Evaluating Tag Recommendations for E-Book Annotation Using a Semantic Similarity Metric

In this paper, we present our work to support publishers and editors in finding descriptive tags for e-books through tag recommendations. We propose a hybrid tag recommendation system for e-books, which leverages search query terms from Amazon users and e-book metadata, which is assigned by publishers and editors. Our idea is to mimic the vocabulary of users in Amazon, who search for and review e-books, and to combine these search terms with editor tags in a hybrid tag recommendation approach. In total, we evaluate 19 tag recommendation algorithms on the review content of Amazon users, which reflects the readers' vocabulary. Our results show that we can improve the performance of tag recommender systems for e-books both concerning tag recommendation accuracy, diversity as well as a novel semantic similarity metric, which we also propose in this paper.

[1]  John Riedl,et al.  Tagsplanations: explaining recommendations using tags , 2009, IUI.

[2]  Alejandro Bellogín,et al.  Content-based recommendation in social tagging systems , 2010, RecSys '10.

[3]  Dominik Kowald,et al.  The Influence of Frequency, Recency and Semantic Context on the Reuse of Tags in Social Tagging Systems , 2016, HT.

[4]  Le Zhao,et al.  Term necessity prediction , 2010, CIKM.

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

[6]  Shaghayegh Sahebi,et al.  Recommender Systems: Sources of Knowledge and Evaluation Metrics , 2013 .

[7]  Juan Enrique Ramos,et al.  Using TF-IDF to Determine Word Relevance in Document Queries , 2003 .

[8]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[9]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation , 1997, CACM.

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

[11]  Dominik Kowald,et al.  The TagRec Framework as a Toolkit for the Development of Tag-Based Recommender Systems , 2017, UMAP.

[12]  Tobias Höllerer,et al.  TasteWeights: a visual interactive hybrid recommender system , 2012, RecSys.

[13]  Barry Smyth,et al.  Similarity vs. Diversity , 2001, ICCBR.

[14]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[15]  Pasquale Lops,et al.  Content-based and collaborative techniques for tag recommendation: an empirical evaluation , 2012, Journal of Intelligent Information Systems.

[16]  Rodrygo L. T. Santos,et al.  Topic diversity in tag recommendation , 2013, RecSys.

[17]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[18]  Arkaitz Zubiaga,et al.  Tags vs shelves: from social tagging to social classification , 2011, HT '11.

[19]  Lars Schmidt-Thieme,et al.  Collaborative Tag Recommendations , 2007, GfKl.

[20]  Dominik Kowald,et al.  Evaluating Tag Recommender Algorithms in Real-World Folksonomies: A Comparative Study , 2015, RecSys.

[21]  M. de Rijke,et al.  Short Text Similarity with Word Embeddings , 2015, CIKM.

[22]  Mirella Lapata,et al.  Automatic Evaluation of Information Ordering: Kendall’s Tau , 2006, CL.