[ { "key": "3P6H87ZE", "version": 56, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/3P6H87ZE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/3P6H87ZE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 484030, "username": "rahulbot", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/rahulbot", "type": "text/html" } } }, "creatorSummary": "Williams et al.", "parsedDate": "2015", "numChildren": 0 }, "data": { "key": "3P6H87ZE", "version": 56, "itemType": "journalArticle", "title": "City Digits: Local Lotto: Developing Youth Data Literacy by Investigating the Lottery", "creators": [ { "creatorType": "author", "firstName": "Sarah", "lastName": "Williams" }, { "creatorType": "author", "firstName": "Erica", "lastName": "Deahl" }, { "creatorType": "author", "firstName": "Laurie", "lastName": "Rubel" }, { "creatorType": "author", "firstName": "Vivian", "lastName": "Lim" } ], "abstractNote": "", "publicationTitle": "Journal of Digital and Media Literacy", "publisher": "", "place": "", "date": "2015", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.jodml.org/2014/12/15/city-digits-local-lotto-developing-youth-data-literacy-by-investigating-the-lottery/", "accessDate": "2015-03-19T18:13:04Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "City Digits", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "data literacy" } ], "collections": [], "relations": {}, "dateAdded": "2015-12-30T02:05:00Z", "dateModified": "2015-12-30T02:05:00Z" } }, { "key": "DKD5RZSR", "version": 46, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/DKD5RZSR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/DKD5RZSR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 484030, "username": "rahulbot", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/rahulbot", "type": "text/html" } } }, "creatorSummary": "Benkler et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "DKD5RZSR", "version": 46, "itemType": "journalArticle", "title": "Social mobilization and the networked public sphere: Mapping the SOPA-PIPA debate", "creators": [ { "creatorType": "author", "firstName": "Yochai", "lastName": "Benkler" }, { "creatorType": "author", "firstName": "Hal", "lastName": "Roberts" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Faris" }, { "creatorType": "author", "firstName": "Alicia", "lastName": "Solow-Niederman" }, { "creatorType": "author", "firstName": "Bruce", "lastName": "Etling" } ], "abstractNote": "", "publicationTitle": "Berkman Center Research Publication", "publisher": "", "place": "", "date": "2013", "volume": "", "issue": "2013-16", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2295953", "accessDate": "2014-06-24T03:15:53Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Social mobilization and the networked public sphere", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-24T03:15:53Z", "dateModified": "2014-06-24T03:15:53Z" } }, { "key": "I7SWA55R", "version": 42, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/I7SWA55R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/I7SWA55R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Odon de Alencar et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "I7SWA55R", "version": 42, "itemType": "conferencePaper", "title": "Geographical Classification of Documents Using Evidence from Wikipedia", "creators": [ { "creatorType": "author", "firstName": "Rafael", "lastName": "Odon de Alencar" }, { "creatorType": "author", "firstName": "Clodoveu Augusto, Jr.", "lastName": "Davis" }, { "creatorType": "author", "firstName": "Marcos André", "lastName": "Gonçalves" } ], "abstractNote": "Obtaining or approximating a geographic location for search results often motivates users to include place names and other geography-related terms in their queries. Previous work shows that queries that include geography-related terms correspond to a significant share of the users' demand. Therefore, it is important to recognize the association of documents to places in order to adequately respond to such queries. This paper describes strategies for text classification into geography-related categories, using evidence extracted from Wikipedia. We use terms that correspond to entry titles and the connections between entries in Wikipedia's graph to establish a semantic network from which classification features are generated. Results of experiments using a news data-set, classified over Brazilian states, show that such terms constitute valid evidence for the geographical classification of documents, and demonstrate the potential of this technique for text classification.", "proceedingsTitle": "Proceedings of the 6th Workshop on Geographic Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "12:1–12:8", "series": "GIR '10", "seriesNumber": "", "DOI": "10.1145/1722080.1722096", "ISBN": "978-1-60558-826-1", "citationKey": "", "url": "http://doi.acm.org/10.1145/1722080.1722096", "accessDate": "2014-06-21T11:39:12Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "geographic information retrieval", "type": 1 }, { "tag": "geospatial evidence", "type": 1 }, { "tag": "text classification", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:39:12Z", "dateModified": "2014-06-21T11:39:12Z" } }, { "key": "J6SPVGGE", "version": 41, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/J6SPVGGE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/J6SPVGGE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Qin et al.", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "J6SPVGGE", "version": 41, "itemType": "conferencePaper", "title": "An Efficient Location Extraction Algorithm by Leveraging Web Contextual Information", "creators": [ { "creatorType": "author", "firstName": "Teng", "lastName": "Qin" }, { "creatorType": "author", "firstName": "Rong", "lastName": "Xiao" }, { "creatorType": "author", "firstName": "Lei", "lastName": "Fang" }, { "creatorType": "author", "firstName": "Xing", "lastName": "Xie" }, { "creatorType": "author", "firstName": "Lei", "lastName": "Zhang" } ], "abstractNote": "A typical location extraction approach consists of two steps, location name detection and location entity disambiguation. Promising results have been obtained in the last decade based on natural language processing technologies. However, there are still two challenges which requires further investigation: 1)How to leverage the prior and contextual evidence to improve the location extraction performance, and 2) How to utilize the interdependence information between the named entity recognition step and disambiguation step. In this paper, we propose an iterative detection-ranking framework to address these problems as well as a set of novel features to mine contextual information from web resources. Experimental results show that our solution outperforms the state-of-the-art approaches, including Metacarta GeoTagger and Yahoo Placemaker.", "proceedingsTitle": "Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "53–60", "series": "GIS '10", "seriesNumber": "", "DOI": "10.1145/1869790.1869801", "ISBN": "978-1-4503-0428-3", "citationKey": "", "url": "http://doi.acm.org/10.1145/1869790.1869801", "accessDate": "2014-06-21T11:36:28Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:36:28Z", "dateModified": "2014-06-21T11:36:28Z" } }, { "key": "9SGBVS8Q", "version": 40, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/9SGBVS8Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/9SGBVS8Q", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Sankaranarayanan et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "9SGBVS8Q", "version": 40, "itemType": "conferencePaper", "title": "TwitterStand: News in Tweets", "creators": [ { "creatorType": "author", "firstName": "Jagan", "lastName": "Sankaranarayanan" }, { "creatorType": "author", "firstName": "Hanan", "lastName": "Samet" }, { "creatorType": "author", "firstName": "Benjamin E.", "lastName": "Teitler" }, { "creatorType": "author", "firstName": "Michael D.", "lastName": "Lieberman" }, { "creatorType": "author", "firstName": "Jon", "lastName": "Sperling" } ], "abstractNote": "Twitter is an electronic medium that allows a large user populace to communicate with each other simultaneously. Inherent to Twitter is an asymmetrical relationship between friends and followers that provides an interesting social network like structure among the users of Twitter. Twitter messages, called tweets, are restricted to 140 characters and thus are usually very focused. We investigate the use of Twitter to build a news processing system, called TwitterStand, from Twitter tweets. The idea is to capture tweets that correspond to late breaking news. The result is analogous to a distributed news wire service. The difference is that the identities of the contributors/reporters are not known in advance and there may be many of them. Furthermore, tweets are not sent according to a schedule: they occur as news is happening, and tend to be noisy while usually arriving at a high throughput rate. Some of the issues addressed include removing the noise, determining tweet clusters of interest bearing in mind that the methods must be online, and determining the relevant locations associated with the tweets.", "proceedingsTitle": "Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "42–51", "series": "GIS '09", "seriesNumber": "", "DOI": "10.1145/1653771.1653781", "ISBN": "978-1-60558-649-6", "citationKey": "", "url": "http://doi.acm.org/10.1145/1653771.1653781", "accessDate": "2014-06-21T11:34:29Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "TwitterStand", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Twitter", "type": 1 }, { "tag": "geotagging", "type": 1 }, { "tag": "news", "type": 1 }, { "tag": "online clustering", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:34:29Z", "dateModified": "2014-06-21T11:34:29Z" } }, { "key": "3XN5IBQW", "version": 39, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/3XN5IBQW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/3XN5IBQW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Lieberman and Samet", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "3XN5IBQW", "version": 39, "itemType": "conferencePaper", "title": "Adaptive Context Features for Toponym Resolution in Streaming News", "creators": [ { "creatorType": "author", "firstName": "Michael D.", "lastName": "Lieberman" }, { "creatorType": "author", "firstName": "Hanan", "lastName": "Samet" } ], "abstractNote": "News sources around the world generate constant streams of information, but effective streaming news retrieval requires an intimate understanding of the geographic content of news. This process of understanding, known as geotagging, consists of first finding words in article text that correspond to location names (toponyms), and second, assigning each toponym its correct lat/long values. The latter step, called toponym resolution, can also be considered a classification problem, where each of the possible interpretations for each toponym is classified as correct or incorrect. Hence, techniques from supervised machine learning can be applied to improve accuracy. New classification features to improve toponym resolution, termed adaptive context features, are introduced that consider a window of context around each toponym, and use geographic attributes of toponyms in the window to aid in their correct resolution. Adaptive parameters controlling the window's breadth and depth afford flexibility in managing a tradeoff between feature computation speed and resolution accuracy, allowing the features to potentially apply to a variety of textual domains. Extensive experiments with three large datasets of streaming news demonstrate the new features' effectiveness over two widely-used competing methods.", "proceedingsTitle": "Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "731–740", "series": "SIGIR '12", "seriesNumber": "", "DOI": "10.1145/2348283.2348381", "ISBN": "978-1-4503-1472-5", "citationKey": "", "url": "http://doi.acm.org/10.1145/2348283.2348381", "accessDate": "2014-06-21T11:31:57Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "adaptive context", "type": 1 }, { "tag": "geotagging", "type": 1 }, { "tag": "machine learning", "type": 1 }, { "tag": "streaming news", "type": 1 }, { "tag": "toponym resolution", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:31:57Z", "dateModified": "2014-06-21T11:31:57Z" } }, { "key": "ATPSQ8SZ", "version": 38, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/ATPSQ8SZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/ATPSQ8SZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Lingad et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "ATPSQ8SZ", "version": 38, "itemType": "conferencePaper", "title": "Location Extraction from Disaster-related Microblogs", "creators": [ { "creatorType": "author", "firstName": "John", "lastName": "Lingad" }, { "creatorType": "author", "firstName": "Sarvnaz", "lastName": "Karimi" }, { "creatorType": "author", "firstName": "Jie", "lastName": "Yin" } ], "abstractNote": "Location information is critical to understanding the impact of a disaster, including where the damage is, where people need assistance and where help is available. We investigate the feasibility of applying Named Entity Recognizers to extract locations from microblogs, at the level of both geo-location and point-of-interest. Our experimental results show that such tools once retrained on microblog data have great potential to detect the where information, even at the granularity of point-of-interest.", "proceedingsTitle": "Proceedings of the 22Nd International Conference on World Wide Web Companion", "conferenceName": "", "publisher": "International World Wide Web Conferences Steering Committee", "place": "Republic and Canton of Geneva, Switzerland", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1017–1020", "series": "WWW '13 Companion", "seriesNumber": "", "DOI": "", "ISBN": "978-1-4503-2038-2", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?id=2487788.2488108", "accessDate": "2014-06-21T11:30:25Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "location extraction", "type": 1 }, { "tag": "named entity recognition", "type": 1 }, { "tag": "social media mining", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:30:25Z", "dateModified": "2014-06-21T11:30:25Z" } }, { "key": "XMBGXV9R", "version": 37, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/XMBGXV9R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/XMBGXV9R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Lieberman et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "XMBGXV9R", "version": 37, "itemType": "conferencePaper", "title": "STEWARD: Architecture of a Spatio-textual Search Engine", "creators": [ { "creatorType": "author", "firstName": "Michael D.", "lastName": "Lieberman" }, { "creatorType": "author", "firstName": "Hanan", "lastName": "Samet" }, { "creatorType": "author", "firstName": "Jagan", "lastName": "Sankaranarayanan" }, { "creatorType": "author", "firstName": "Jon", "lastName": "Sperling" } ], "abstractNote": "STEWARD (\"Spatio-Textual Extraction on the Web Aiding Retrieval of Documents\"), a system for extracting, querying, and visualizing textual references to geographic locations in unstructured text documents, is presented. Methods for retrieving and processing web documents, extracting and disambiguating georeferences, and identifying geographic focus are described. A brief overview of STEWARD's querying capabilities, as well as the design of an intuitive user interface, are provided. Finally, several application scenarios and future extensions to STEWARD are discussed.", "proceedingsTitle": "Proceedings of the 15th Annual ACM International Symposium on Advances in Geographic Information Systems", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "25:1–25:8", "series": "GIS '07", "seriesNumber": "", "DOI": "10.1145/1341012.1341045", "ISBN": "978-1-59593-914-2", "citationKey": "", "url": "http://doi.acm.org/10.1145/1341012.1341045", "accessDate": "2014-06-21T11:15:41Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "STEWARD", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "STEWARD", "type": 1 }, { "tag": "geocoding", "type": 1 }, { "tag": "spatio-textual search engine", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:15:41Z", "dateModified": "2014-06-21T11:15:41Z" } }, { "key": "FPQEA2QZ", "version": 36, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/FPQEA2QZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/FPQEA2QZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Karimzadeh et al.", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "FPQEA2QZ", "version": 36, "itemType": "conferencePaper", "title": "GeoTxt: A Web API to Leverage Place References in Text", "creators": [ { "creatorType": "author", "firstName": "Morteza", "lastName": "Karimzadeh" }, { "creatorType": "author", "firstName": "Wenyi", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Siddhartha", "lastName": "Banerjee" }, { "creatorType": "author", "firstName": "Jan Oliver", "lastName": "Wallgrün" }, { "creatorType": "author", "firstName": "Frank", "lastName": "Hardisty" }, { "creatorType": "author", "firstName": "Scott", "lastName": "Pezanowski" }, { "creatorType": "author", "firstName": "Prasenjit", "lastName": "Mitra" }, { "creatorType": "author", "firstName": "Alan M.", "lastName": "MacEachren" } ], "abstractNote": "Associating place name mentions in unstructured text with their actual references in geographic space is vital to enable spatial queries and analysis. In this paper, we introduce GeoTxt, a web API plus human-usable web tool designed and implemented to tackle three components of place-reference processing from text, namely: extraction, disambiguation, and geolocation of place names mentioned in unstructured text. Current GeoTxt development is focused particularly on support for processing short microblog posts.", "proceedingsTitle": "Proceedings of the 7th Workshop on Geographic Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "72–73", "series": "GIR '13", "seriesNumber": "", "DOI": "10.1145/2533888.2533942", "ISBN": "978-1-4503-2241-6", "citationKey": "", "url": "http://doi.acm.org/10.1145/2533888.2533942", "accessDate": "2014-06-21T11:08:25Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "GeoTxt", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "geocoding", "type": 1 }, { "tag": "geographic information retrieval", "type": 1 }, { "tag": "geographic information systems", "type": 1 }, { "tag": "natural language processing", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:08:25Z", "dateModified": "2014-06-21T11:08:25Z" } }, { "key": "3BKC6GCD", "version": 35, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/3BKC6GCD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/3BKC6GCD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Atkinson and Van der Goot", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "3BKC6GCD", "version": 35, "itemType": "conferencePaper", "title": "Near Real Time Information Mining in Multilingual News", "creators": [ { "creatorType": "author", "firstName": "Martin", "lastName": "Atkinson" }, { "creatorType": "author", "firstName": "Erik", "lastName": "Van der Goot" } ], "abstractNote": "This paper presents a near real-time multilingual news monitoring and analysis system that forms the backbone of our research work. The system integrates technologies to address the problems related to information extraction and analysis of open source intelligence on the World Wide Web. By chaining together different techniques in text mining, automated machine learning and statistical analysis, we can automatically determine who, where and, to a certain extent, what is being reported in news articles.", "proceedingsTitle": "Proceedings of the 18th International Conference on World Wide Web", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1153–1154", "series": "WWW '09", "seriesNumber": "", "DOI": "10.1145/1526709.1526903", "ISBN": "978-1-60558-487-4", "citationKey": "", "url": "http://doi.acm.org/10.1145/1526709.1526903", "accessDate": "2014-06-21T11:00:38Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "automated media monitoring", "type": 1 }, { "tag": "information mining and analysis", "type": 1 }, { "tag": "multi-linguality", "type": 1 }, { "tag": "open source text", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T11:00:38Z", "dateModified": "2014-06-21T11:00:38Z" } }, { "key": "TDSUH4M9", "version": 34, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/TDSUH4M9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/TDSUH4M9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Leidner and Lieberman", "parsedDate": "2011-07", "numChildren": 0 }, "data": { "key": "TDSUH4M9", "version": 34, "itemType": "journalArticle", "title": "Detecting Geographical References in the Form of Place Names and Associated Spatial Natural Language", "creators": [ { "creatorType": "author", "firstName": "Jochen L.", "lastName": "Leidner" }, { "creatorType": "author", "firstName": "Michael D.", "lastName": "Lieberman" } ], "abstractNote": "Recognizing spatial language in text documents, termed geoparsing, is useful for many applications, because together with mapping such language to lat/long values, also known as geocoding, it enables the connection of the unstructured textual realm with the structured realm of Geographic Information Systems (GIS) [11]. For example, news stories about events happening in a particular location can be explored on a map for a spatial understanding of these events, as implemented by applications like the European Media Monitor (EMM) [18] and NewsStand [13, 20]. Web pages, blogs, encyclopedia articles, news stories, tweets and travel reports can all benefit from such interlinking with maps, which requires the recognition of spatial language. Note that geoparsing can be considered as a more specific application of the task of Named Entity Recognition and Classification (NERC): NERC is concerned with automatically recognizing proper nouns of any kind, often meant to include monetary amounts, dates, and other types, while geoparsing is the NERC task applied to locations specifically. Geoparsing is also known by many names in the literature, including geotagging, georecognition, and toponym recognition, but for consistency, here we will refer only to geoparsing. In this paper, we provide an overview of the challenges related to geoparsing, several families of geoparsing methods, existing systems and data collections available for performing geoparsing, and open research questions related to geoparsing.", "publicationTitle": "SIGSPATIAL Special", "publisher": "", "place": "", "date": "July 2011", "volume": "3", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "5–11", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1145/2047296.2047298", "citationKey": "", "url": "http://doi.acm.org/10.1145/2047296.2047298", "accessDate": "2014-06-21T10:55:52Z", "PMID": "", "PMCID": "", "ISSN": "1946-7729", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-21T10:55:52Z", "dateModified": "2014-06-21T10:55:52Z" } }, { "key": "JVWRVMFD", "version": 33, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/JVWRVMFD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/JVWRVMFD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Hill et al.", "parsedDate": "2002", "numChildren": 0 }, "data": { "key": "JVWRVMFD", "version": 33, "itemType": "conferencePaper", "title": "Digital Gazetteers: Integration into Distributed Digital Library Services", "creators": [ { "creatorType": "author", "firstName": "Linda L.", "lastName": "Hill" }, { "creatorType": "author", "firstName": "Gail", "lastName": "Hodge" }, { "creatorType": "author", "firstName": "David", "lastName": "Smith" } ], "abstractNote": "This NKOS workshop for JCDL (the 5th in the series: http://nkos.slis.kent.edu/) will focus on work-in-progress on gazetteer services and gazetteer-related projects in connection with distributed digital library services. It builds on the Digital Gazetteer Information Exchange (DGIE) workshop funded by the NSF in October 1999.Digital gazetteers are specialized KOS that map placenames and types of places to map-based locations and thus integrate word-based georeferencing to map-based georeferencing. The format consists of invited and selected presentations and discussion sessions, with the goal of developing collaborations for future research and development.Participants may provide handouts describing their own gazetteer and other NKOS related projects and will be given the opportunity to introduce their work and their interests briefly.", "proceedingsTitle": "Proceedings of the 2Nd ACM/IEEE-CS Joint Conference on Digital Libraries", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2002", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "427–427", "series": "JCDL '02", "seriesNumber": "", "DOI": "10.1145/544220.544377", "ISBN": "1-58113-513-0", "citationKey": "", "url": "http://doi.acm.org/10.1145/544220.544377", "accessDate": "2014-06-21T10:55:08Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Digital Gazetteers", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "controlled vocabularies", "type": 1 }, { "tag": "gazetteer and thesaurus protocols", "type": 1 }, { "tag": "gazetteers", "type": 1 }, { "tag": "geoparsing", "type": 1 }, { "tag": "geospatial digital library components", "type": 1 }, { "tag": "networked knowledge organization systems", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T10:55:08Z", "dateModified": "2014-06-21T10:55:08Z" } }, { "key": "FQGQFEIM", "version": 32, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/FQGQFEIM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/FQGQFEIM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Creel and Weimer", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "FQGQFEIM", "version": 32, "itemType": "conferencePaper", "title": "Toponym Extraction and Resolution in a Digital Library", "creators": [ { "creatorType": "author", "firstName": "James S.", "lastName": "Creel" }, { "creatorType": "author", "firstName": "Katherine", "lastName": "Weimer" } ], "abstractNote": "Geospatial metadata enable rich and varied interfaces to digital collections, and present unique challenges and affordances for automated extraction. We describe our findings developing and utilizing a geoparser for the Texas A&M University Libraries' Institutional Repository.", "proceedingsTitle": "Proceedings of the 12th ACM/IEEE-CS Joint Conference on Digital Libraries", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "415–416", "series": "JCDL '12", "seriesNumber": "", "DOI": "10.1145/2232817.2232918", "ISBN": "978-1-4503-1154-0", "citationKey": "", "url": "http://doi.acm.org/10.1145/2232817.2232918", "accessDate": "2014-06-21T10:53:34Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "geographic information systems", "type": 1 }, { "tag": "geoparsing", "type": 1 }, { "tag": "georesolution", "type": 1 }, { "tag": "geotagging", "type": 1 }, { "tag": "metadata assignment", "type": 1 }, { "tag": "named entity recognition", "type": 1 }, { "tag": "named entity resolution", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T10:53:34Z", "dateModified": "2014-06-21T10:53:34Z" } }, { "key": "T8MNGBXH", "version": 31, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/T8MNGBXH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/T8MNGBXH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Zubizarreta et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "T8MNGBXH", "version": 31, "itemType": "conferencePaper", "title": "A Georeferencing Multistage Method for Locating Geographic Context in Web Search", "creators": [ { "creatorType": "author", "firstName": "Álvaro", "lastName": "Zubizarreta" }, { "creatorType": "author", "firstName": "Pablo", "lastName": "de la Fuente" }, { "creatorType": "author", "firstName": "José M.", "lastName": "Cantera" }, { "creatorType": "author", "firstName": "Mario", "lastName": "Arias" }, { "creatorType": "author", "firstName": "Jorge", "lastName": "Cabrero" }, { "creatorType": "author", "firstName": "Guido", "lastName": "García" }, { "creatorType": "author", "firstName": "César", "lastName": "Llamas" }, { "creatorType": "author", "firstName": "Jesús", "lastName": "Vegas" } ], "abstractNote": "The geographic scope of Web pages is becoming an essential dimension of Web search, especially for mobile users. This paper shows a multistage method for assigning a geographic focus to Web pages (GeoReferencing) according to their text contents. We suggest several heuristics for the disambiguation toponyms and a scoring procedure for focus determination. Furthermore, we provide an experimental methodology for evaluating the accuracy. Finally, we obtained promising results of over 70% accuracy with a city-level resolution.", "proceedingsTitle": "Proceedings of the 17th ACM Conference on Information and Knowledge Management", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1485–1486", "series": "CIKM '08", "seriesNumber": "", "DOI": "10.1145/1458082.1458347", "ISBN": "978-1-59593-991-3", "citationKey": "", "url": "http://doi.acm.org/10.1145/1458082.1458347", "accessDate": "2014-06-21T10:52:16Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "geocoding", "type": 1 }, { "tag": "geoparsing", "type": 1 }, { "tag": "georeferencing", "type": 1 }, { "tag": "gir", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T10:52:16Z", "dateModified": "2014-06-21T10:52:16Z" } }, { "key": "IATKARGE", "version": 30, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/IATKARGE", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/IATKARGE", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Ding et al.", "parsedDate": "2000", "numChildren": 0 }, "data": { "key": "IATKARGE", "version": 30, "itemType": "conferencePaper", "title": "Computing Geographical Scopes of Web Resources", "creators": [ { "creatorType": "author", "firstName": "Junyan", "lastName": "Ding" }, { "creatorType": "author", "firstName": "Luis", "lastName": "Gravano" }, { "creatorType": "author", "firstName": "Narayanan", "lastName": "Shivakumar" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 26th International Conference on Very Large Data Bases", "conferenceName": "", "publisher": "Morgan Kaufmann Publishers Inc.", "place": "San Francisco, CA, USA", "date": "2000", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "545–556", "series": "VLDB '00", "seriesNumber": "", "DOI": "", "ISBN": "1-55860-715-3", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?id=645926.672013", "accessDate": "2014-06-21T10:49:27Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-21T10:49:27Z", "dateModified": "2014-06-21T10:49:27Z" } }, { "key": "8QCUQ3RU", "version": 29, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/8QCUQ3RU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/8QCUQ3RU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Adelfio and Samet", "parsedDate": "2013", "numChildren": 0 }, "data": { "key": "8QCUQ3RU", "version": 29, "itemType": "conferencePaper", "title": "GeoWhiz: Toponym Resolution Using Common Categories", "creators": [ { "creatorType": "author", "firstName": "Marco D.", "lastName": "Adelfio" }, { "creatorType": "author", "firstName": "Hanan", "lastName": "Samet" } ], "abstractNote": "Determining geographic interpretations for place names, or toponyms, involves resolving multiple types of ambiguity. Place names commonly occur within lists and data tables, whose authors frequently omit qualifications (such as city or state containers) for place names because they expect the meaning of individual place names to be obvious from context. GeoWhiz is a system that demonstrates a novel technique for place name disambiguation (also known as toponym resolution). The system uses Bayesian inference to assign categories to user-specified lists of place names, then interprets individual toponyms based on the most likely category assignments. The categories are defined along three orthogonal dimensions: place types (e.g., cities, capitals, rivers, etc.), geographic containers, and prominence (e.g., based on population). A map interface enables users to explore possible interpretations and compare the interpretations that are most likely based on selected categories.", "proceedingsTitle": "Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2013", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "532–535", "series": "SIGSPATIAL'13", "seriesNumber": "", "DOI": "10.1145/2525314.2525321", "ISBN": "978-1-4503-2521-9", "citationKey": "", "url": "http://doi.acm.org/10.1145/2525314.2525321", "accessDate": "2014-06-21T09:59:10Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "GeoWhiz", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "geotagging", "type": 1 }, { "tag": "structured data extraction", "type": 1 }, { "tag": "toponym resolution", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-21T09:59:10Z", "dateModified": "2014-06-21T09:59:10Z" } }, { "key": "ZS9DGSV5", "version": 27, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/ZS9DGSV5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/ZS9DGSV5", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Smith and Mann", "parsedDate": "2003", "numChildren": 0 }, "data": { "key": "ZS9DGSV5", "version": 27, "itemType": "conferencePaper", "title": "Bootstrapping Toponym Classifiers", "creators": [ { "creatorType": "author", "firstName": "David A.", "lastName": "Smith" }, { "creatorType": "author", "firstName": "Gideon S.", "lastName": "Mann" } ], "abstractNote": "We present minimally supervised methods for training and testing geographic name disambiguation (GND) systems. We train data-driven place name classifiers using toponyms already disambiguated in the training text --- by such existing cues as \"Nashville, Tenn.\" or \"Springfield, MA\" --- and test the system on texts where these cues have been stripped out and on hand-tagged historical texts. We experiment on three English-language corpora of varying provenance and complexity: newsfeed from the 1990s, personal narratives from the 19th century American west, and memoirs and records of the U.S. Civil War. Disambiguation accuracy ranges from 87% for news to 69% for some historical collections.", "proceedingsTitle": "Proceedings of the HLT-NAACL 2003 Workshop on Analysis of Geographic References - Volume 1", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Stroudsburg, PA, USA", "date": "2003", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "45–49", "series": "HLT-NAACL-GEOREF '03", "seriesNumber": "", "DOI": "10.3115/1119394.1119401", "ISBN": "", "citationKey": "", "url": "http://dx.doi.org/10.3115/1119394.1119401", "accessDate": "2014-06-21T09:58:02Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-21T09:58:02Z", "dateModified": "2014-06-21T09:58:02Z" } }, { "key": "K6FJK5JJ", "version": 26, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/K6FJK5JJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/K6FJK5JJ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Buscaldi", "parsedDate": "2011-07", "numChildren": 0 }, "data": { "key": "K6FJK5JJ", "version": 26, "itemType": "journalArticle", "title": "Approaches to Disambiguating Toponyms", "creators": [ { "creatorType": "author", "firstName": "Davide", "lastName": "Buscaldi" } ], "abstractNote": "Many approaches have been proposed in recent years in the context of Geographic Information Retrieval (GIR), mostly in order to deal with geographically constrained information in un-structured texts. Most of these approaches share a common scheme: in order to disambiguate a toponym t with n possible referents in a document d, they find a certain number of context toponyms c0,...,ck that are contained in d. A score for each referent is calculated according to the context toponyms, and the referent with the highest score is selected. According to the method used to calculate the score, Toponym Disambiguation (TD) methods may be grouped into three main categories, as proposed by [7]: • map-based: methods that use an explicit representation of toponyms on a map, for instance to calculate the average distance of unambiguous context toponyms from referents; • knowledge-based: methods that exploit external knowledge sources such as gazetteers, Wikipedia or ontologies to find disambiguation clues; • data-driven or supervised: methods based on machine learning techniques.", "publicationTitle": "SIGSPATIAL Special", "publisher": "", "place": "", "date": "July 2011", "volume": "3", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "16–19", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1145/2047296.2047300", "citationKey": "", "url": "http://doi.acm.org/10.1145/2047296.2047300", "accessDate": "2014-06-21T09:55:52Z", "PMID": "", "PMCID": "", "ISSN": "1946-7729", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-21T09:55:52Z", "dateModified": "2014-06-21T09:55:52Z" } }, { "key": "XRSBACFP", "version": 25, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/XRSBACFP", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/XRSBACFP", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Sandhaus", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "XRSBACFP", "version": 25, "itemType": "document", "title": "The New York Times Annotated Corpus LDC2008T19", "creators": [ { "creatorType": "author", "firstName": "Evan", "lastName": "Sandhaus" } ], "abstractNote": "The New York Times Annotated Corpus contains over 1.8 million articles written and published by the New York Times between January 1, 1987 and June 19, 2007 with article metadata provided by the New York Times Newsroom, the New York Times Indexing Service and the online production staff at nytimes.com. The corpus includes:\n\nOver 1.8 million articles (excluding wire services articles that appeared during the covered period).\nOver 650,000 article summaries written by library \"scientists\".\nOver 1,500,000 articles manually tagged by library \"scientists\" with tags drawn from a normalized indexing vocabulary of people, organizations, locations and topic descriptors.\nOver 275,000 algorithmically-tagged articles that have been hand verified by the online production staff at nytimes.com.\nJava tools for parsing corpus documents from .xml into a memory resident object.\nAs part of the New York Times' indexing procedures, most articles are manually summarized and tagged by a staff of library \"scientists\". This collection contains over 650,000 article-summary pairs which may prove to be useful in the development and evaluation of algorithms for automated document summarization. Also, over 1.5 million documents have at least one tag. Articles are tagged for persons, places, organizations, titles and topics using a controlled vocabulary that is applied consistently across articles. For instance if one article mentions \"Bill Clinton\" and another refers to \"President William Jefferson Clinton\", both articles will be tagged with \"CLINTON, BILL\".\n\nThe New York Times has established a community website for researchers working on the data set at http://groups.google.com/group/nytnlp and encourages feedback and discussion about the corpus.", "type": "", "date": "2008", "publisher": "Linguistic Data Consortium", "place": "", "DOI": "", "citationKey": "", "url": "https://catalog.ldc.upenn.edu/LDC2008T19", "accessDate": "2014-06-19", "archive": "", "archiveLocation": "", "shortTitle": "NYT Annotated Corpus", "language": "English", "libraryCatalog": "LDC2008T19", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-20T19:08:33Z", "dateModified": "2014-06-20T19:10:31Z" } }, { "key": "KIJGS2F4", "version": 20, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/KIJGS2F4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/KIJGS2F4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Amitay et al.", "parsedDate": "2004", "numChildren": 0 }, "data": { "key": "KIJGS2F4", "version": 20, "itemType": "conferencePaper", "title": "Web-a-where: Geotagging Web Content", "creators": [ { "creatorType": "author", "firstName": "Einat", "lastName": "Amitay" }, { "creatorType": "author", "firstName": "Nadav", "lastName": "Har'El" }, { "creatorType": "author", "firstName": "Ron", "lastName": "Sivan" }, { "creatorType": "author", "firstName": "Aya", "lastName": "Soffer" } ], "abstractNote": "We describe Web-a-Where, a system for associating geography with Web pages. Web-a-Where locates mentions of places and determines the place each name refers to. In addition, it assigns to each page a geographic focus --- a locality that the page discusses as a whole. The tagging process is simple and fast, aimed to be applied to large collections of Web pages and to facilitate a variety of location-based applications and data analyses.Geotagging involves arbitrating two types of ambiguities: geo/non-geo and geo/geo. A geo/non-geo ambiguity occurs when a place name also has a non-geographic meaning, such as a person name (e.g., Berlin) or a common word (Turkey). Geo/geo ambiguity arises when distinct places have the same name, as in London, England vs. London, Ontario.An implementation of the tagger within the framework of the WebFountain data mining system is described, and evaluated on several corpora of real Web pages. Precision of up to 82% on individual geotags is achieved. We also evaluate the relative contribution of various heuristics the tagger employs, and evaluate the focus-finding algorithm using a corpus pretagged with localities, showing that as many as 91% of the foci reported are correct up to the country level.", "proceedingsTitle": "Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2004", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "273–280", "series": "SIGIR '04", "seriesNumber": "", "DOI": "10.1145/1008992.1009040", "ISBN": "1-58113-881-4", "citationKey": "", "url": "http://doi.acm.org/10.1145/1008992.1009040", "accessDate": "2014-06-20T19:04:51Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Web-a-where", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "disambiguation", "type": 1 }, { "tag": "gazetteer", "type": 1 }, { "tag": "geographic tagging", "type": 1 }, { "tag": "information retrieval", "type": 1 }, { "tag": "natural language processing", "type": 1 }, { "tag": "text mining", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-20T19:04:51Z", "dateModified": "2014-06-20T19:04:51Z" } }, { "key": "QWJ5CVHZ", "version": 18, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/QWJ5CVHZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/QWJ5CVHZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Mogelson", "parsedDate": "2012-02-01", "numChildren": 0 }, "data": { "key": "QWJ5CVHZ", "version": 18, "itemType": "newspaperArticle", "title": "The Hard Way Out of Afghanistan", "creators": [ { "creatorType": "author", "firstName": "Luke", "lastName": "Mogelson" } ], "abstractNote": "Winding down the war means pushing deeper into Taliban country every day.", "publicationTitle": "The New York Times", "publisher": "", "place": "", "date": "2012-02-01", "volume": "", "issue": "", "edition": "", "section": "Magazine", "pages": "", "ISSN": "0362-4331", "DOI": "", "citationKey": "", "url": "http://www.nytimes.com/2012/02/05/magazine/afghanistan.html", "accessDate": "2014-06-20T14:57:34Z", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NYTimes.com", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Afghanistan War (2001- )", "type": 1 }, { "tag": "Improvised Explosive Devices", "type": 1 }, { "tag": "Taliban", "type": 1 }, { "tag": "United States Defense and Military Forces", "type": 1 }, { "tag": "United States Marine Corps", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-20T14:57:34Z", "dateModified": "2014-06-20T14:57:34Z" } }, { "key": "6W3WB92B", "version": 16, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/6W3WB92B", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/6W3WB92B", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Calmes and Castle", "parsedDate": "2013-06-18", "numChildren": 0 }, "data": { "key": "6W3WB92B", "version": 16, "itemType": "newspaperArticle", "title": "G-8 Meeting Ends With Cordial Stalemate on Syria", "creators": [ { "creatorType": "author", "firstName": "Jackie", "lastName": "Calmes" }, { "creatorType": "author", "firstName": "Stephen", "lastName": "Castle" } ], "abstractNote": "The United States and leaders of other major industrialized nations averted a clash with President Vladimir Putin of Russia by avoiding mention of the most contentious matters that divided them.", "publicationTitle": "The New York Times", "publisher": "", "place": "", "date": "2013-06-18", "volume": "", "issue": "", "edition": "", "section": "World / Europe", "pages": "", "ISSN": "0362-4331", "DOI": "", "citationKey": "", "url": "http://www.nytimes.com/2013/06/19/world/europe/g-8-meeting-ends-with-cordial-stalemate-on-syria.html", "accessDate": "2014-06-20T14:17:01Z", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "NYTimes.com", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Group of Eight", "type": 1 }, { "tag": "Syria", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-20T14:17:01Z", "dateModified": "2014-06-20T14:17:01Z" } }, { "key": "5TKT3V4B", "version": 15, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/5TKT3V4B", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/5TKT3V4B", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1658610, "username": "kanarinka", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/kanarinka", "type": "text/html" } } }, "creatorSummary": "Simon", "parsedDate": "1996", "numChildren": 0 }, "data": { "key": "5TKT3V4B", "version": 15, "itemType": "bookSection", "title": "Designing Organizations for an Information-Rich World", "creators": [ { "creatorType": "author", "firstName": "Herbert A.", "lastName": "Simon" }, { "creatorType": "editor", "firstName": "Donald M.", "lastName": "Lamberton" } ], "abstractNote": "", "bookTitle": "The economics of communication and information", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "1996", "publisher": "Elgar Reference Collection. International Library of Critical Writings in Economics, vol. 70.", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "187-202", "ISBN": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "EBSCOhost", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Analysis of Collective Decision-Making: General D70", "type": 1 }, { "tag": "Belief D83", "type": 1 }, { "tag": "Communication", "type": 1 }, { "tag": "Diffusion Processes O33", "type": 1 }, { "tag": "Information and Knowledge", "type": 1 }, { "tag": "Learning", "type": 1 }, { "tag": "Search", "type": 1 }, { "tag": "Technological Change: Choices and Consequences", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-06-20T10:25:51Z", "dateModified": "2014-06-20T10:25:51Z" } }, { "key": "2ZHRMRG6", "version": 13, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/2ZHRMRG6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/2ZHRMRG6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 484030, "username": "rahulbot", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/rahulbot", "type": "text/html" } } }, "creatorSummary": "Rose et al.", "parsedDate": "2002", "numChildren": 0 }, "data": { "key": "2ZHRMRG6", "version": 13, "itemType": "conferencePaper", "title": "The Reuters Corpus Volume 1-from Yesterday's News to Tomorrow's Language Resources.", "creators": [ { "creatorType": "author", "firstName": "Tony", "lastName": "Rose" }, { "creatorType": "author", "firstName": "Mark", "lastName": "Stevenson" }, { "creatorType": "author", "firstName": "Miles", "lastName": "Whitehead" } ], "abstractNote": "", "proceedingsTitle": "LREC", "conferenceName": "", "publisher": "", "place": "", "date": "2002", "eventPlace": "", "volume": "2", "issue": "", "numberOfVolumes": "", "pages": "827–832", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://lrec.elra.info/proceedings/lrec2002/pdf/80.pdf", "accessDate": "2014-06-20T10:15:56Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-20T10:15:56Z", "dateModified": "2014-06-20T10:15:56Z" } }, { "key": "28NB79ZV", "version": 8, "library": { "type": "group", "id": 270195, "name": "cliff-newskdd", "links": { "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/270195/items/28NB79ZV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/cliff-newskdd/items/28NB79ZV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 484030, "username": "rahulbot", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/rahulbot", "type": "text/html" } } }, "creatorSummary": "Teitler et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "28NB79ZV", "version": 8, "itemType": "conferencePaper", "title": "NewsStand: A new view on news", "creators": [ { "creatorType": "author", "firstName": "Benjamin E.", "lastName": "Teitler" }, { "creatorType": "author", "firstName": "Michael D.", "lastName": "Lieberman" }, { "creatorType": "author", "firstName": "Daniele", "lastName": "Panozzo" }, { "creatorType": "author", "firstName": "Jagan", "lastName": "Sankaranarayanan" }, { "creatorType": "author", "firstName": "Hanan", "lastName": "Samet" }, { "creatorType": "author", "firstName": "Jon", "lastName": "Sperling" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems", "conferenceName": "", "publisher": "ACM", "place": "", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "18", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?id=1463458", "accessDate": "2014-06-20T10:01:46Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "NewsStand", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-06-20T10:01:46Z", "dateModified": "2014-06-20T10:01:46Z" } } ]