[ { "key": "RAKTGFZK", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/RAKTGFZK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/RAKTGFZK", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/H5H68DKU", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "RAKTGFZK", "version": 1, "parentItem": "H5H68DKU", "itemType": "attachment", "linkMode": "imported_url", "title": "Untangling Text Data Mining", "accessDate": "2010-12-01T13:26:48Z", "url": "http://people.ischool.berkeley.edu/~hearst/papers/acl99/acl99-tdm.html", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "acl99-tdm.html", "md5": null, "mtime": 1291210006000, "tags": [], "relations": {}, "dateAdded": "2010-12-01T13:26:48Z", "dateModified": "2010-12-01T13:26:48Z" } }, { "key": "H5H68DKU", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/H5H68DKU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/H5H68DKU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "numChildren": 1 }, "data": { "key": "H5H68DKU", "version": 1, "itemType": "webpage", "title": "Untangling Text Data Mining", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://people.ischool.berkeley.edu/~hearst/papers/acl99/acl99-tdm.html", "accessDate": "2010-12-01T13:26:47Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-12-01T13:26:47Z", "dateModified": "2010-12-01T13:26:47Z" } }, { "key": "BPPARIU7", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/BPPARIU7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/BPPARIU7", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/6R5768BS", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "BPPARIU7", "version": 1, "parentItem": "6R5768BS", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2010-10-20T15:34:27Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=775061&type=pdf&coll=GUIDE&dl=GUIDE&CFID=109644040&CFTOKEN=60974473", "note": "", "contentType": "", "charset": "", "filename": "Kleinberg - 2002 - Bursty and hierarchical structure in streams.cfm", "md5": "8c7a1006c2a02bfd2315e6bab943317f", "mtime": 1287588884000, "tags": [], "relations": {}, "dateAdded": "2010-10-20T15:34:27Z", "dateModified": "2010-10-20T15:34:44Z" } }, { "key": "N7MNR7RE", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/N7MNR7RE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/N7MNR7RE", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/6R5768BS", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "N7MNR7RE", "version": 1, "parentItem": "6R5768BS", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-10-20T15:34:39Z", "url": "http://portal.acm.org/citation.cfm?id=775061", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1287588880000, "tags": [], "relations": {}, "dateAdded": "2010-10-20T15:34:39Z", "dateModified": "2010-10-20T15:34:39Z" } }, { "key": "6R5768BS", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/6R5768BS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/6R5768BS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Kleinberg", "parsedDate": "2002", "numChildren": 2 }, "data": { "key": "6R5768BS", "version": 1, "itemType": "conferencePaper", "title": "Bursty and hierarchical structure in streams", "creators": [ { "creatorType": "author", "firstName": "Jon", "lastName": "Kleinberg" } ], "abstractNote": "A fundamental problem in text data mining is to extract meaningful structure from document streams that arrive continuously over time. E-mail and news articles are two natural examples of such streams, each characterized by topics that appear, grow in intensity for a period of time, and then fade away. The published literature in a particular research field can be seen to exhibit similar phenomena over a much longer time scale. Underlying much of the text mining work in this area is the following intuitive premise --- that the appearance of a topic in a document stream is signaled by a \"burst of activity,\" with certain features rising sharply in frequency as the topic emerges.The goal of the present work is to develop a formal approach for modeling such \"bursts,\" in such a way that they can be robustly and efficiently identified, and can provide an organizational framework for analyzing the underlying content. The approach is based on modeling the stream using an infinite-state automaton, in which bursts appear naturally as state transitions; in some ways, it can be viewed as drawing an analogy with models from queueing theory for bursty network traffic. The resulting algorithms are highly efficient, and yield a nested representation of the set of bursts that imposes a hierarchical structure on the overall stream. Experiments with e-mail and research paper archives suggest that the resulting structures have a natural meaning in terms of the content that gave rise to them.", "proceedingsTitle": "Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining", "conferenceName": "", "publisher": "ACM", "place": "Edmonton, Alberta, Canada", "date": "2002", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "91-101", "series": "", "seriesNumber": "", "DOI": "10.1145/775047.775061", "ISBN": "1-58113-567-X", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=775061", "accessDate": "2010-10-20T15:34:22Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-20T15:34:22Z", "dateModified": "2010-10-20T15:34:22Z" } }, { "key": "C2JQ3JBA", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/C2JQ3JBA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/C2JQ3JBA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Paek et al.", "numChildren": 0 }, "data": { "key": "C2JQ3JBA", "version": 1, "itemType": "webpage", "title": "Predicting the Importance of Newsfeed Posts and Social Network Friends - Microsoft Research", "creators": [ { "creatorType": "author", "firstName": "Tim", "lastName": "Paek" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Gamon" }, { "creatorType": "author", "firstName": "Scott", "lastName": "Counts" }, { "creatorType": "author", "firstName": "David Maxwell", "lastName": "Chickering" }, { "creatorType": "author", "firstName": "Aman", "lastName": "Dhesi" } ], "abstractNote": "As users of social networking websites expand their network of friends, they are often flooded with newsfeed posts and status updates, most of which they consider to be \"unimportant\" and not newsworthy. In order to better understand how people judge the importance of their newsfeed, we conducted a study in which Facebook users were asked to rate the importance of their newsfeed posts as well as their friends. We learned classifiers of newsfeed and friend importance to identify predictive sets of features related to social media properties, the message text, and shared background information. For classifying friend importance, the best performing model achieved 85% accuracy and 25% error reduction. By leveraging this model for classifying newsfeed posts, the best newsfeed classifier achieved 64% accuracy and 27% error reduction.", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://research.microsoft.com/apps/pubs/default.aspx?id=135702", "accessDate": "2010-10-12T08:44:48Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-12T08:46:39Z", "dateModified": "2010-10-12T08:46:39Z" } }, { "key": "F2ZEX3IN", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/F2ZEX3IN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/F2ZEX3IN", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/TAZPNT7R", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "F2ZEX3IN", "version": 1, "parentItem": "TAZPNT7R", "itemType": "attachment", "linkMode": "imported_url", "title": "I256: Applied Natural Language Processing", "accessDate": "2010-10-05T20:58:10Z", "url": "http://courses.ischool.berkeley.edu/i256/f06/sched.html", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "sched.html", "md5": null, "mtime": 1286312289000, "tags": [], "relations": {}, "dateAdded": "2010-10-05T20:58:10Z", "dateModified": "2010-10-05T20:58:10Z" } }, { "key": "TAZPNT7R", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/TAZPNT7R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/TAZPNT7R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "numChildren": 1 }, "data": { "key": "TAZPNT7R", "version": 1, "itemType": "webpage", "title": "I256: Applied Natural Language Processing", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://courses.ischool.berkeley.edu/i256/f06/sched.html", "accessDate": "2010-10-05T20:58:09Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-05T20:58:09Z", "dateModified": "2010-10-05T20:58:09Z" } }, { "key": "2WTE9GU2", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/2WTE9GU2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/2WTE9GU2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Hearst", "numChildren": 1 }, "data": { "key": "2WTE9GU2", "version": 1, "itemType": "webpage", "title": "Untangling Text Data Mining", "creators": [ { "creatorType": "author", "firstName": "Marti", "lastName": "Hearst" } ], "abstractNote": "The possibilities for data mining from large text collections are virtually untapped. Text expresses a vast, rich range of information, but encodes this information in a form that is difficult to decipher automatically. Perhaps for this reason, there has been little work in text data mining to date, and most people who have talked about it have either conflated it with information access or have not made use of text directly to discover heretofore unknown information.\n\nIn this paper I will first define data mining, information access, and corpus-based computational linguistics, and then discuss the relationship of these to text data mining. The intent behind these contrasts is to draw attention to exciting new kinds of problems for computational linguists. I describe examples of what I consider to be real text data mining efforts and briefly outline our recent ideas about how to pursue exploratory data analysis over text.", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://people.ischool.berkeley.edu/~hearst/papers/acl99/acl99-tdm.html", "accessDate": "2010-10-05T20:49:18Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-10-05T20:49:18Z", "dateModified": "2010-10-05T20:49:43Z" } }, { "key": "7TP47I24", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/7TP47I24", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/7TP47I24", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/2WTE9GU2", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "7TP47I24", "version": 1, "parentItem": "2WTE9GU2", "itemType": "attachment", "linkMode": "imported_url", "title": "Untangling Text Data Mining", "accessDate": "2010-10-05T20:49:19Z", "url": "http://people.ischool.berkeley.edu/~hearst/papers/acl99/acl99-tdm.html", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "acl99-tdm.html", "md5": null, "mtime": 1286311758000, "tags": [], "relations": {}, "dateAdded": "2010-10-05T20:49:19Z", "dateModified": "2010-10-05T20:49:19Z" } }, { "key": "W6WC9MC5", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/W6WC9MC5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/W6WC9MC5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/BKCBG6KX", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "W6WC9MC5", "version": 1, "parentItem": "BKCBG6KX", "itemType": "attachment", "linkMode": "imported_file", "title": "Optimizing Complex Extraction Programs over Evolving Text Data.pdf", "accessDate": "", "url": "", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Optimizing Complex Extraction Programs over Evolving Text Data.pdf", "md5": "f7b9a182cce043d5f49ae9d5d8b92fab", "mtime": 1277747556000, "tags": [], "relations": {}, "dateAdded": "2010-06-28T17:55:37Z", "dateModified": "2010-06-28T17:55:37Z" } }, { "key": "BNHGMPGE", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/BNHGMPGE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/BNHGMPGE", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/BKCBG6KX", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "BNHGMPGE", "version": 1, "parentItem": "BKCBG6KX", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2010-06-28T17:55:13Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1559881&type=pdf&coll=GUIDE&dl=GUIDE&CFID=95197396&CFTOKEN=80079744", "note": "", "contentType": "", "charset": "", "filename": "Chen et al. - 2009 - Optimizing complex extraction programs over evolvi.cfm", "md5": "f46aa063fc402508bc083fa00c4a3cbc", "mtime": 1277747711000, "tags": [], "relations": {}, "dateAdded": "2010-06-28T17:55:13Z", "dateModified": "2010-06-28T17:55:16Z" } }, { "key": "ICVNI5RI", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/ICVNI5RI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/ICVNI5RI", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/BKCBG6KX", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "ICVNI5RI", "version": 1, "parentItem": "BKCBG6KX", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-06-28T17:55:15Z", "url": "http://portal.acm.org/citation.cfm?doid=1559845.1559881", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1277747710000, "tags": [], "relations": {}, "dateAdded": "2010-06-28T17:55:15Z", "dateModified": "2010-06-28T17:55:15Z" } }, { "key": "BKCBG6KX", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/BKCBG6KX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/BKCBG6KX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Chen et al.", "parsedDate": "2009", "numChildren": 3 }, "data": { "key": "BKCBG6KX", "version": 1, "itemType": "conferencePaper", "title": "Optimizing complex extraction programs over evolving text data", "creators": [ { "creatorType": "author", "firstName": "Fei", "lastName": "Chen" }, { "creatorType": "author", "firstName": "Byron J.", "lastName": "Gao" }, { "creatorType": "author", "firstName": "AnHai", "lastName": "Doan" }, { "creatorType": "author", "firstName": "Jun", "lastName": "Yang" }, { "creatorType": "author", "firstName": "Raghu", "lastName": "Ramakrishnan" } ], "abstractNote": "Most information extraction (IE) approaches have considered only static text corpora, over which we apply IE only once. Many real-world text corpora however are dynamic. They evolve over time, and so to keep extracted information up to date we often must apply IE repeatedly, to consecutive corpus snapshots. Applying IE from scratch to each snapshot can take a lot of time. To avoid doing this, we have recently developed Cyclex, a system that recycles previous IE results to speed up IE over subsequent corpus snapshots. Cyclex clearly demonstrated the promise of the recycling idea. The work itself however is limited in that it considers only IE programs that contain a single IE ``blackbox.'' In practice, many IE programs are far more complex, containing multiple IE blackboxes connected in a compositional ``workflow.''", "proceedingsTitle": "Proceedings of the 35th SIGMOD international conference on Management of data", "conferenceName": "", "publisher": "ACM", "place": "Providence, Rhode Island, USA", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "321-334", "series": "", "seriesNumber": "", "DOI": "10.1145/1559845.1559881", "ISBN": "978-1-60558-551-2", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?doid=1559845.1559881", "accessDate": "2010-06-28T17:55:11Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "evolving text", "type": 1 }, { "tag": "information extraction", "type": 1 }, { "tag": "optimization", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2010-06-28T17:55:11Z", "dateModified": "2010-06-28T17:55:11Z" } }, { "key": "QQKUS32V", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/QQKUS32V", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/QQKUS32V", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/SW3KUN5P", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "QQKUS32V", "version": 1, "parentItem": "SW3KUN5P", "itemType": "attachment", "linkMode": "imported_url", "title": "DBLP Record 'conf/sdm/AggarwalY06'", "accessDate": "2010-05-04T21:05:33Z", "url": "http://dblp.uni-trier.de/rec/bibtex/conf/sdm/AggarwalY06", "note": "", "contentType": "text/html", "charset": "windows-1252", "filename": "AggarwalY06.html", "md5": null, "mtime": 1273007132000, "tags": [], "relations": {}, "dateAdded": "2010-05-04T21:05:33Z", "dateModified": "2010-05-04T21:05:33Z" } }, { "key": "SW3KUN5P", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/SW3KUN5P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/SW3KUN5P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "numChildren": 1 }, "data": { "key": "SW3KUN5P", "version": 1, "itemType": "webpage", "title": "DBLP Record 'conf/sdm/AggarwalY06'", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "http://dblp.uni-trier.de/rec/bibtex/conf/sdm/AggarwalY06", "accessDate": "2010-05-04T21:05:32Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-04T21:05:32Z", "dateModified": "2010-05-04T21:05:32Z" } }, { "key": "962SGBFC", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/962SGBFC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/962SGBFC", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/BT3V4IKT", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "962SGBFC", "version": 1, "parentItem": "BT3V4IKT", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-05-04T21:04:44Z", "url": "http://portal.acm.org/citation.cfm?id=1529619", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1273007073000, "tags": [], "relations": {}, "dateAdded": "2010-05-04T21:04:44Z", "dateModified": "2010-05-04T21:04:44Z" } }, { "key": "GKTJEGE9", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/GKTJEGE9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/GKTJEGE9", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/BT3V4IKT", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "GKTJEGE9", "version": 1, "parentItem": "BT3V4IKT", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2010-05-04T21:04:41Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1529619&type=pdf&coll=GUIDE&dl=GUIDE&CFID=87124109&CFTOKEN=16393002", "note": "", "contentType": "", "charset": "", "filename": "Karnstedt et al. - 2009 - Adaptive burst detection in a stream engine.cfm", "md5": "7e988622afee1cfdb1698bf1c2bbf663", "mtime": 1273007073000, "tags": [], "relations": {}, "dateAdded": "2010-05-04T21:04:41Z", "dateModified": "2010-05-04T21:04:43Z" } }, { "key": "BT3V4IKT", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/BT3V4IKT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/BT3V4IKT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Karnstedt et al.", "parsedDate": "2009", "numChildren": 2 }, "data": { "key": "BT3V4IKT", "version": 1, "itemType": "conferencePaper", "title": "Adaptive burst detection in a stream engine", "creators": [ { "creatorType": "author", "firstName": "Marcel", "lastName": "Karnstedt" }, { "creatorType": "author", "firstName": "Daniel", "lastName": "Klan" }, { "creatorType": "author", "firstName": "Christian", "lastName": "Pölitz" }, { "creatorType": "author", "firstName": "Kai-Uwe", "lastName": "Sattler" }, { "creatorType": "author", "firstName": "Conny", "lastName": "Franke" } ], "abstractNote": "Detecting bursts in data streams is an important and challenging task. Due to the complexity of this task, usually burst detection cannot be formulated using standard query operators. Therefore, we show how to integrate burst detection for stationary as well as non-stationary data into query formulation and processing, from the language level to the operator level. Afterwards, we present fundamentals of threshold-based burst detection. We focus on the applicability of time series forecasting techniques in order to dynamically identify suitable thresholds for stream data containing arbitrary trends and periods. The proposed approach is evaluated with respect to quality and performance on synthetic and real-world sensor data using a full-fledged DSMS.", "proceedingsTitle": "Proceedings of the 2009 ACM symposium on Applied Computing", "conferenceName": "", "publisher": "ACM", "place": "Honolulu, Hawaii", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1511-1515", "series": "", "seriesNumber": "", "DOI": "10.1145/1529282.1529619", "ISBN": "978-1-60558-166-8", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1529619", "accessDate": "2010-05-04T21:04:40Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-04T21:04:40Z", "dateModified": "2010-05-04T21:04:40Z" } }, { "key": "8DNEI8T6", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/8DNEI8T6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/8DNEI8T6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Looks et al.", "numChildren": 0 }, "data": { "key": "8DNEI8T6", "version": 1, "itemType": "journalArticle", "title": "Streaming Hierarchical Clustering for Concept Mining", "creators": [ { "creatorType": "author", "firstName": "Moshe", "lastName": "Looks" }, { "creatorType": "author", "firstName": "Andrew", "lastName": "Levine" }, { "creatorType": "author", "firstName": "G. Adam", "lastName": "Covington" }, { "creatorType": "author", "firstName": "Ronald P", "lastName": "Loui" }, { "creatorType": "author", "firstName": "John W", "lastName": "Lockwood" }, { "creatorType": "author", "firstName": "Young H", "lastName": "Cho" } ], "abstractNote": "", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.1590", "accessDate": "2010-05-04T20:59:36Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-04T20:59:36Z", "dateModified": "2010-05-04T20:59:36Z" } }, { "key": "5BSAVC67", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/5BSAVC67", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/5BSAVC67", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Huang and Cardenas", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "5BSAVC67", "version": 1, "itemType": "document", "title": "Extracting Hot Events from News Feeds, Visualization, and Insights", "creators": [ { "creatorType": "author", "firstName": "Zhen", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Alfonso F.", "lastName": "Cardenas" } ], "abstractNote": "Abstract— Our aim is a real time news extraction system capable of identifying up-to-date “hot news” from large amounts of news reports on the internet. We show two important characteristics of hotness: short-term burst and long-term historical variation. Based on these factors, we define our problem: given all news articles on the current day p and previous news archives, identify the hot news on day p. Our novel system consists of four parts. First, all entities (atomic elements in text such as the names of persons, organizations, locations, etc) which occurred on the current day are extracted. Second, hot terms on day p are identified with our novel term weighting scheme for hotness. Third, each news article on the current day will be represented as a vector of hot terms with frequency. The last step is to cluster all new articles on day p and rank the result clusters with their hotness score. The scheme is also adaptive since the hot terms extracted are different from day to day, and reflect the hot events on each day. The focus of this paper is to illustrate the visualization and the insight of the hot-news through time, not the underlying algorithm details we developed.\nOur experiments conducted on a Yahoo! News dataset indicate that our term weighting scheme incorporating the two important features of hotness evaluate the significance of each extracted entity properly.", "type": "", "date": "2009", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "www.mist.cs.ucla.edu/papers/VLC09_HuangCardenas.pdf", "accessDate": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "", "callNumber": "2009 Distributed Multimedia Systems Conference, San Francisco, California, September 10-12, 2009", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-04T20:56:35Z", "dateModified": "2010-05-04T20:56:35Z" } }, { "key": "96VB57IJ", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/96VB57IJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/96VB57IJ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/P6WJGMHI", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "96VB57IJ", "version": 1, "parentItem": "P6WJGMHI", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Snapshot", "accessDate": "2010-05-04T20:51:56Z", "url": "http://portal.acm.org/citation.cfm?id=1315460", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "citation.html", "md5": null, "mtime": 1273006312000, "tags": [], "relations": {}, "dateAdded": "2010-05-04T20:51:56Z", "dateModified": "2010-05-04T20:51:56Z" } }, { "key": "5VE45UXM", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/5VE45UXM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/5VE45UXM", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/17113/items/P6WJGMHI", "type": "application/json" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } } }, "data": { "key": "5VE45UXM", "version": 1, "parentItem": "P6WJGMHI", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2010-05-04T20:51:54Z", "url": "http://portal.acm.org/ft_gateway.cfm?id=1315460&type=pdf&coll=GUIDE&dl=GUIDE&CFID=87122847&CFTOKEN=73849802", "note": "", "contentType": "", "charset": "", "filename": "Aggarwal et al. - 2003 - A framework for clustering evolving data streams.cfm", "md5": "cef0f2f6861ea0644614f26ea1068532", "mtime": 1273006310000, "tags": [], "relations": {}, "dateAdded": "2010-05-04T20:51:54Z", "dateModified": "2010-05-04T20:51:55Z" } }, { "key": "P6WJGMHI", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/P6WJGMHI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/P6WJGMHI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "creatorSummary": "Aggarwal et al.", "parsedDate": "2003", "numChildren": 2 }, "data": { "key": "P6WJGMHI", "version": 1, "itemType": "conferencePaper", "title": "A framework for clustering evolving data streams", "creators": [ { "creatorType": "author", "firstName": "Charu C.", "lastName": "Aggarwal" }, { "creatorType": "author", "firstName": "Jiawei", "lastName": "Han" }, { "creatorType": "author", "firstName": "Jianyong", "lastName": "Wang" }, { "creatorType": "author", "firstName": "Philip S.", "lastName": "Yu" } ], "abstractNote": "The clustering problem is a difficult problem for the data stream domain. This is because the large volumes of data arriving in a stream renders most traditional algorithms too inefficient. In recent years, a few one-pass clustering algorithms have been developed for the data stream problem. Although such methods address the scalability issues of the clustering problem, they are generally blind to the evolution of the data and do not address the following issues: (1) The quality of the clusters is poor when the data evolves considerably over time. (2) A data stream clustering algorithm requires much greater functionality in discovering and exploring clusters over different portions of the stream.", "proceedingsTitle": "Proceedings of the 29th international conference on Very large data bases - Volume 29", "conferenceName": "", "publisher": "VLDB Endowment", "place": "Berlin, Germany", "date": "2003", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "81-92", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "0-12-722442-4", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=1315460", "accessDate": "2010-05-04T20:51:53Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-04T20:51:53Z", "dateModified": "2010-05-04T20:51:53Z" } }, { "key": "NFS4UK7P", "version": 1, "library": { "type": "group", "id": 17113, "name": "Text Mining", "links": { "alternate": { "href": "https://www.zotero.org/groups/text_mining", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/17113/items/NFS4UK7P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/text_mining/items/NFS4UK7P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 235284, "username": "buki", "name": "Andreas Bauer", "links": { "alternate": { "href": "https://www.zotero.org/buki", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "NFS4UK7P", "version": 1, "itemType": "document", "title": "Reuters NewsScope Event Indices Research Whitepaper", "creators": [], "abstractNote": "The Reuters NewsScope Event Indices Project is an integrated framework for incorporating real-time news from the Reuters NewsScope subscription service into systematic investment and risk-management protocols. The framework consists of a set of real-time event indices— each one taking on numerical values between 0 and 100—designed to capture the occurrence of unusual events of a particular kind. For example, the Macroeconomic index measures the real-time quantity of macroeconomic news, and the Natural Disaster index measures the real-time quantity of natural-disaster news. Each index is constructed by applying dis- ciplined pattern-recognition algorithms to real-time newsfeeds, and calibrated using econo- metric methods applied to historical data. In this first release, we construct indices that are calibrated to foreign exchange markets, and future releases will focus on other markets.", "type": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "puppetmastertrading.com/.../Reuters_NewsScope_Event_Indices_Whitepaper.pdf", "accessDate": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2010-05-03T21:20:47Z", "dateModified": "2010-05-03T21:21:26Z" } } ]