@article{li2011linking, abstract = {Many data sets contain temporal records over a long period of time; each record is associated with a time stamp and describes some aspects of a realworld entity at that particular time (e.g., author information in DBLP). In such cases, we often wish to identify records that describe the same entity over time and so be able to enable interesting longitudinal data analysis. However, existing record linkage techniques ignore the temporal information and can fall short for temporal data. This paper studies linking temporal records. First, we apply time decay to capture the effect of elapsed time on entity value evolution. Second, instead of comparing each pair of records locally, we propose clustering methods that consider time order of the records and make global decisions. Experimental results show that our algorithms significantly outperform traditional linkage methods on various temporal data sets.}, author = {Li, P. and Luna Dong, X. and Maurino, A. and Srivastava, D.}, interhash = {0d8151346fd512743809aa0cfe591955}, intrahash = {85be46ab943802120277be8f8b6b264b}, issn = {2150-8097}, journal = {Proceedings of the VLDB Endowment}, month = aug, number = 11, pages = {956--967}, title = {Linking Temporal Records}, url = {http://hdl.handle.net/10281/28587}, volume = 4, year = 2011 } @book{srivastava2009mining, abstract = {Giving a broad perspective of the field from numerous vantage points, 'Text Mining' focuses on statistical methods for text mining and analysis. It examines methods to automatically cluster and classify text documents and applies these methods in a variety of areas.}, address = {Boca Raton, FL}, author = {Srivastava, Asho and Sahami, Mehran.}, interhash = {290eabe518274b6fbcc73a106a7d52a6}, intrahash = {45ab79501c114299142864becfa6c841}, isbn = {9781420059403 1420059408}, pages = {--}, publisher = {CRC Press}, refid = {144226505}, title = {Text mining : classification, clustering, and applications}, url = {http://www.worldcat.org/search?qt=worldcat_org_all&q=9781420059403}, year = 2009 } @inproceedings{Cooley97, author = {Cooley, R. and Mobasher, B. and Srivastava, J.}, booktitle = {Proceedings of the 9th International Conference on Tools with Artificial Intelligence (ICTAI'97)}, interhash = {94895d7c0cc214ed623d941b2dab7367}, intrahash = {e1a677620e58ec56e683e2a80c4f0feb}, month = {November}, pages = {558--567}, publisher = {IEEE Computer Society}, title = {Web mining : Information and pattern discovery on the world wide web}, year = 1997 } @article{Cooley99, author = {Cooley, R. and Mobasher, B. and Srivastava, J.}, interhash = {68b1e11110e6498699524008fe67f8c1}, intrahash = {8673b93f2e415df95099fe00bccd154d}, journal = {Knowledge and Information Systems}, month = {Febuary}, number = 1, pages = {5--32}, publisher = {Springer-Verlag}, title = {Data preparation for mining world wide web browsing patterns}, volume = 1, year = 1999 } @inproceedings{content-only, author = {Cooley, R. and Mobasher, B. and Srivastava, J.}, booktitle = {Proceedings of the Ninth IEEE International Conference on Tools with Artificial Intelligence (ICTAI'97)}, interhash = {94895d7c0cc214ed623d941b2dab7367}, intrahash = {e385cc03235ad1efc751e12fb2fd11d0}, location = {Newport Beach, CA}, month = Nov, publisher = {IEEE Computer Society}, title = {Web Mining: Information and Pattern Discovery on the World Wide Web}, url = {http://maya.cs.depaul.edu/~mobasher/papers/webminer-tai97.ps}, year = 1997 } @inproceedings{1145629, address = {New York, NY, USA}, author = {Desikan, Prasanna Kumar and Pathak, Nishith and Srivastava, Jaideep and Kumar, Vipin}, booktitle = {ICWE '06: Proceedings of the 6th international conference on Web engineering}, doi = {http://doi.acm.org/10.1145/1145581.1145629}, interhash = {d2c5bff1a5bcbcb1dcf2e3fdfb81a874}, intrahash = {32b98aca2e38ee638d3aea77dddea2a2}, isbn = {1-59593-352-2}, location = {Palo Alto, California, USA}, month = {July}, pages = {233--240}, publisher = {ACM Press}, title = {Divide and conquer approach for efficient pagerank computation}, url = {http://portal.acm.org/citation.cfm?doid=1145581.1145629}, year = 2006 } @techreport{delong06concept, author = {DeLong, Colin and Mane, Sandeep and Srivastava, Jaideep}, interhash = {9d474013aee7d0d1fdb4c4c55dcdd4ac}, intrahash = {3d0477dac3614b173f144a389b01158a}, number = {06-007}, publisher = {University of Minnesota}, title = {Concept-Aware Ranking: Teaching an Old Graph New Moves}, url = {http://www.cs.umn.edu/research/technical_reports.php?page=report&report_id=06-007}, year = 2006 } @techreport{delong06concept, author = {DeLong, Colin and Mane, Sandeep and Srivastava, Jaideep}, interhash = {9d474013aee7d0d1fdb4c4c55dcdd4ac}, intrahash = {3d0477dac3614b173f144a389b01158a}, number = {06-007}, publisher = {University of Minnesota}, title = {Concept-Aware Ranking: Teaching an Old Graph New Moves}, url = {http://www.cs.umn.edu/research/technical_reports.php?page=report&report_id=06-007}, year = 2006 } @article{Cooleyetal99, author = {Cooley, R. and Mobasher, B. and Srivastava, J.}, interhash = {68b1e11110e6498699524008fe67f8c1}, intrahash = {e515dc2a8adbc7fa84b7fe968b61391e}, journal = {Journal of Knowledge and Information Systems}, location = {Santa Barbara, CA}, number = 1, pages = {5--32}, title = {Data preparation for mining world wide web browsing patterns}, volume = 1, year = 1999 } @article{Srivastavaetal, author = {Srivastava, J. and Cooley, R. and Deshpande, M. and Tan, P.-N.}, interhash = {08571943908ec1aa9aa5c003e79d5b8d}, intrahash = {dc941da0f5c7da937269241b0df0b3b3}, journal = {SIGKDD Explorations}, location = {Santa Barbara, CA}, number = 2, pages = {12--23}, title = {Web usage mining: discovery and application of usage patterns from web data}, url = {http://citeseer.nj.nec.com/srivastava00web.html}, volume = 1, year = 2000 } @incollection{Cooleyetal00, author = {Cooley, R. and Tang, P.-N. and Srivastava, J.}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {\cite{webkdd99book}}, interhash = {4cb524eff321348696985af1d63a3e59}, intrahash = {5862558933e364680abc29bd5b4e0d84}, pages = {163--182}, title = {Discovery of interesting usage patterns from web data}, year = 2000 } @article{MobasheretalCACM, author = {Mobasher, B. and Cooley, R. and Srivastava, J.}, interhash = {98d5090dafb39596483c75dc4a6846c3}, intrahash = {a7a6cdb6e0790b276d7f0642991e734e}, journal = {Communications of the ACM}, location = {Santa Barbara, CA}, number = 8, pages = {142--151}, title = {Automatic personalization based on Web usage mining}, volume = 43, year = 2000 } @incollection{SrivastavaetalNGDM, author = {Srivastava, J. and Desikan, P. and Kumar, V.}, booktitle = {\cite{NGDM-book}}, interhash = {840c6d7403c6c0c62414de7b5112fb83}, intrahash = {1dc5a9c7e27b52924e2a6eb06732fd19}, isbn = {90-74821-43-X}, title = {Web Mining -- Concepts, Applications \& Research Directions}, year = 2003 }