A Rule-Based Flickr Tag Recommendation System

Personalized tag recommendation focuses on helping users find desirable keywords (tags) to annotate Web resources based on both user profiles and main resource characteristics. Flickr is a popular online photo service whose resource sharing system significantly relies on annotations. However, recommending tags to a Flickr user who is annotating a photo is a challenging task as the lack of a controlled tag vocabulary makes the annotation history collection very sparse. This chapter presents a novel rule-based personalized tag recommendation system to suggest additional pertinent tags to partially annotated resources. Rules represent potentially valuable correlations among tag sets. Intuitively, the system should recommend tags highly correlated with the previously annotated tags. Unlike previous rule-based approaches, a Wordnet taxonomy is used to drive the rule mining process and discover rules, called generalized rules, that may contain either single tags or their semantically meaningful aggregations. The use of generalized rules in tag recommendation makes the system (1) more robust to data sparsity and (2) able to capture different viewpoints of the analyzed data. Experiments demonstrate the usefulness of generalized rules in recommending additional tags for real photos published on Flickr.

[1]  Lambert Schomaker,et al.  Variants of the Borda count method for combining ranked classifier hypotheses , 2000 .

[2]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[3]  Siegfried Handschuh,et al.  P-TAG: large scale automatic generation of personalized annotation tags for the web , 2007, WWW '07.

[4]  Jiawei Han,et al.  Mining Multiple-Level Association Rules in Large Databases , 1999, IEEE Trans. Knowl. Data Eng..

[5]  Luca Cagliero,et al.  CAS-Mine: providing personalized services in context-aware applications by means of generalized rules , 2010, Knowledge and Information Systems.

[6]  Marcus Fontoura,et al.  Using annotations in enterprise search , 2006, WWW '06.

[7]  Ramez Elmasri,et al.  Fundamentals of Database Systems, 5th Edition , 2006 .

[8]  Bracha Shapira,et al.  Recommender Systems Handbook , 2015, Springer US.

[9]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[10]  Roelof van Zwol,et al.  Flickr tag recommendation based on collective knowledge , 2008, WWW.

[11]  Ingmar Weber,et al.  Personalized, interactive tag recommendation for flickr , 2008, RecSys '08.

[12]  Evangelos E. Milios,et al.  Efficient Tag Recommendation for Real-Life Data , 2011, TIST.

[13]  Panagiotis Symeonidis,et al.  Tag recommendations based on tensor dimensionality reduction , 2008, RecSys '08.

[14]  Ramakrishnan Srikant,et al.  Mining generalized association rules , 1995, Future Gener. Comput. Syst..

[15]  Jane Yung-jen Hsu,et al.  A Content-Based Method to Enhance Tag Recommendation , 2009, IJCAI.

[16]  Ramez Elmasri,et al.  Fundamentals of Database Systems , 1989 .

[17]  Masaru Kitsuregawa,et al.  FP-tax: tree structure based generalized association rule mining , 2004, DMKD '04.

[18]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[19]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[20]  Thanaruk Theeramunkong,et al.  A new method for finding generalized frequent itemsets in generalized association rule mining , 2002, Proceedings ISCC 2002 Seventh International Symposium on Computers and Communications.

[21]  Yong Yu,et al.  Optimizing web search using social annotations , 2007, WWW '07.

[22]  Mark Sanderson,et al.  Information retrieval system evaluation: effort, sensitivity, and reliability , 2005, SIGIR '05.

[23]  Ralf Krestel,et al.  Latent dirichlet allocation for tag recommendation , 2009, RecSys '09.

[24]  Luca Cagliero,et al.  Support driven opportunistic aggregation for generalized itemset extraction , 2010, 2010 5th IEEE International Conference Intelligent Systems.

[25]  Luca Cagliero,et al.  Generalized association rule mining with constraints , 2012, Inf. Sci..

[26]  James Ze Wang,et al.  Toward Bridging the Annotation-Retrieval Gap in Image Search , 2007, IEEE MultiMedia.

[27]  Adam Rae,et al.  Improving tag recommendation using social networks , 2010, RIAO.

[28]  Ramakrishnan Srikant,et al.  Mining Association Rules with Item Constraints , 1997, KDD.

[29]  Gilad Mishne,et al.  AutoTag: a collaborative approach to automated tag assignment for weblog posts , 2006, WWW '06.

[30]  Hector Garcia-Molina,et al.  Social tag prediction , 2008, SIGIR '08.

[31]  Pasquale Lops,et al.  Content-based Recommender Systems: State of the Art and Trends , 2011, Recommender Systems Handbook.

[32]  Luca Cagliero.  Discovering Temporal Change Patterns in the Presence of Taxonomies , 2013, IEEE Transactions on Knowledge and Data Engineering.

[33]  Andreas Hotho,et al.  Tag Recommendations in Folksonomies , 2007, LWA.