WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 01
Learning to recognize valuable tags
Proceedings of the 14th international conference on Intelligent user interfaces
A content-based method to enhance tag recommendation
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Separating the reputation and the sociability of online community users
Proceedings of the 2010 ACM Symposium on Applied Computing
Adaptive combination of tag and link-based user similarity in flickr
Proceedings of the international conference on Multimedia
Extracting Representative Tags for Flickr Users
ICDMW '10 Proceedings of the 2010 IEEE International Conference on Data Mining Workshops
Leveraging collaborative tagging for web item design
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Learning semantic relationships between entities in twitter
ICWE'11 Proceedings of the 11th international conference on Web engineering
Hierarchical tag visualization and application for tag recommendations
Proceedings of the 20th ACM international conference on Information and knowledge management
Hi-index | 0.00 |
Most item recommendation systems nowadays are implemented by applying machine learning algorithms with user surveys as ground truth. In order to get satisfactory results from machine learning, massive amounts of user surveys are required. But in reality obtaining a large number of user surveys is not easy. Additionally, in many cases the opinions are subjective and personal. Hence user surveys cannot tell all the aspects of the truth. However, in this paper, we try to generate ground truth automatically instead of doing user surveys. To prove that our approach is useful, we build our experiment using Flickr to recommend tags that can represent the users' interested topics. First, when we build training and testing models by user surveys, we note that the extracted tags are inclined to be too ordinary to be recommended as "Flickr-aware" terms that are more photographic or Flickr-friendly. To capture real representative tags for users, we apply LSA in a novel way to build ground truth for our training model. In order to verify our scheme, we define Flickr-aware terms to measure the extracted representative tags. Our experiments show that our proposed scheme with the automatically generated ground truth and measurements visibly improve the recommendation results.