[ { "key": "VW66DG9D", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/VW66DG9D", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/VW66DG9D", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/7448/items/AJ4SC3SD", "type": "application/json" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } } }, "data": { "key": "VW66DG9D", "version": 1, "parentItem": "AJ4SC3SD", "itemType": "attachment", "linkMode": "linked_url", "title": "icde_2008_inf_engine.pdf (Objet application/pdf)", "accessDate": "2010-01-13T07:39:36Z", "url": "http://www.oracle.com/technology/tech/semantic_technologies/pdf/icde_2008_inf_engine.pdf", "note": "", "contentType": "application/pdf", "charset": "windows-1252", "tags": [], "relations": {}, "dateAdded": "2010-01-13T07:39:36Z", "dateModified": "2011-02-14T14:26:13Z" } }, { "key": "UCPUE3M9", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/UCPUE3M9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/UCPUE3M9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Luo et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "UCPUE3M9", "version": 1, "itemType": "journalArticle", "title": "Geotagging in multimedia and computer vision—a survey", "creators": [ { "creatorType": "author", "firstName": "Jiebo", "lastName": "Luo" }, { "creatorType": "author", "firstName": "Dhiraj", "lastName": "Joshi" }, { "creatorType": "author", "firstName": "Jie", "lastName": "Yu" }, { "creatorType": "author", "firstName": "Andrew", "lastName": "Gallagher" } ], "abstractNote": "", "publicationTitle": "Multimedia Tools and Applications", "publisher": "", "place": "", "date": "10/2010", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Multimed Tools Appl", "DOI": "10.1007/s11042-010-0623-y", "citationKey": "", "url": "http://www.springerlink.com/content/418r5103v3q12986/", "accessDate": "2010-10-29T08:52:45Z", "PMID": "", "PMCID": "", "ISSN": "1380-7501", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-29T08:52:45Z", "dateModified": "2010-10-29T08:52:45Z" } }, { "key": "JWBEBA2S", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/JWBEBA2S", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/JWBEBA2S", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Myung et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "JWBEBA2S", "version": 1, "itemType": "conferencePaper", "title": "SPARQL basic graph pattern processing with iterative MapReduce", "creators": [ { "creatorType": "author", "firstName": "Jaeseok", "lastName": "Myung" }, { "creatorType": "author", "firstName": "Jongheum", "lastName": "Yeon" }, { "creatorType": "author", "firstName": "Sang-goo", "lastName": "Lee" } ], "abstractNote": "There have been a number of approaches to adopt the RDF data model and the MapReduce framework for a data warehouse, as the data model is suitable for data integration and the data processing framework is good for large-scale fault-tolerant data analyses. Nevertheless, most approaches consider the data model and the framework separately. It has been difficult to create synergy because there have been only a few algorithms which connects the data model and the framework. In this paper, we offer a general and efficient MapReduce algorithm for SPARQL Basic Graph Pattern which is a set of triple patterns to be joined. In a MapReduce world, it is known that the join operation requires computationally expensive MapReduce iterations. For this reason, we minimize the number of iterations with the followings. First, we adopt traditional multi-way join into MapReduce instead of multiple individual joins. Second, by analyzing a given query, we select a good join-key to avoid unnecessary iterations. As a result, the algorithm shows good performance and scalability in terms of time and data size.", "proceedingsTitle": "Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud", "conferenceName": "", "publisher": "ACM", "place": "Raleigh, North Carolina", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1-6", "series": "", "seriesNumber": "", "DOI": "10.1145/1779599.1779605", "ISBN": "978-1-60558-991-6", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1779599.1779605", "accessDate": "2010-10-25T14:28:42Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "basic graph pattern", "type": 1 }, { "tag": "cloud computing", "type": 1 }, { "tag": "data warehouse", "type": 1 }, { "tag": "mapreduce", "type": 1 }, { "tag": "query processing", "type": 1 }, { "tag": "rdf", "type": 1 }, { "tag": "sparql", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2010-10-25T14:28:42Z", "dateModified": "2010-10-25T14:28:42Z" } }, { "key": "PS8SQUBS", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/PS8SQUBS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/PS8SQUBS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Priss et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "PS8SQUBS", "version": 1, "itemType": "book", "title": "Conceptual Structures: Knowledge Architectures for Smart Applications", "creators": [ { "creatorType": "editor", "firstName": "Uta", "lastName": "Priss" }, { "creatorType": "editor", "firstName": "Simon", "lastName": "Polovina" }, { "creatorType": "editor", "firstName": "Richard", "lastName": "Hill" } ], "abstractNote": "", "series": "", "seriesNumber": "", "volume": "4604", "numberOfVolumes": "", "edition": "", "date": "2007", "publisher": "Springer Berlin Heidelberg", "place": "Berlin, Heidelberg", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-3-540-73680-6", "DOI": "", "citationKey": "", "url": "http://www.springerlink.com/content/cx311558l39g4836/", "accessDate": "2010-10-25T14:22:25Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Conceptual Structures", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-25T14:22:25Z", "dateModified": "2010-10-25T14:22:25Z" } }, { "key": "G4N7QKSV", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/G4N7QKSV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/G4N7QKSV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Pérez et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "G4N7QKSV", "version": 1, "itemType": "journalArticle", "title": "Semantics and complexity of SPARQL", "creators": [ { "creatorType": "author", "firstName": "Jorge", "lastName": "Pérez" }, { "creatorType": "author", "firstName": "Marcelo", "lastName": "Arenas" }, { "creatorType": "author", "firstName": "Claudio", "lastName": "Gutierrez" } ], "abstractNote": "SPARQL is the standard language for querying RDF data. In this article, we address systematically the formal study of the database aspects of SPARQL, concentrating in its graph pattern matching facility. We provide a compositional semantics for the core part of SPARQL, and study the complexity of the evaluation of several fragments of the language. Among other complexity results, we show that the evaluation of general SPARQL patterns is PSPACE-complete. We identify a large class of SPARQL patterns, defined by imposing a simple and natural syntactic restriction, where the query evaluation problem can be solved more efficiently. This restriction gives rise to the class of well-designed patterns. We show that the evaluation problem is coNP-complete for well-designed patterns. Moreover, we provide several rewriting rules for well-designed patterns whose application may have a considerable impact in the cost of evaluating SPARQL queries.", "publicationTitle": "ACM Trans. Database Syst.", "publisher": "", "place": "", "date": "2009", "volume": "34", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "1-45", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1145/1567274.1567278", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1567274.1567278&coll=portal&dl=ACM&CFID=56622501&CFTOKEN=93816691", "accessDate": "2010-06-01T08:49:29Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "complexity", "type": 1 }, { "tag": "query language", "type": 1 }, { "tag": "rdf", "type": 1 }, { "tag": "semantic web", "type": 1 }, { "tag": "sparql", "type": 1 } ], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-06-01T08:49:29Z", "dateModified": "2010-06-01T08:49:29Z" } }, { "key": "I7PUZHI4", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/I7PUZHI4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/I7PUZHI4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "I7PUZHI4", "version": 1, "itemType": "webpage", "title": "Explorer des actualités multimédia dans le Web de données", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://www.slideshare.net/ic_2009/explorer-des-actualits-multimdia-dans-le-web-de-donnes", "accessDate": "2010-02-25T21:35:41Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": { "owl:sameAs": "http://zotero.org/groups/6390/items/DHJH3UVF" }, "dateAdded": "2010-02-25T21:44:08Z", "dateModified": "2010-02-25T21:44:08Z" } }, { "key": "RPPXWEN3", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/RPPXWEN3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/RPPXWEN3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "RPPXWEN3", "version": 1, "itemType": "webpage", "title": "Indexation de photos sociales par propagation sur une hiérarchie de concepts", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://www.slideshare.net/ic_2009/indexation-de-photos-sociales-par-propagation-sur-une-hirarchie-de-concepts", "accessDate": "2010-02-25T21:24:30Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-02-25T21:24:30Z", "dateModified": "2010-02-25T21:24:30Z" } }, { "key": "FEGQR3UM", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/FEGQR3UM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/FEGQR3UM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "FEGQR3UM", "version": 1, "itemType": "webpage", "title": "- Home", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://www.prom.case.unibz.it/", "accessDate": "2010-02-09T10:46:19Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-02-09T10:46:19Z", "dateModified": "2010-02-09T10:46:19Z" } }, { "key": "WKMMCDPE", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/WKMMCDPE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/WKMMCDPE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Cordella et al.", "parsedDate": "2004", "numChildren": 0 }, "data": { "key": "WKMMCDPE", "version": 1, "itemType": "journalArticle", "title": "A (sub)graph isomorphism algorithm for matching large graphs", "creators": [ { "creatorType": "author", "firstName": "L.P.", "lastName": "Cordella" }, { "creatorType": "author", "firstName": "P.", "lastName": "Foggia" }, { "creatorType": "author", "firstName": "C.", "lastName": "Sansone" }, { "creatorType": "author", "firstName": "M.", "lastName": "Vento" } ], "abstractNote": "", "publicationTitle": "IEEE Transactions on Pattern Analysis and Machine Intelligence", "publisher": "", "place": "", "date": "10/2004", "volume": "26", "issue": "10", "section": "", "partNumber": "", "partTitle": "", "pages": "1367-1372", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "IEEE Trans. Pattern Anal. Machine Intell.", "DOI": "10.1109/TPAMI.2004.75", "citationKey": "", "url": "http://www.computer.org/portal/web/csdl/abs/trans/tp/2004/10/i1367abs.htm", "accessDate": "2010-01-22T21:42:40Z", "PMID": "", "PMCID": "", "ISSN": "0162-8828", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CrossRef", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-22T21:42:40Z", "dateModified": "2010-01-22T21:42:40Z" } }, { "key": "E6JVWVRM", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/E6JVWVRM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/E6JVWVRM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Ullmann", "parsedDate": "1976", "numChildren": 0 }, "data": { "key": "E6JVWVRM", "version": 1, "itemType": "journalArticle", "title": "An Algorithm for Subgraph Isomorphism", "creators": [ { "creatorType": "author", "firstName": "J. R.", "lastName": "Ullmann" } ], "abstractNote": "Subgraph isomorphism can be determined by means of a brute-force tree-search enumeration procedure. In this paper a new algorithm is introduced that attains efficiency by inferentially eliminating successor nodes in the tree search. To assess the time actually taken by the new algorithm, subgraph isomorphism, clique detection, graph isomorphism, and directed graph isomorphism experiments have been carried out with random and with various nonrandom graphs. A parallel asynchronous logic-in-memory implementation of a vital part of the algorithm is also described, although this hardware has not actually been built. The hardware implementation would allow very rapid determination of isomorphism.", "publicationTitle": "J. ACM", "publisher": "", "place": "", "date": "1976", "volume": "23", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "31-42", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1145/321921.321925", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=321925", "accessDate": "2010-01-22T21:40:39Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-22T21:40:39Z", "dateModified": "2010-01-22T21:40:39Z" } }, { "key": "AJ4SC3SD", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/AJ4SC3SD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/AJ4SC3SD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 1 }, "data": { "key": "AJ4SC3SD", "version": 1, "itemType": "webpage", "title": "Neo4j Blog: Social networks in the database: using a graph database", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://blog.neo4j.org/2009/09/social-networks-in-database-using-graph.html", "accessDate": "2010-01-13T07:38:12Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-13T07:38:12Z", "dateModified": "2010-01-13T07:38:12Z" } }, { "key": "QMTPI32C", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/QMTPI32C", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/QMTPI32C", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "QMTPI32C", "version": 1, "itemType": "webpage", "title": "Cytoscape: Hands-down Winner for Large-scale Graph Visualization » AI3:::Adaptive Information", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://www.mkbergman.com/415/cytoscape-hands-down-winner-for-large-scale-graph-visualization/", "accessDate": "2010-01-13T07:36:21Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-13T07:36:21Z", "dateModified": "2010-01-13T07:36:21Z" } }, { "key": "PU43NIH5", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/PU43NIH5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/PU43NIH5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Le and Dieng-Kuntz", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "PU43NIH5", "version": 1, "itemType": "conferencePaper", "title": "A Graph-Based Algorithm for Alignment of OWL Ontologies", "creators": [ { "creatorType": "author", "firstName": "Bach Thanh", "lastName": "Le" }, { "creatorType": "author", "firstName": "Rose", "lastName": "Dieng-Kuntz" } ], "abstractNote": "This paper presents ASCO3 algorithm, aimed at finding mappings between entities of two ontologies represented in OWL DL/Lite. ASCO3 algorithm searches the maximal common subgraph of two graphs representing two ontologies, and relies on an algorithm of search of the maximal clique of their association graph.", "proceedingsTitle": "Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence", "conferenceName": "", "publisher": "IEEE Computer Society", "place": "", "date": "2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "466-469", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "0-7695-3026-5", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1331740.1331893", "accessDate": "2010-01-13T07:33:22Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-13T07:33:22Z", "dateModified": "2010-01-13T07:33:22Z" } }, { "key": "WH8S4UU7", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/WH8S4UU7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/WH8S4UU7", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "WH8S4UU7", "version": 1, "itemType": "webpage", "title": "Ontology creation for the rest of us…", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://coe.ihmc.us/groups/coe/", "accessDate": "2010-01-13T07:31:24Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [ "HKBW7PF3" ], "relations": {}, "dateAdded": "2010-01-13T07:31:24Z", "dateModified": "2010-01-13T07:31:24Z" } }, { "key": "M965GII3", "version": 1, "library": { "type": "group", "id": 7448, "name": "Semat", "links": { "alternate": { "href": "https://www.zotero.org/groups/semat", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/7448/items/M965GII3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/semat/items/M965GII3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 21619, "username": "eegyedzs", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/eegyedzs", "type": "text/html" } } }, "creatorSummary": "Veldman", "parsedDate": "2009-10-23", "numChildren": 0 }, "data": { "key": "M965GII3", "version": 1, "itemType": "webpage", "title": "Matching Profiles from Social Network Sites", "creators": [ { "creatorType": "author", "firstName": "I.", "lastName": "Veldman" } ], "abstractNote": "", "websiteTitle": "", "websiteType": "Master's Thesis", "date": "2009-10-23", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://eprints.eemcs.utwente.nl/16408/", "accessDate": "2009-11-14T23:03:36Z", "shortTitle": "", "language": "", "rights": "", "extra": "In recent years social networking sites have become very popular. Many people are member of one or more of these profile sites and tend to put a lot of informa- tion about themselves online. This often publicly available data can be useful for many purposes. Retrieving all available data from one person and merging it into one profile even more. Detection of which profiles belong to the same person becomes very important. This task is called Entity Resolution (ER).\nIn this research we develop a model to solve the ER problem for profiles from social networking sites. First we present a simple model. Then we try to improve this model by making use of the social networks a member can have on these sites. We believe that involving the networks can improve the results significantly.\nGeneral idea is that we have two sites with profiles. With the model we try to find out which profiles of the first profile site correspond to which profiles of the second profile site, whereby we assume a person to have at most one profile at each profile site.\nIn the simple model, we compare all profiles of the first profile site against all profiles of the second site. This comparison will result in a score for each pair: the pairwise similarity score. The higher this score, the higher the probability that these profiles belong to the same person. The pairs that satisfy the so-called pairwise threshold are the candidate matches. From these candidate matches, the matches are chosen.\nIn the network model, we start the same way. When the list of candidate matches is determined, the network phase is started. For each candidate match the network similarity score is calculated. This is done by determining the overlap in the networks of both profiles in the candidate match. The more overlap between the networks, the higher the network similarity score, the higher the probability that the profiles in the candidate match belong to the same person. This time, the candidate matches should satisfy a network threshold in order to stay a candidate match. Then from the remaining candidate matches, the matches are chosen.\nIn order to test whether the network model would indeed improve the simple model, we have set up experiments. Since no suitable data sets were available, we retrieved our own data set. Unfortunately, it appeared to have some limitations. Also, we have built a prototype that implemented the model. The prototype has several parameters for which we could vary the values in the experiments to find a good configuration.\nThe network model ensures that there are more conditions that need to be met to be a match. The experimental results confirm this. That means that the precision of the results increases. On the other side, due to these strict conditions, corresponding profiles are missed, which is undesired. However, in case there are ambiguous profiles in the set, the network model can distinguish the correct profile, which is highly desired. This situation will occur frequently in real life, hence we think the network model can really contribute to solving the ER problem.", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-11-14T23:03:36Z", "dateModified": "2009-11-14T23:03:36Z" } } ]