%0 Conference Paper %1 Song:2008:RAT:1390334.1390423 %A Song, Yang %A Zhuang, Ziming %A Li, Huajing %A Zhao, Qiankun %A Li, Jia %A Lee, Wang-Chien %A Giles, C. Lee %B Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval %C New York, NY, USA %D 2008 %I ACM %K %P 515--522 %R 10.1145/1390334.1390423 %T Real-time Automatic Tag Recommendation %X Tags are user-generated labels for entities. Existing research on tag recommendation either focuses on improving its accuracy or on automating the process, while ignoring the efficiency issue. We propose a highly-automated novel framework for real-time tag recommendation. The tagged training documents are treated as triplets of (words, docs, tags), and represented in two bipartite graphs, which are partitioned into clusters by Spectral Recursive Embedding (SRE). Tags in each topical cluster are ranked by our novel ranking algorithm. A two-way Poisson Mixture Model (PMM) is proposed to model the document distribution into mixture components within each cluster and aggregate words into word clusters simultaneously. A new document is classified by the mixture model based on its posterior probabilities so that tags are recommended according to their ranks. Experiments on large-scale tagging datasets of scientific documents (CiteULike) and web pages del.icio.us) indicate that our framework is capable of making tag recommendation efficiently and effectively. The average tagging time for testing a document is around 1 second, with over 88% test documents correctly labeled with the top nine tags we suggested. %@ 978-1-60558-164-4

@inproceedings{Song:2008:RAT:1390334.1390423, abstract = {Tags are user-generated labels for entities. Existing research on tag recommendation either focuses on improving its accuracy or on automating the process, while ignoring the efficiency issue. We propose a highly-automated novel framework for real-time tag recommendation. The tagged training documents are treated as triplets of (words, docs, tags), and represented in two bipartite graphs, which are partitioned into clusters by Spectral Recursive Embedding (SRE). Tags in each topical cluster are ranked by our novel ranking algorithm. A two-way Poisson Mixture Model (PMM) is proposed to model the document distribution into mixture components within each cluster and aggregate words into word clusters simultaneously. A new document is classified by the mixture model based on its posterior probabilities so that tags are recommended according to their ranks. Experiments on large-scale tagging datasets of scientific documents (CiteULike) and web pages del.icio.us) indicate that our framework is capable of making tag recommendation efficiently and effectively. The average tagging time for testing a document is around 1 second, with over 88% test documents correctly labeled with the top nine tags we suggested.}, acmid = {1390423}, added-at = {2016-09-05T20:16:51.000+0200}, address = {New York, NY, USA}, author = {Song, Yang and Zhuang, Ziming and Li, Huajing and Zhao, Qiankun and Li, Jia and Lee, Wang-Chien and Giles, C. Lee}, biburl = {https://www.bibsonomy.org/bibtex/2bed83f4b5fa42888e0af7a4b7cc516ab/nosebrain}, booktitle = {Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, doi = {10.1145/1390334.1390423}, interhash = {e6505664e875de06d98a6e787d4367d1}, intrahash = {bed83f4b5fa42888e0af7a4b7cc516ab}, isbn = {978-1-60558-164-4}, keywords = {}, location = {Singapore, Singapore}, numpages = {8}, pages = {515--522}, publisher = {ACM}, series = {SIGIR '08}, timestamp = {2016-09-05T20:16:51.000+0200}, title = {Real-time Automatic Tag Recommendation}, year = 2008 }