Deeper Into the Folksonomy Graph: FolkRank Adaptations and Extensions for Improved Tag Recommendations

The information contained in social tagging systems is often modelled as a graph of connections between users, items and tags. Recommendation algorithms such as FolkRank, have the potential to leverage complex relationships in the data, corresponding to multiple hops in the graph. We present an in-depth analysis and evaluation of graph models for social tagging data and propose novel adaptations and extensions of FolkRank to improve tag recommendations. We highlight implicit assumptions made by the widely used folksonomy model, and propose an alternative and more accurate graph-representation of the data. Our extensions of FolkRank address the new item problem by incorporating content data into the algorithm, and significantly improve prediction results on unpruned datasets. Our adaptations address issues in the iterative weight spreading calculation that potentially hinder FolkRank's ability to leverage the deep graph as an information source. Moreover, we evaluate the benefit of considering each deeper level of the graph, and present important insights regarding the characteristics of social tagging data in general. Our results suggest that the base assumption made by conventional weight propagation methods, that closeness in the graph always implies a positive relationship, does not hold for the social tagging domain.

[1]  Yang Song,et al.  Real-time automatic tag recommendation , 2008, SIGIR '08.

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

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

[4]  Bamshad Mobasher,et al.  Adapting K-Nearest Neighbor for Tag Recommendation in Folksonomies , 2009, ITWP.

[5]  Abdulmotaleb El-Saddik,et al.  Personalized PageRank vectors for tag recommendations: inside FolkRank , 2011, RecSys '11.

[6]  Andreas Hotho,et al.  Extending FolkRank with content data , 2012, RSWeb@RecSys.

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

[8]  Evangelos E. Milios,et al.  The impact of resource title on tags in collaborative tagging systems , 2010, HT '10.

[9]  Anette Hulth,et al.  Improved Automatic Keyword Extraction Given More Linguistic Knowledge , 2003, EMNLP.

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

[11]  Jianchang Mao,et al.  Towards the Semantic Web: Collaborative Tag Suggestions , 2006 .

[12]  Evangelos E. Milios,et al.  Tag Sources for Recommendation in Collaborative Tagging Systems , 2009, DC@PKDD/ECML.

[13]  Lars Schmidt-Thieme,et al.  Learning optimal ranking with tensor factorization for tag recommendation , 2009, KDD.

[14]  Mitsuru Ishizuka,et al.  Keyword extraction from a single document using word co-occurrence statistical information , 2004, Int. J. Artif. Intell. Tools.

[15]  Christian Bauckhage,et al.  I tag, you tag: translating tags for advanced user models , 2010, WSDM '10.

[16]  Evangelos E. Milios,et al.  World Wide Web site summarization , 2004, Web Intell. Agent Syst..

[17]  R. P. van de Riet,et al.  Applications of Natural Language to Information Systems: Proceedings of the Second International Workshop June 26-28, 1996, Amsterdam, the Netherlands , 1996 .

[18]  Carl Gutwin,et al.  KEA: practical automatic keyphrase extraction , 1999, DL '99.

[19]  B. Mobasher,et al.  Improving Link Analysis for Tag Recommendation in Folksonomies , 2010 .

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

[21]  Feifan Liu,et al.  Unsupervised Approaches for Automatic Keyword Extraction Using Meeting Transcripts , 2009, NAACL.

[22]  Andreas Hotho,et al.  Information Retrieval in Folksonomies: Search and Ranking , 2006, ESWC.

[23]  Ingrid Renz,et al.  Keyword Extraction for Text Characterization , 2003, NLDB.