Serendipitous Recommendation for Scholarly Papers Considering Relations Among Researchers Kazunari Sugiyama, Min-Yen Kan National University of Singapore.

Slides:

Advertisements

Similar presentations

Recommender System A Brief Survey.

Advertisements

1 Weiren Yu 1,2, Xuemin Lin 1, Wenjie Zhang 1 1 University of New South Wales 2 NICTA, Australia Towards Efficient SimRank Computation over Large Networks.

Prediction Modeling for Personalization & Recommender Systems Bamshad Mobasher DePaul University Bamshad Mobasher DePaul University.

Linking Entities in #Microposts ROMIL BANSAL, SANDEEP PANEM, PRIYA RADHAKRISHNAN, MANISH GUPTA, VASUDEVA VARMA INTERNATIONAL INSTITUTE OF INFORMATION TECHNOLOGY,

Towards Twitter Context Summarization with User Influence Models Yi Chang et al. WSDM 2013 Hyewon Lim 21 June 2013.

Robust Extraction of Named Entity Including Unfamiliar Word Masatoshi Tsuchiya, Shinya Hida & Seiichi Nakagawa Reporter: Chia-Ying Lee Advisor: Prof. Hsin-Hsi.

计算机科学与技术学院 Chinese Semantic Role Labeling with Dependency-driven Constituent Parse Tree Structure Hongling Wang, Bukang Wang Guodong Zhou NLP Lab, School.

1 JCDL 2011 Report Kazunari Sugiyama WING meeting 19 th August, 2011.

Product Review Summarization from a Deeper Perspective Duy Khang Ly, Kazunari Sugiyama, Ziheng Lin, Min-Yen Kan National University of Singapore.

Funding Networks Abdullah Sevincer University of Nevada, Reno Department of Computer Science & Engineering.

Unsupervised Feature Selection for Multi-Cluster Data Deng Cai et al, KDD 2010 Presenter: Yunchao Gong Dept. Computer Science, UNC Chapel Hill.

Faculty of Computer Science © 2006 CMPUT 605March 31, 2008 Towards Applying Text Mining and Natural Language Processing for Biomedical Ontology Acquisition.

Query-Based Outlier Detection in Heterogeneous Information Networks Jonathan Kuck 1, Honglei Zhuang 1, Xifeng Yan 2, Hasan Cam 3, Jiawei Han 1 1 University.

CONTENT-BASED BOOK RECOMMENDING USING LEARNING FOR TEXT CATEGORIZATION TRIVIKRAM BHAT UNIVERSITY OF TEXAS AT ARLINGTON DATA MINING CSE6362 BASED ON PAPER.

POTENTIAL RELATIONSHIP DISCOVERY IN TAG-AWARE MUSIC STYLE CLUSTERING AND ARTIST SOCIAL NETWORKS Music style analysis such as music classification and clustering.

Longbiao Kang, Baotian Hu, Xiangping Wu, Qingcai Chen, and Yan He Intelligent Computing Research Center, School of Computer Science and Technology, Harbin.

Item-based Collaborative Filtering Recommendation Algorithms

Automated malware classification based on network behavior

The 2nd International Conference of e-Learning and Distance Education, 21 to 23 February 2011, Riyadh, Saudi Arabia Prof. Dr. Torky Sultan Faculty of Computers.

Rui Yan, Yan Zhang Peking University

CS598CXZ Course Summary ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.

Slide Image Retrieval: A Preliminary Study Guo Min Liew and Min-Yen Kan National University of Singapore Web IR / NLP Group (WING)

Challenges in Information Retrieval and Language Modeling Michael Shepherd Dalhousie University Halifax, NS Canada.

A methodology for developing new technology ideas to avoid

Tag Clouds Revisited Date : 2011/12/12 Source : CIKM’11 Speaker : I- Chih Chiu Advisor : Dr. Koh. Jia-ling 1.

1 Formal Models for Expert Finding on DBLP Bibliography Data Presented by: Hongbo Deng Co-worked with: Irwin King and Michael R. Lyu Department of Computer.

Multimodal Alignment of Scholarly Documents and Their Presentations Bamdad Bahrani JCDL 2013 Submission Feb 2013.

PAUL ALEXANDRU CHIRITA STEFANIA COSTACHE SIEGFRIED HANDSCHUH WOLFGANG NEJDL 1* L3S RESEARCH CENTER 2* NATIONAL UNIVERSITY OF IRELAND PROCEEDINGS OF THE.

Automatic Detection of Tags for Political Blogs Khairun-nisa Hassanali Vasileios Hatzivassiloglou The University.

This work is supported by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center contract number.

11 A Hybrid Phish Detection Approach by Identity Discovery and Keywords Retrieval Reporter: 林佳宜 /10/17.

A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation D. Bollegala, N. Okazaki and M. Ishizuka The University.

New and Improved: Modeling Versions to Improve App Recommendation Date: 2014/10/2 Author: Jovian Lin, Kazunari Sugiyama, Min-Yen Kan, Tat-Seng Chua Source:

Developing Trust Networks based on User Tagging Information for Recommendation Making Touhid Bhuiyan et al. WISE May 2012 SNU IDB Lab. Hyunwoo Kim.

Recommending Twitter Users to Follow Using Content and Collaborative Filtering Approaches John HannonJohn Hannon, Mike Bennett, Barry SmythBarry Smyth.

Domain-Specific Iterative Readability Computation Jin Zhao 13/05/2011.

LexPageRank: Prestige in Multi- Document Text Summarization Gunes Erkan and Dragomir R. Radev Department of EECS, School of Information University of Michigan.

Opinion Holders in Opinion Text from Online Newspapers Youngho Kim, Yuchul Jung and Sung-Hyon Myaeng Reporter: Chia-Ying Lee Advisor: Prof. Hsin-Hsi Chen.

Personalized Course Navigation Based on Grey Relational Analysis Han-Ming Lee, Chi-Chun Huang, Tzu- Ting Kao (Dept. of Computer Science and Information.

1 Intelligente Analyse- und Informationssysteme Frank Reichartz, Hannes Korte & Gerhard Paass Fraunhofer IAIS, Sankt Augustin, Germany Dependency Tree.

Personalized Interaction With Semantic Information Portals Eric Schwarzkopf DFKI

27-31 May 2008LREC 2008 (Marrakech, Morocco)1 The ACL ARC Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics.

Content-Based Image Retrieval Using Block Discrete Cosine Transform Presented by Te-Wei Chiang Department of Information Networking Technology Chihlee.

Scientific Paper Recommendation Emphasizing Each Researcher’s Most Recent Research Topic Kazunari Sugiyama 8 th January, 2010.

Semi-automatic Product Attribute Extraction from Store Website

Citation Provenance FYP/Research Update WING Meeting 28 Sept 2012 Heng Low Wee 1/5/

Automating Readers’ Advisory to Make Book Recommendations for K-12 Readers by Alicia Wood.

Post-Ranking query suggestion by diversifying search Chao Wang.

Divided Pretreatment to Targets and Intentions for Query Recommendation Reporter: Yangyang Kang /23.

1 JCDL 2013 Report Kazunari Sugiyama WING meeting 23 rd August, 2013.

User Modeling and Recommender Systems: recommendation algorithms

Artificial Intelligence Techniques Internet Applications 4.

1 Discovering Web Communities in the Blogspace Ying Zhou, Joseph Davis (HICSS 2007)

Improving Collaborative Filtering by Incorporating Customer Reviews Hui Hui Supervisor Prof Min-Yen Kan Dr. Kazunari Sugiyama 1.

Concept-Based Analysis of Scientific Literature Chen-Tse Tsai, Gourab Kundu, Dan Roth UIUC.

A Recommender System based on Tag and Time Information for Social Tagging Systems Nan Zheng and Qiudan Li (Chinese Academy of Sciences) Expert Systems.

Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.

Intelligent Database Systems Lab Presenter: YU-TING LU Authors: Yong-Bin Kang, Pari Delir Haghighi, Frada Burstein ESA CFinder: An intelligent key.

MINING DEEP KNOWLEDGE FROM SCIENTIFIC NETWORKS

School of Computer Science & Engineering

CSE5544 Final Project Interactive Visualization Tool(s) for IEEE Vis Publication Exploration and Analysis Team Name: Publication Miner Team Members:

CSE5544 Final Project Interactive Visualization Tool(s) for IEEE Vis Publication Exploration and Analysis Team Name: Publication Miner Team Members:

E-Commerce Theories & Practices

Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning Shizhu He, Cao liu, Kang Liu and Jun Zhao.

Location Recommendation — for Out-of-Town Users in Location-Based Social Network Yina Meng.

Liang Zheng and Yuzhong Qu

Navi 下一步工作的设想郑亮 6.6.

RECOMMENDER SYSTEMS WITH SOCIAL REGULARIZATION

Mashup Service Recommendation based on User Interest and Service Network Buqing Cao ICWS2013, IJWSR.

Topic: Semantic Text Mining

Presentation transcript:

Serendipitous Recommendation for Scholarly Papers Considering Relations Among Researchers Kazunari Sugiyama, Min-Yen Kan National University of Singapore

Introduction 2 WING, NUS Candidate papers to recommend User profile Recommended papers Papers similar to each user’s profile are recommended. Researcher Content-based Recommendation

Introduction 3 WING, NUS (‘11) [No published papers in the past] Publication list Junior researcher (having only one recently published paper) Senior researcher (having several past published papers) (‘11) Publication list (‘01)(‘02) Serendipitous recommendation is important. Broaden their range of research interests. Seek to apply their knowledge towards other areas. [Sugiyama and Kan, JCDL’10]

Attend seminars Introduction WING, NUS Serendipitous discovery: Interactions with others play an important role. User profile construction for serendipitous recommendation with others I.Dissimilar users II.Co-author network We can also use this approach even if the research topic is different from ours! 4 Advice from colleagues How about using this technique? That’s nice idea!

User 1 User 2 User 3 User n User profile generated from published history of papers User profile for serendipitous recommendation User 4 (Sim: 0.16) Weight: 1/(0.16+1) User 10 (Sim: 0.26) Weight: 1/(0.26+1) User 5 (Sim: 0.21) Weight: 1/(0.21+1) User 1 (Sim: 0.32) Weight: 1/(0.32+1) User 1 (Sim: 0.14) Weight: 1/(0.14+1) User profile for serendipitous recommendation User 7 (Sim: 0.25) Weight: 1/(0.25+1) User profile for serendipitous recommendation User 6 (Sim: 0.07) Weight: 1/(0.07+1) User 2 (Sim: 0.12) Weight: 1/(0.12+1) User profile for serendipitous recommendation User Profile Construction via Dissimilar Users (DU) 5

User Profile Construction via Co-author Network (CAN) 6 Weighting scheme (W1) Linear Combination (LC) (W2) Reciprocal of Path Length (RCP-PL) (W3) Reciprocal of Similarity (RCP-SIM) (W4) Product of W2 and W3 (RCP-PLSIM) Y.-I. Lin J.-T. Yoon S.-B. Park J.-L. Cao S-.H. Kim C.-Y. Woo Y. Kang D.-W. Song Y.-C. Park S-.Y. Nam R-.K. Lee T. Cong G. Okoshi 3 4 H.-W. Rhee 2 Consider only radial network from the target researcher, “Y.I. Lin”

Basic User Profile Construction (Junior Researchers) 7 WING, NUS Weighting scheme Linear combination Cosine similarity Reciprocal of published year

Basic User Profile Construction (Senior Researchers) 8 WING, NUS Forgetting factor Weighting scheme Linear combination Cosine similarity Reciprocal of published year

Experiments Experimental Data Researchers 15 junior researchers 13 senior researchers NLP and IR researchers who have publication lists in DBLP Candidate Papers to Recommend ACL Anthology Reference Corpus [Bird et al., LREC’08] Includes information about citation and reference papers 9 Evaluation Measure Normalized Item Novelty

Normalized Item Novelty Item novelty (ITN) [Zhang and Hurley, RecSys’08] 10 WING, NUS : User profile : Feature vector of the candidate paper to recommend Monotone increasing Normalized item novelty (nITN) Avoid monotone increasing

Results with Dissimilar Users (DU) 11 [Item [Junior researchers] 12 [Senior researchers] 9 User profiles that contain a variety of topics can be constructed by using more dissimilar users.

Results with the Co-author Network (CAN) 12 [Item [Senior researchers] 3 [Junior researchers] 3 [The best in (DU): 0.644] [The best in (DU): 0.645] (CAN) is more effective approach to constructing user profile for serendipitous recommendation rather than (DU).

Examples of Serendipitous Recommendation 13 WING, NUS Recommended topics Junior researcher (Major research topic: discourse analysis) Noun phrase chunking Collocation Term Recognition Senior researcher (Major research topic: sentiment analysis) Knowledge acquisition Relation extraction in named entities Relation extraction in biomedical text It is highly possible that he can discover something new and helpful.

Conclusion Propose constructing user profile for serendipitous recommendation that considers relations among researchers - Dissimilar users - Co-author network Observe serendipitous nature of the recommendation 14 WING, NUS Future Work Construct user profile that provides highly accurate recommendation of serendipitous papers Expand the kinds of candidate papers to recommend Thank you very much!