Tag2Word: Using Tags to Generate Words for Content Based Tag Recommendation
Y. Wu, Y. Yao, F. Xu, H. Tong, and J. Lu. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, page 2287--2292. New York, NY, USA, ACM, (2016)
DOI: 10.1145/2983323.2983682
Abstract
Tag recommendation is helpful for the categorization and searching of online content. Existing tag recommendation methods can be divided into collaborative filtering methods and content based methods. In this paper, we put our focus on the content based tag recommendation due to its wider applicability. Our key observation is the tag-content co-occurrence, i.e., many tags have appeared multiple times in the corresponding content. Based on this observation, we propose a generative model (Tag2Word), where we generate the words based on the tag-word distribution as well as the tag itself. Experimental evaluations on real data sets demonstrate that the proposed method outperforms several existing methods in terms of recommendation accuracy, while enjoying linear scalability.
%0 Conference Paper
%1 Wu:2016:TUT:2983323.2983682
%A Wu, Yong
%A Yao, Yuan
%A Xu, Feng
%A Tong, Hanghang
%A Lu, Jian
%B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management
%C New York, NY, USA
%D 2016
%I ACM
%K recommendation tag toread
%P 2287--2292
%R 10.1145/2983323.2983682
%T Tag2Word: Using Tags to Generate Words for Content Based Tag Recommendation
%U http://doi.acm.org/10.1145/2983323.2983682
%X Tag recommendation is helpful for the categorization and searching of online content. Existing tag recommendation methods can be divided into collaborative filtering methods and content based methods. In this paper, we put our focus on the content based tag recommendation due to its wider applicability. Our key observation is the tag-content co-occurrence, i.e., many tags have appeared multiple times in the corresponding content. Based on this observation, we propose a generative model (Tag2Word), where we generate the words based on the tag-word distribution as well as the tag itself. Experimental evaluations on real data sets demonstrate that the proposed method outperforms several existing methods in terms of recommendation accuracy, while enjoying linear scalability.
%@ 978-1-4503-4073-1
@inproceedings{Wu:2016:TUT:2983323.2983682,
abstract = {Tag recommendation is helpful for the categorization and searching of online content. Existing tag recommendation methods can be divided into collaborative filtering methods and content based methods. In this paper, we put our focus on the content based tag recommendation due to its wider applicability. Our key observation is the tag-content co-occurrence, i.e., many tags have appeared multiple times in the corresponding content. Based on this observation, we propose a generative model (Tag2Word), where we generate the words based on the tag-word distribution as well as the tag itself. Experimental evaluations on real data sets demonstrate that the proposed method outperforms several existing methods in terms of recommendation accuracy, while enjoying linear scalability.},
acmid = {2983682},
added-at = {2017-06-17T01:53:04.000+0200},
address = {New York, NY, USA},
author = {Wu, Yong and Yao, Yuan and Xu, Feng and Tong, Hanghang and Lu, Jian},
biburl = {https://www.bibsonomy.org/bibtex/2b731974a718ce3d14728b654c573bfea/hotho},
booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management},
doi = {10.1145/2983323.2983682},
interhash = {3e28a2ee27e7034c49e58fc965b65099},
intrahash = {b731974a718ce3d14728b654c573bfea},
isbn = {978-1-4503-4073-1},
keywords = {recommendation tag toread},
location = {Indianapolis, Indiana, USA},
numpages = {6},
pages = {2287--2292},
publisher = {ACM},
series = {CIKM '16},
timestamp = {2017-06-17T01:53:04.000+0200},
title = {Tag2Word: Using Tags to Generate Words for Content Based Tag Recommendation},
url = {http://doi.acm.org/10.1145/2983323.2983682},
year = 2016
}