《电子商务 E-business》阅读文献：A Two-Level Learning Hierarchy of Concept Based Keyword Extraction for Tag Recommendations

Folke Eisterlehner Andreas Hotho Robert Jaschke(Eds ECML PKDD Discovery Challenge 2009(DC09) International Workshop at the european Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases Bled, Slovenia, September 7th, 2009 ECML PKDD 2009 nd Prine

Folke Eisterlehner Andreas Hotho Robert J¨aschke (Eds.) ECML PKDD Discovery Challenge 2009 (DC09) International Workshop at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases in Bled, Slovenia, September 7th, 2009

Table of contents Table of Contents Relational Classification for Personalized Tag Recommendation Leandro Balby Marinho, Christine Preisach, and Lars Schmidt Thieme Measuring Vertex Centrality in Co-occurrence Graphs for Online Social Tag Recommendation lvdn Cantador, David vallet, and Joemon M. Jose ocial Tag Prediction Base on Supervised Ranking Model Hao Cao, Maogiang Xie, Lian Xue, Chunhua Liu, Fei Teng, and Yalou huang Tag Recommendations Based on Tracking Social Bookmarking Systems A Fast effective Multi-Channeled Tag Recommender Jonathan Gemmell, Maryam Ramezani, Thomas Schimoler, Laura Christiansen. and Bamshad Mobasher A modified and fast Perceptron learning rule and its use for Tag Recommendations in Social Bookmarking Systems Anestis Ghanogiannis and Theodore Kalamboukis Discriminative Clustering for Content-Based Tag Recommendation in Social Bookmarking System Malik Tahir Hassan. Asim Karim. Suresh Manandhar, and James Time based Tag Recommendation using Direct and Extended Users Sets. 99 reza lofciu and Gianluca Demartini A Weighting Scheme for Tag Recommendation in Social Bookmarking 109 Sanghun Ju and Kyu-Baek Hwang ARKTis-A Fast Tag Recommender System Based On Heuristics 119 mas Kleinbauer and sebastian germein Tag Recommendation using Probabilistic Topic Models Ralf Krestel and Peter Fankhauser

Table of Contents Table of Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 Preface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 Relational Classification for Personalized Tag Recommendation . . . . . . . . . 7 Leandro Balby Marinho, Christine Preisach, and Lars Schmidt￾Thieme Measuring Vertex Centrality in Co-occurrence Graphs for Online Social Tag Recommendation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 Iv´an Cantador, David Vallet, and Joemon M. Jose Social Tag Prediction Base on Supervised Ranking Model . . . . . . . . . . . . . . 35 Hao Cao, Maoqiang Xie, Lian Xue, Chunhua Liu, Fei Teng, and Yalou Huang Tag Recommendations Based on Tracking Social Bookmarking Systems . . 49 Szymon Chojnacki A Fast Effective Multi-Channeled Tag Recommender . . . . . . . . . . . . . . . . . . 59 Jonathan Gemmell, Maryam Ramezani, Thomas Schimoler, Laura Christiansen, and Bamshad Mobasher A modified and fast Perceptron learning rule and its use for Tag Recommendations in Social Bookmarking Systems . . . . . . . . . . . . . . . . . . . . 71 Anestis Gkanogiannis and Theodore Kalamboukis Discriminative Clustering for Content-Based Tag Recommendation in Social Bookmarking Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85 Malik Tahir Hassan, Asim Karim, Suresh Manandhar, and James Cussens Time based Tag Recommendation using Direct and Extended Users Sets . 99 Tereza Iofciu and Gianluca Demartini A Weighting Scheme for Tag Recommendation in Social Bookmarking Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109 Sanghun Ju and Kyu-Baek Hwang ARKTiS - A Fast Tag Recommender System Based On Heuristics. . . . . . . 119 Thomas Kleinbauer and Sebastian Germesin Tag Recommendation using Probabilistic Topic Models . . . . . . . . . . . . . . . . 131 Ralf Krestel and Peter Fankhauser

A Probabilistic Ranking Approach for Tag Recommendation Zhen liao, Maogiang Xie, Hao Cao, and Yalou huang Tag Sources for Recommendation in Collaborative Tagging Systems 157 Marek Lipczak, Yeming Hu, Yael Kollet, and evangelos Milios Collaborative Tag Recommendation System based on Logistic Regression 173 E. Montanes, J.R. Quevedo, I. Diaz, and. ranilla Content- and Graph-based Tag Recommendation: Two Variations Johannes Mrosek, Stefan Bussmann, Hendrik Albers, Kai Posdziech, Benedikt Hengefeld, Nils Opperman, Stefan Robert, and Gerrit S A Two-Level Learning Hierarchy of Concept Based Keyword Extraction for Tag recommendations Hendri Muri and Klaus Bern TaR: a Social Tag Recommender System Cataldo Musto, Fedelucio Narducci, marco de Gemmis, Pasquale Combining Tag Recommendations Based on User Histo lari nieminen Factor Models for Tag Recommendation in BibSonom Steffen Rendle and Lars Schmidt- Thieme Content-based and Graph-based Tag Suggestion 243 Xiance Si, Zhiyuan Liu, Peng Li, Qiria Jiang, and Maosong Sun RSDC09: Tag Recommendation Using Keywords and Association Rules. 261 Wang, Liangjie Hong and Brian D. Davis Understanding the user: Personomy translation for tag recommendation. 275 Robert Wetzker. Alan Said. and Carsten Zimmermann A Tag Recommendation System based on contents Ning Zhang, Yuan Zhang, and ie Tang A Collaborative Filtering Tag Recommendation System based on Graph. 297 Yuan Zhang, Ning Zhang, and Jie Tang

A Probabilistic Ranking Approach for Tag Recommendation . . . . . . . . . . . 143 Zhen Liao, Maoqiang Xie, Hao Cao, and Yalou Huang Tag Sources for Recommendation in Collaborative Tagging Systems . . . . . 157 Marek Lipczak, Yeming Hu, Yael Kollet, and Evangelos Milios Collaborative Tag Recommendation System based on Logistic Regression 173 E. Monta˜n´es, J. R. Quevedo, I. D´ıaz, and J. Ranilla Content- and Graph-based Tag Recommendation: Two Variations . . . . . . . 189 Johannes Mrosek, Stefan Bussmann, Hendrik Albers, Kai Posdziech, Benedikt Hengefeld, Nils Opperman, Stefan Robert, and Gerrit Spira A Two-Level Learning Hierarchy of Concept Based Keyword Extraction for Tag Recommendations. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 201 Hendri Murfi and Klaus Obermayer STaR: a Social Tag Recommender System . . . . . . . . . . . . . . . . . . . . . . . . . . . . 215 Cataldo Musto, Fedelucio Narducci, Marco de Gemmis, Pasquale Lops, and Giovanni Semeraro Combining Tag Recommendations Based on User History . . . . . . . . . . . . . . 229 Ilari T. Nieminen Factor Models for Tag Recommendation in BibSonomy . . . . . . . . . . . . . . . . 235 Steffen Rendle and Lars Schmidt-Thieme Content-based and Graph-based Tag Suggestion . . . . . . . . . . . . . . . . . . . . . . 243 Xiance Si, Zhiyuan Liu, Peng Li, Qixia Jiang, and Maosong Sun RSDC’09: Tag Recommendation Using Keywords and Association Rules . 261 Jian Wang, Liangjie Hong and Brian D. Davison Understanding the user: Personomy translation for tag recommendation . 275 Robert Wetzker, Alan Said, and Carsten Zimmermann A Tag Recommendation System based on contents . . . . . . . . . . . . . . . . . . . . 285 Ning Zhang, Yuan Zhang, and Jie Tang A Collaborative Filtering Tag Recommendation System based on Graph . 297 Yuan Zhang, Ning Zhang, and Jie Tang

Preface Since 1999 the ECML PKDD embraces the tradition of organizing a Discovery Challenge, allowing researchers to develop and test algorithms for novel and eal world datasets. This year's Discovery Challenge presents a dataset from he field of social bookmarking to deal with the recommendation of tags. The results submitted by the challenge's participants are presented at an ECML PKDD workshop on September 7th, 2009, in Bled, Slovenia. The provided dataset has been created using data of the social bookmark and publication sharing system BibSonomy, 2 operated by the organizers of the allenge. The training data was released on March 25th 2009, the test data or July 6th. The participants had time until July &th to submit their results. This gave researchers 14 weeks time to tune their algorithms on a snapshot of a real world folksonomy dataset and 48 hours to compute results on the test data To support the user during the tagging process and to facilitate the tagging, BibSonomy includes a tag recommender. When a user finds an interesting web page(or publication) and posts it to BibSonomy, the system offers up to five recommended tags on the posting page. The goal of the challenge is to learn a model which effectively predicts the keywords a user has in mind when describing a web page (or publication). We divided the problem into three tasks, each of which focusing on a certain aspect. All three tasks get the same dataset fo training. It is a snapshot of Bibsonomy until December 31st 2008. The dataset leaned and consists of two parts, the core part and the complete snapshot The test dataset is different for each task Task 1: Content-Based Tag Recommendations. The test data for this task con- tains posts, whose user, resource or tags are not contained in the post-core at level 2 of the training data. Thus, methods which can't produce tag recommen- dations for new resources or are unable to suggest new tags very probably wor produce good results here Task 2: Graph-Based Recommendations. This task is especially intended fc methods relying on the graph structure of the training data only. The user. resource, and tags of each post in the test data are all contained in the training datas post-core at level 2 Task 3: Online Tag Recommendations. This is a bonus task which will take place after Tasks 1 and 2. The participants shall implement a recommendation servic which can be called via Http by Bibsonomy'S recommender infrastructure when a user posts a bookmark or publication. All participating recommenders are called on each posting process, one of them is chosen to actually deliver the results to the user. We can then measure the performance of the recommenders in an online setting, where timeouts are important and where we can measure which tags the user has clicked on http://www.kde.cs.uni-kassel.de/ws/dc09 http://www.bibsonomy.org

Preface Since 1999 the ECML PKDD embraces the tradition of organizing a Discovery Challenge, allowing researchers to develop and test algorithms for novel and real world datasets. This year’s Discovery Challenge1 presents a dataset from the field of social bookmarking to deal with the recommendation of tags. The results submitted by the challenge’s participants are presented at an ECML PKDD workshop on September 7th, 2009, in Bled, Slovenia. The provided dataset has been created using data of the social bookmark and publication sharing system BibSonomy,2 operated by the organizers of the challenge. The training data was released on March 25th 2009, the test data on July 6th. The participants had time until July 8th to submit their results. This gave researchers 14 weeks time to tune their algorithms on a snapshot of a real world folksonomy dataset and 48 hours to compute results on the test data. To support the user during the tagging process and to facilitate the tagging, BibSonomy includes a tag recommender. When a user finds an interesting web page (or publication) and posts it to BibSonomy, the system offers up to five recommended tags on the posting page. The goal of the challenge is to learn a model which effectively predicts the keywords a user has in mind when describing a web page (or publication). We divided the problem into three tasks, each of which focusing on a certain aspect. All three tasks get the same dataset for training. It is a snapshot of BibSonomy until December 31st 2008. The dataset is cleaned and consists of two parts, the core part and the complete snapshot. The test dataset is different for each task. Task 1: Content-Based Tag Recommendations. The test data for this task con￾tains posts, whose user, resource or tags are not contained in the post-core at level 2 of the training data. Thus, methods which can’t produce tag recommen￾dations for new resources or are unable to suggest new tags very probably won’t produce good results here. Task 2: Graph-Based Recommendations. This task is especially intended for methods relying on the graph structure of the training data only. The user, resource, and tags of each post in the test data are all contained in the training data’s post-core at level 2. Task 3: Online Tag Recommendations. This is a bonus task which will take place after Tasks 1 and 2. The participants shall implement a recommendation service which can be called via HTTP by BibSonomy’s recommender infrastructure when a user posts a bookmark or publication. All participating recommenders are called on each posting process, one of them is chosen to actually deliver the results to the user. We can then measure the performance of the recommenders in an online setting, where timeouts are important and where we can measure which tags the user has clicked on. 1 http://www.kde.cs.uni-kassel.de/ws/dc09/ 2 http://www.bibsonomy.org 5