@inproceedings{lorince2014supertagger, author = {Lorince, Jared and Zorowitz, Sam and Murdock, Jaimie and Todd, Peter}, interhash = {4af29810e9c882dc18f560527c65de2f}, intrahash = {014abc7dc30e38859c5e8605dce1a8f6}, title = {“Supertagger” Behavior in Building Folksonomies}, year = 2014 } @inproceedings{heckner2009personal, address = {San Jose, CA, USA}, author = {Heckner, Markus and Heilemann, Michael and Wolff, Christian}, booktitle = {Int'l AAAI Conference on Weblogs and Social Media (ICWSM)}, interhash = {f954e699dc6ca2d0abbe5f6ebe166dc7}, intrahash = {d1074484ea350ad88400fe4fc6984874}, month = may, title = {Personal Information Management vs. Resource Sharing: Towards a Model of Information Behaviour in Social Tagging Systems}, year = 2009 } @preprint{beel2013research, author = {Beel, Joeran and Langer, Stefan and Genzmehr, Marcel and Gipp, Bela and Breitinger, Corinna and Nürnberger, Andreas}, interhash = {544758b1fd737c010643f529c4f48ae6}, intrahash = {4afa2bd342dda6b6d32713aa0fbc33bd}, title = {Research Paper Recommender System Evaluation: A Quantitative Literature Survey}, year = 2013 } @article{ohm2009broken, author = {Ohm, Paul}, interhash = {e5f5be1dfe3d7da207c058591e18f58f}, intrahash = {61225f84d3fc809981d436ffe76489b6}, journal = {UCLA Law Review, Vol. 57, p. 1701, 2010}, language = {English}, location = {http://ssrn.com/paper=1450006}, publisher = {SSRN}, title = {Broken Promises of Privacy: Responding to the Surprising Failure of Anonymization}, type = {Accepted Paper Series}, year = 2009 } @article{Ross2009578, abstract = {Facebook is quickly becoming one of the most popular tools for social communication. However, Facebook is somewhat different from other Social Networking Sites as it demonstrates an offline-to-online trend; that is, the majority of Facebook Friends are met offline and then added later. The present research investigated how the Five-Factor Model of personality relates to Facebook use. Despite some expected trends regarding Extraversion and Openness to Experience, results indicated that personality factors were not as influential as previous literature would suggest. The results also indicated that a motivation to communicate was influential in terms of Facebook use. It is suggested that different motivations may be influential in the decision to use tools such as Facebook, especially when individual functions of Facebook are being considered.}, author = {Ross, Craig and Orr, Emily S. and Sisic, Mia and Arseneault, Jaime M. and Simmering, Mary G. and Orr, R. Robert}, doi = {10.1016/j.chb.2008.12.024}, interhash = {98f45e3865f7e4802258347ee91e678b}, intrahash = {fbcbb77a298da03d1e2d8bcd9ac3e0b4}, issn = {0747-5632}, journal = {Computers in Human Behavior}, note = {Including the Special Issue: State of the Art Research into Cognitive Load Theory}, number = 2, pages = {578 - 586}, title = {Personality and motivations associated with Facebook use}, url = {http://www.sciencedirect.com/science/article/pii/S0747563208002355}, volume = 25, year = 2009 } @inproceedings{McNee:2006:DLS:1180875.1180903, abstract = {If recommenders are to help people be more productive, they need to support a wide variety of real-world information seeking tasks, such as those found when seeking research papers in a digital library. There are many potential pitfalls, including not knowing what tasks to support, generating recommendations for the wrong task, or even failing to generate any meaningful recommendations whatsoever. We posit that different recommender algorithms are better suited to certain information seeking tasks. In this work, we perform a detailed user study with over 130 users to understand these differences between recommender algorithms through an online survey of paper recommendations from the ACM Digital Library. We found that pitfalls are hard to avoid. Two of our algorithms generated 'atypical' recommendations recommendations that were unrelated to their input baskets. Users reacted accordingly, providing strong negative results for these algorithms. Results from our 'typical' algorithms show some qualitative differences, but since users were exposed to two algorithms, the results may be biased. We present a wide variety of results, teasing out differences between algorithms. Finally, we succinctly summarize our most striking results as "Don't Look Stupid" in front of users.}, acmid = {1180903}, address = {New York, NY, USA}, author = {McNee, Sean M. and Kapoor, Nishikant and Konstan, Joseph A.}, booktitle = {Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work}, doi = {10.1145/1180875.1180903}, interhash = {24be686d042a3a4a710d9ff22dee0f2e}, intrahash = {7775150ca225770019bd94db9be5db40}, isbn = {1-59593-249-6}, location = {Banff, Alberta, Canada}, numpages = {10}, pages = {171--180}, publisher = {ACM}, series = {CSCW '06}, title = {Don't look stupid: avoiding pitfalls when recommending research papers}, url = {http://doi.acm.org/10.1145/1180875.1180903}, year = 2006 } @article{Hanhijärvi2009, abstract = {Mining graph data is an active research area. Several data mining methods and algorithms have been proposed to identify structures from graphs; still, the evaluation of those results is lacking. Within the framework of statistical hypothesis testing, we focus in this paper on randomization techniques for unweighted undirected graphs. Randomization is an important approach to assess the statistical significance of data mining results. Given an input graph, our randomization method will sample data from the class of graphs that share certain structural properties with the input graph. Here we describe three alternative algorithms based on local edge swapping and Metropolis sampling. We test our framework with various graph data sets and mining algorithms for two applications, namely graph clustering and frequent subgraph mining.}, author = {Hanhijärvi, Sami and Garriga, Gemma and Puolamäki, Kai}, institution = {PASCAL EPrints [http://eprints.pascal-network.org/perl/oai2] (United Kingdom)}, interhash = {3124a1f618340ea80417804c79f2d5a4}, intrahash = {a48be9257b9ca84ad9a426d4ff55d309}, location = {http://www.scientificcommons.org/42170854}, title = {Randomization techniques for graphs}, url = {http://eprints.pascal-network.org/archive/00004486/}, year = 2009 } @inproceedings{Rendle:2010:FPM:1772690.1772773, abstract = {Recommender systems are an important component of many websites. Two of the most popular approaches are based on matrix factorization (MF) and Markov chains (MC). MF methods learn the general taste of a user by factorizing the matrix over observed user-item preferences. On the other hand, MC methods model sequential behavior by learning a transition graph over items that is used to predict the next action based on the recent actions of a user. In this paper, we present a method bringing both approaches together. Our method is based on personalized transition graphs over underlying Markov chains. That means for each user an own transition matrix is learned - thus in total the method uses a transition cube. As the observations for estimating the transitions are usually very limited, our method factorizes the transition cube with a pairwise interaction model which is a special case of the Tucker Decomposition. We show that our factorized personalized MC (FPMC) model subsumes both a common Markov chain and the normal matrix factorization model. For learning the model parameters, we introduce an adaption of the Bayesian Personalized Ranking (BPR) framework for sequential basket data. Empirically, we show that our FPMC model outperforms both the common matrix factorization and the unpersonalized MC model both learned with and without factorization.}, acmid = {1772773}, address = {New York, NY, USA}, author = {Rendle, Steffen and Freudenthaler, Christoph and Lars, Schmidt-Thieme}, booktitle = {Proceedings of the 19th international conference on World wide web}, doi = {10.1145/1772690.1772773}, interhash = {578c4d7bb47620c5b943d9533ae2ae5f}, intrahash = {a806788d8f8f9259624a853551e40c30}, isbn = {978-1-60558-799-8}, location = {Raleigh, North Carolina, USA}, numpages = {10}, pages = {811--820}, publisher = {ACM}, series = {WWW '10}, title = {Factorizing personalized Markov chains for next-basket recommendation}, url = {http://doi.acm.org/10.1145/1772690.1772773}, year = 2010 } @inproceedings{Jin:2003:CFD:956863.956922, abstract = {In this paper, we describe a new model for collaborative filtering. The motivation of this work comes from the fact that two users with very similar preferences on items may have very different rating schemes. For example, one user may tend to assign a higher rating to all items than another user. Unlike previous models of collaborative filtering, which determine the similarity between two users only based on their rating performance, our model treats the user's preferences on items separately from the user's rating scheme. More specifically, for each user, we build two separate models: a preference model capturing which items are favored by the user and a rating model capturing how the user would rate an item given the preference information. The similarity of two users is computed based on the underlying preference model, instead of the surface ratings. We compare the new model with several representative previous approaches on two data sets. Experiment results show that the new model outperforms all the previous approaches that are tested consistently on both data sets.}, acmid = {956922}, address = {New York, NY, USA}, author = {Jin, Rong and Si, Luo and Zhai, ChengXiang and Callan, Jamie}, booktitle = {Proceedings of the twelfth international conference on Information and knowledge management}, doi = {10.1145/956863.956922}, interhash = {e12feb03e54e75b093319ec861c5dbb5}, intrahash = {1da2fda40d4a93cb43c7f2f058c0cd3f}, isbn = {1-58113-723-0}, location = {New Orleans, LA, USA}, numpages = {8}, pages = {309--316}, publisher = {ACM}, series = {CIKM '03}, title = {Collaborative filtering with decoupled models for preferences and ratings}, url = {http://doi.acm.org/10.1145/956863.956922}, year = 2003 } @inproceedings{hu2004mining, acmid = {1014073}, address = {New York, NY, USA}, author = {Hu, Minqing and Liu, Bing}, booktitle = {Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining}, doi = {http://doi.acm.org/10.1145/1014052.1014073}, interhash = {fa4cfdb6168dd55d8fb419fef992c631}, intrahash = {88f1001cb2a901275383ad63b87d61fc}, isbn = {1-58113-888-1}, location = {Seattle, WA, USA}, numpages = {10}, pages = {168--177}, publisher = {ACM}, series = {KDD '04}, title = {Mining and summarizing customer reviews}, url = {http://doi.acm.org/10.1145/1014052.1014073}, year = 2004 } @article{springerlink:10.1007/s00778-010-0204-8, abstract = {Graph conductance queries, also known as personalized PageRank and related to random walks with restarts, were originally proposed to assign a hyperlink-based prestige score to Web pages. More general forms of such queries are also very useful for ranking in entity-relation (ER) graphs used to represent relational, XML and hypertext data. Evaluation of PageRank usually involves a global eigen computation. If the graph is even moderately large, interactive response times may not be possible. Recently, the need for interactive PageRank evaluation has increased. The graph may be fully known only when the query is submitted. Browsing actions of the user may change some inputs to the PageRank computation dynamically. In this paper, we describe a system that analyzes query workloads and the ER graph, invests in limited offline indexing, and exploits those indices to achieve essentially constant-time query processing, even as the graph size scales. Our techniques—data and query statistics collection, index selection and materialization, and query-time index exploitation—have parallels in the extensive relational query optimization literature, but is applied to supporting novel graph data repositories. We report on experiments with five temporal snapshots of the CiteSeer ER graph having 74–702 thousand entity nodes, 0.17–1.16 million word nodes, 0.29–3.26 million edges between entities, and 3.29–32.8 million edges between words and entities. We also used two million actual queries from CiteSeer’s logs. Queries run 3–4 orders of magnitude faster than whole-graph PageRank, the gap growing with graph size. Index size is smaller than a text index. Ranking accuracy is 94–98% with reference to whole-graph PageRank.}, address = {Berlin / Heidelberg}, affiliation = {IIT Bombay, Powai, Mumbai, Maharashtra India}, author = {Chakrabarti, Soumen and Pathak, Amit and Gupta, Manish}, doi = {10.1007/s00778-010-0204-8}, interhash = {96a2d92f703a13f77bae8f56372f3e1b}, intrahash = {dcc951cd461fe1c454db7a738429d421}, issn = {1066-8888}, journal = {The VLDB Journal}, keyword = {Computer Science}, pages = {1-26}, publisher = {Springer}, title = {Index design and query processing for graph conductance search}, url = {http://dx.doi.org/10.1007/s00778-010-0204-8}, year = 2010 } @inproceedings{Sherchan:2006:FMR:1141277.1141722, acmid = {1141722}, address = {New York, NY, USA}, author = {Sherchan, Wanita and Loke, Seng W. and Krishnaswamy, Shonali}, booktitle = {Proceedings of the 2006 ACM symposium on Applied computing}, doi = {http://doi.acm.org/10.1145/1141277.1141722}, interhash = {6a847312028872dfb07d2472b4e88ca6}, intrahash = {afa80aad5c9222e20177793dfae5945a}, isbn = {1-59593-108-2}, location = {Dijon, France}, numpages = {7}, pages = {1886--1892}, publisher = {ACM}, series = {SAC '06}, title = {A fuzzy model for reasoning about reputation in web services}, url = {http://doi.acm.org/10.1145/1141277.1141722}, year = 2006 } @misc{Xu09relevanceranking, author = {Xu, Jun and Li, Hang and Zhong, Chaoliang}, interhash = {c0a86e1785768ef1f15d5cacc1442597}, intrahash = {4d086714a580d80c68077fcc98656db3}, title = {Relevance Ranking using Kernels}, url = {http://www.google.de/url?sa=t&source=web&cd=2&ved=0CCEQFjAB&url=http%3A%2F%2Fresearch.microsoft.com%2Fpubs%2F81437%2FMSR_TechReport_2009_Kernel4IR.pdf&rct=j&q=Relevance%20Ranking%20using%20Kernels&ei=uzftTM28GMr2sgaO4Y35Dg&usg=AFQjCNFftCUJMs7LgoqEXR2VvT7bQ7FWHw&sig2=H5OBpauNrYXJ0asAFrEuGQ&cad=rja}, year = 2009 } @inproceedings{marinho:ecml2009, abstract = {Collaborative tagging applications allow users to annotate online resources, resulting in a complex three dimensional network of interrelated users, resources and tags often called a folksonom A pivotal challenge of these systems remains the inclusion of the varied information channels introduced by the multi-dimensional folksonomy into recommendation techniques. In this paper we propose a composite tag recommender based upon popularity and collaborative filtering. These recommenders were chosen based on their speed, memory requirements and ability to cover complimentary channels of the folksonomy. Alone these recommenders perform poorly; together they achieve a synergy which proves to be as effective as state of the art tag recommenders.}, address = {Bled, Slovenia}, author = {Gemmell, Jonathan and Ramezani, Maryam and Schimoler, Thomas and Christiansen, Laura and Mobasher, Bamshad}, booktitle = {ECML PKDD Discovery Challenge 2009 (DC09)}, editor = {Eisterlehner, Folke and Hotho, Andreas and Jäschke, Robert}, interhash = {4c9f99e93a8038baad43493c0ba8600f}, intrahash = {cea0f6c4149738eb084852aa6c71b935}, issn = {1613-0073}, month = {September}, publisher = {CEUR Workshop Proceedings}, title = {A Fast Effective Multi-Channeled Tag Recommender}, url = {http://sunsite.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-497/}, volume = 497, year = 2009 } @inproceedings{gemmell2009impact, abstract = {Collaborative tagging applications have become a popular tool allowing Internet users to manage online resources with tags. Most collaborative tagging applications permit unsupervised tagging resulting in tag ambiguity in which a single tag has many different meanings and tag redundancy in which several tags have the same meaning. Common metrics for evaluating tag recommenders may overestimate the utility of ambiguous tags or ignore the appropriateness of redundant tags. Ambiguity and redundancy may even burden the user with additional effort by requiring them to clarify an annotation or forcing them to distinguish between highly related items. In this paper we demonstrate that ambiguity and redundancy impede the evaluation and performance of tag recommenders. Five tag recommendation strategies based on popularity, collaborative filtering and link analysis are explored. We use a cluster-based approach to define ambiguity and redundancy and provide extensive evaluation on three real world datasets.}, address = {New York, NY, USA}, author = {Gemmell, Jonathan and Ramezani, Maryam and Schimoler, Thomas and Christiansen, Laura and Mobasher, Bamshad}, booktitle = {RecSys '09: Proceedings of the third ACM conference on Recommender systems}, doi = {http://doi.acm.org/10.1145/1639714.1639724}, interhash = {15c65045bac07bf5f9f82526aabf716b}, intrahash = {0710acde8c3db11f5dbd63f76bd30dc6}, isbn = {978-1-60558-435-5}, location = {New York, New York, USA}, pages = {45--52}, publisher = {ACM}, title = {The impact of ambiguity and redundancy on tag recommendation in folksonomies}, url = {http://portal.acm.org/citation.cfm?id=1639724}, year = 2009 } @inproceedings{conf/ijcai/GemmellSRM09, author = {Gemmell, Jonathan and Schimoler, Thomas and Ramezani, Maryam and Mobasher, Bamshad}, booktitle = {ITWP}, crossref = {conf/ijcai/2009itwp}, editor = {Anand, Sarabjot S. and Mobasher, Bamshad and Kobsa, Alfred and Jannach, Dietmar}, ee = {http://ceur-ws.org/Vol-528/paper8.pdf}, interhash = {9ce91fd3f0808eb4b750e0d1d68bdaf0}, intrahash = {8b50a08149b62c6fed95fd6e557f89bf}, publisher = {CEUR-WS.org}, series = {CEUR Workshop Proceedings}, title = {Adapting K-Nearest Neighbor for Tag Recommendation in Folksonomies.}, url = {http://dblp.uni-trier.de/db/conf/ijcai/itwp2009.html#GemmellSRM09}, volume = 528, year = 2009 } @book{Gentle:2007, abstract = {Bibliogr. S. [505] - 518}, author = {Gentle, James E.}, interhash = {2156bd85da160d6baf88b187fd1e6230}, intrahash = {fccc8b26fcc1912304600c6410f241e5}, isbn = {978-0-387-70872-0}, opac = {http://opac.bibliothek.uni-kassel.de/DB=1/PPN?PPN=190806516}, publisher = {Springer New York}, title = {Matrix algebra}, url = {http://opac.bibliothek.uni-kassel.de/DB=1/PPN?PPN=190806516}, year = 2007 }