":110},"It addresses the lack of a comprehensive survey for Twitter recommendations by introducing a taxonomy that categorizes existing work and highlights research gaps.",{"name":116,"@type":107,"acceptedAnswer":117},"What does the proposed taxonomy include?",{"text":118,"@type":110},"The taxonomy organizes recommendation tasks by the unique functions users perform on Twitter, and the paper uses it to describe recent related studies along with their datasets and techniques.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},253859,1790460502,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":30,"category_name":31,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":20,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":47},1374404730887,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","A Survey of Recommender Systems in Twitter  \nSu Mon Kywe, Ee-Peng Lim and Feida Zhu  \nSingapore Management University, Singapore  \n{[monkywe.su.2011](monkywe.su.2011) , eplim, [fdzhu}@smu.edu.sg](fdzhu}@smu.edu.sg)  \nAbstract. Twitter is a social information network where short messages or tweets are shared among a large number of users through a very simple messaging mechanism. With a population of more than 100M users generating more than 300M tweets each day, Twitter users can be easily overwhelmed by the massive amount of information available and the huge number of people they can interact with. To overcome the above information overload problem, recommender systems can be introduced to help users make the appropriate selection. Researchers have began to study recommendation problems in Twitter but their works usually address individual recommendation tasks. There is so far no comprehensive survey for the realm of recommendation in Twitter to categorize the existing works as well as to identify areas that need to be further studied. The paper therefore aims to ¯ll this gap by introducing a taxonomy of recommendation tasks in Twitter, and to use the taxonomy to describe the relevant works in recent years. The paper further presents the datasets and techniques used in these works. Finally, it proposes a few research directions for recommendation tasks in Twitter.  \nKeywords: Twitter, recommender systems, personalization  \n1 Introduction  \n1.1 Motivation  \nTwitter is an online social information network launched in July 2006 . By 2012, the number of Twitter users has grown to over 140 million 1 . Unlike many other online social networks, the user-user relationships in Twitter network can be social or informational, or both. This is because users not only follow other users for maintaining social links, but also for gaining access to interesting information generated by others[13, 15] . For example, Twitter has been often used to share information and sentiments about live events including the 2011 Egypt's revolution[5] .  \nAs Twitter users generate more than 300M tweets each day, these users are also overwhelmed by the massive amount of information available and the huge number of people they can interact with. To overcome the above information overload problem, recommender systems can be introduced to help users make  \n1 [http://en.wikipedia.org/wiki/Twitter](http://en.wikipedia.org/wiki/Twitter)  \n2 Su Mon Kywe, Ee-Peng Lim and Feida Zhu  \nthe appropriate selection. While some of these are already deployed so far, most of them are still being studied as research projects in universities and industry labs. These research projects usually address individual recommendation tasks. There is currently no comprehensive survey for the realm of recommendation in Twitter to categorize the existing works as well as to identify areas that need to be further studied. The paper therefore aims to ¯ll this gap by introducing a taxonomy of recommendation tasks in Twitter, and to use the taxonomy to describe the relevant works in recent years.  \nOur taxonomy is designed considering the unique functions users can perform in Twitter. Before we show the taxonomy, we ¯rst review these functions as follows.  \n{ Tweet - This refers to posting a message of up to 140 characters, known as tweets. The content of tweets may vary from users' daily activities to news[13] . Some messages may also include URLs to web pages or hashtags to relate tweets of similar topics together. Each hashtag is a keyword pre¯xed by a \\# symbol. For example, \\#Egypt and \\#Jan25 have been used to group tweets related to Egypt's revolution in January 2011 .  \n{ Retweet-This refers to forwarding a tweet from another user to the followers. Such re-sharing of tweets is a prevailing mechanism in Twitter to di®use information.  \n{ Follow-This refers to linking to another user and receiving the linked user's tweets after that. The user creating such a link is called the follower a","cbCaipi2E6YtQdEV","https://ap.wps.com/l/cbCaipi2E6YtQdEV","pdf",213128,"English","# Introduction\n## Motivation\n## A Taxonomy of Recommendation Tasks for Twitter","[{\"question\":\"Why is a recommender system important for Twitter?\",\"answer\":\"Twitter users face information overload due to the massive volume of tweets and many potential interactions. Recommender systems help users choose relevant content and actions.\"},{\"question\":\"What problem does the paper aim to solve?\",\"answer\":\"It addresses the lack of a comprehensive survey for Twitter recommendations by introducing a taxonomy that categorizes existing work and highlights research gaps.\"},{\"question\":\"What does the proposed taxonomy include?\",\"answer\":\"The taxonomy organizes recommendation tasks by the unique functions users perform on Twitter, and the paper uses it to describe recent related studies along with their datasets and techniques.\"}]","A Survey of Recommender Systems in Twitter | PDF",1789271108]