1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Exploiting Concept Drift to Predict Popularity of Social Multimedia in Microblogs
作者 沈錳坤
Li, Cheng-Te;Shan, Man-Kwan;Jheng, Shih-Hong;Chou, Kuan-Ching
貢獻者 資科系
關鍵詞 Popularity prediction;Social multimedia;Concept drift;Information diffusion;Microblog social network
日期 2016-04
上傳時間 29-六月-2017 09:43:08 (UTC+8)
摘要 Microblogging services such as Twitter and Plurk allow users to easily access and share different types of social multimedia (e.g. images and videos) in the cyber world. However, the massive amount of information available causes information overload, which prevents users from quickly accessing popular and important digital content. This paper studies the problem of predicting the popularity of social multimedia content embedded in short microblog messages. A property of social multimedia is that it can be continuously re-shared, thus its popularity may revive or evolve over time. We exploit the idea of concept drift to capture this property. We formulate the problem using a classification-based approach and propose to tackle two tasks, re-share classification and popularity score classification. Two categories of features are devised and extracted, including information diffusion and explicit multimedia meta information. We develop a concept drift-based popularity predictor by ensembling multiple trained classifiers from social multimedia instances in different time intervals. The key idea lies in dynamically determining the ensemble weights of classifiers. Experiments conducted on Plurk and Twitter datasets show the high accuracy of the popularity classification and the results on detecting popular social multimedia are promising.
關聯 Information Sciences, 339, 310-331
資料類型 article
DOI http://dx.doi.org/10.1016/j.ins.2016.01.009
dc.contributor 資科系
dc.creator (作者) 沈錳坤zh_TW
dc.creator (作者) Li, Cheng-Te;Shan, Man-Kwan;Jheng, Shih-Hong;Chou, Kuan-Ching
dc.date (日期) 2016-04
dc.date.accessioned 29-六月-2017 09:43:08 (UTC+8)-
dc.date.available 29-六月-2017 09:43:08 (UTC+8)-
dc.date.issued (上傳時間) 29-六月-2017 09:43:08 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/110579-
dc.description.abstract (摘要) Microblogging services such as Twitter and Plurk allow users to easily access and share different types of social multimedia (e.g. images and videos) in the cyber world. However, the massive amount of information available causes information overload, which prevents users from quickly accessing popular and important digital content. This paper studies the problem of predicting the popularity of social multimedia content embedded in short microblog messages. A property of social multimedia is that it can be continuously re-shared, thus its popularity may revive or evolve over time. We exploit the idea of concept drift to capture this property. We formulate the problem using a classification-based approach and propose to tackle two tasks, re-share classification and popularity score classification. Two categories of features are devised and extracted, including information diffusion and explicit multimedia meta information. We develop a concept drift-based popularity predictor by ensembling multiple trained classifiers from social multimedia instances in different time intervals. The key idea lies in dynamically determining the ensemble weights of classifiers. Experiments conducted on Plurk and Twitter datasets show the high accuracy of the popularity classification and the results on detecting popular social multimedia are promising.
dc.format.extent 4345420 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Information Sciences, 339, 310-331
dc.subject (關鍵詞) Popularity prediction;Social multimedia;Concept drift;Information diffusion;Microblog social network
dc.title (題名) Exploiting Concept Drift to Predict Popularity of Social Multimedia in Microblogs
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.1016/j.ins.2016.01.009
dc.doi.uri (DOI) http://dx.doi.org/10.1016/j.ins.2016.01.009