{"id":"https://openalex.org/W2120169450","doi":"https://doi.org/10.1145/1298406.1298437","title":"Automated story capture from internet weblogs","display_name":"Automated story capture from internet weblogs","publication_year":2007,"publication_date":"2007-10-28","ids":{"openalex":"https://openalex.org/W2120169450","doi":"https://doi.org/10.1145/1298406.1298437","mag":"2120169450"},"language":"en","primary_location":{"id":"doi:10.1145/1298406.1298437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070125884","display_name":"Andrew S. Gordon","orcid":null},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew S. Gordon","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073799773","display_name":"Qun Cao","orcid":"https://orcid.org/0000-0002-6167-2455"},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qun Cao","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021828171","display_name":"Reid Swanson","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reid Swanson","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070125884"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"],"apc_list":null,"apc_paid":null,"fwci":4.8296,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95005471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.8137292265892029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753127932548523},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6386869549751282},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.629331111907959},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5557761788368225},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.49320071935653687},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.466586172580719},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.404638409614563},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40320077538490295}],"concepts":[{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.8137292265892029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753127932548523},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6386869549751282},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.629331111907959},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5557761788368225},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.49320071935653687},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.466586172580719},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.404638409614563},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40320077538490295},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1298406.1298437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:ADA470419","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&amp;verb=getRecord&amp;metadataPrefix=html&amp;identifier=ADA470419","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1773803948","https://openalex.org/W1991451482","https://openalex.org/W2018560257","https://openalex.org/W2100350189","https://openalex.org/W2139432071","https://openalex.org/W4256500826","https://openalex.org/W6637852806"],"related_works":["https://openalex.org/W2348886128","https://openalex.org/W2388067091","https://openalex.org/W2367656648","https://openalex.org/W2350200549","https://openalex.org/W2362132076","https://openalex.org/W2965396777","https://openalex.org/W2389168924","https://openalex.org/W2067294484","https://openalex.org/W4280593102","https://openalex.org/W2170000670"],"abstract_inverted_index":{"Among":[0],"the":[1,11,64,74],"most":[2],"interesting":[3],"ways":[4],"that":[5],"people":[6],"share":[7],"knowledge":[8,36],"is":[9],"through":[10],"telling":[12],"of":[13,22,69,77,87],"stories,":[14],"i.e.":[15],"first-person":[16],"narratives":[17],"about":[18],"real-life":[19],"experiences.":[20],"Millions":[21],"these":[23],"stories":[24,50,88],"appear":[25],"in":[26],"Internet":[27,52,82],"weblogs,":[28,83],"offering":[29],"a":[30,85,91],"potentially":[31],"valuable":[32],"resource":[33],"for":[34],"future":[35],"management":[37],"and":[38,66],"training":[39],"applications.":[40],"In":[41],"this":[42],"paper":[43],"we":[44],"describe":[45,73],"efforts":[46],"to":[47,81],"automatically":[48],"capture":[49],"from":[51],"weblogs":[53],"by":[54],"extracting":[55],"them":[56],"using":[57],"statistical":[58],"text":[59],"classification":[60],"techniques.":[61],"We":[62,72],"evaluate":[63],"precision":[65],"recall":[67],"performance":[68],"competing":[70],"approaches.":[71],"large-scale":[75],"application":[76],"story":[78],"extraction":[79],"technology":[80],"producing":[84],"corpus":[86],"with":[89],"over":[90],"billion":[92],"words.":[93]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
