User Recommendations based on Tensor Dimensionality Reduction Export

@incollection{citeulike:5292207, abstract = {Social Tagging is the process by which many users add metadata in the form of keywords, to annotate and categorize items (songs, pictures, web links, products etc.). Social tagging systems (STSs) can recommend users with common social interest based on common tags on similar items. However, users may have different interests for an item, and items may have multiple facets. In contrast to the current recommendation algorithms, our approach develops a model to capture the three types of entities that exist in a social tagging system: users, items, and tags. These data are represented by a 3-order tensor, on which latent semantic analysis and dimensionality reduction is performed using the Higher Order Singular Value Decomposition (HOSVD) method. We perform experimental comparison of the proposed method against a baseline user recommendation algorithm with a real data set (BibSonomy), attaining significant improvements.}, author = {Symeonidis, Panagiotis}, citeulike-article-id = {5292207}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-1-4419-0221-4_39}, citeulike-linkout-1 = {http://www.springerlink.com/content/j32671483j478801}, doi = {10.1007/978-1-4419-0221-4_39}, journal = {Artificial Intelligence Applications and Innovations III}, keywords = {dimensionality-reduction, dlpaws, dppaws, recommender, tagging}, pages = {331--340}, posted-at = {2009-07-28 16:32:07}, priority = {3}, title = {User Recommendations based on Tensor Dimensionality Reduction}, url = {http://dx.doi.org/10.1007/978-1-4419-0221-4_39}, year = {2009} }

TY - CHAP ID - citeulike:5292207 L3 - citeulike-article-id:5292207 N2 - Social Tagging is the process by which many users add metadata in the form of keywords, to annotate and categorize items (songs, pictures, web links, products etc.). Social tagging systems (STSs) can recommend users with common social interest based on common tags on similar items. However, users may have different interests for an item, and items may have multiple facets. In contrast to the current recommendation algorithms, our approach develops a model to capture the three types of entities that exist in a social tagging system: users, items, and tags. These data are represented by a 3-order tensor, on which latent semantic analysis and dimensionality reduction is performed using the Higher Order Singular Value Decomposition (HOSVD) method. We perform experimental comparison of the proposed method against a baseline user recommendation algorithm with a real data set (BibSonomy), attaining significant improvements. JF - Artificial Intelligence Applications and Innovations III EP - 340 TI - User Recommendations based on Tensor Dimensionality Reduction SP - 331 KW - dimensionality-reduction KW - dlpaws KW - dppaws KW - recommender KW - tagging AU - Symeonidis, Panagiotis PY - 2009/// UR - http://dx.doi.org/10.1007/978-1-4419-0221-4_39 ER -