{"id":"https://openalex.org/W2112893705","doi":"https://doi.org/10.1145/1178745.1178757","title":"Discovering groups of people in Google news","display_name":"Discovering groups of people in Google news","publication_year":2006,"publication_date":"2006-10-27","ids":{"openalex":"https://openalex.org/W2112893705","doi":"https://doi.org/10.1145/1178745.1178757","mag":"2112893705"},"language":"en","primary_location":{"id":"doi:10.1145/1178745.1178757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1178745.1178757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international workshop on Human-centered multimedia","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/A5103960169","display_name":"Dhiraj Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dhiraj Joshi","raw_affiliation_strings":["The Pennsylvania State University, University Park","The Pennsylvania State University,#R##N#University Park"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University,#R##N#University Park","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012965551","display_name":"Daniel G\u00e1tica-P\u00e9rez","orcid":"https://orcid.org/0000-0001-5488-2182"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Gatica-Perez","raw_affiliation_strings":["IDIAP Research Institute and Ecole Polytechnique Federale de Lausanne (EPFL), Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute and Ecole Polytechnique Federale de Lausanne (EPFL), Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430","https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103960169"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.9952,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.77039835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9883999824523926,"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/T10028","display_name":"Topic Modeling","score":0.9847000241279602,"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.8355287313461304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7432469725608826},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6286251544952393},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6208800077438354},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5828182697296143},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.579303503036499},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5107045769691467},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48852503299713135},{"id":"https://openalex.org/keywords/social-group","display_name":"Social group","score":0.47270914912223816},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4661470949649811},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.43434178829193115},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4328480064868927},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4161282479763031},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3708680272102356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3194047212600708},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09636244177818298}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.8355287313461304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432469725608826},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6286251544952393},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6208800077438354},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5828182697296143},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.579303503036499},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5107045769691467},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48852503299713135},{"id":"https://openalex.org/C180872759","wikidata":"https://www.wikidata.org/wiki/Q874405","display_name":"Social group","level":2,"score":0.47270914912223816},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4661470949649811},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.43434178829193115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4328480064868927},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4161282479763031},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3708680272102356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3194047212600708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09636244177818298},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1178745.1178757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1178745.1178757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international workshop on Human-centered multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.139.1321","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.139.1321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~gatica/publications/JoshiGatica-acmmm-hcm06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W70838842","https://openalex.org/W950821216","https://openalex.org/W1499011913","https://openalex.org/W1542148285","https://openalex.org/W1547561528","https://openalex.org/W1603920809","https://openalex.org/W1660390307","https://openalex.org/W1880262756","https://openalex.org/W2061901927","https://openalex.org/W2097777089","https://openalex.org/W2117495845","https://openalex.org/W2134731454","https://openalex.org/W2138228978","https://openalex.org/W2140124448","https://openalex.org/W2142887429","https://openalex.org/W2144799688","https://openalex.org/W2148108980","https://openalex.org/W2160752569","https://openalex.org/W2165734786","https://openalex.org/W2165874743","https://openalex.org/W3184295504","https://openalex.org/W4233125481","https://openalex.org/W6629971756","https://openalex.org/W6632663641","https://openalex.org/W6637101025","https://openalex.org/W6681144085","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2588002110","https://openalex.org/W2111020819","https://openalex.org/W2082325506","https://openalex.org/W2775171027","https://openalex.org/W2982493961","https://openalex.org/W4389358025","https://openalex.org/W2921491680","https://openalex.org/W4214866631","https://openalex.org/W2171515436","https://openalex.org/W4285156758"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4,125],"the":[5,25,103,116,138],"problem":[6],"of":[7,27,60,84,127,140],"content-based":[8],"social":[9,70,147],"network":[10,71,148],"discovery":[11],"among":[12],"people":[13,36,85,93,109,128],"who":[14],"frequently":[15],"appear":[16],"in":[17,86,102],"world":[18],"news.":[19],"Google":[20],"news":[21,47,88],"is":[22,43,56],"used":[23,123],"as":[24],"source":[26],"data.":[28],"We":[29,135],"describe":[30],"a":[31,87,144],"probabilistic":[32,50],"framework":[33],"for":[34,46],"associating":[35],"with":[37,129],"groups.":[38],"A":[39],"low-dimensional":[40],"topic-based":[41],"representation":[42],"first":[44],"obtained":[45],"stories":[48],"via":[49],"latent":[51],"semantic":[52,61],"analysis":[53,72],"(PLSA).":[54],"This":[55],"followed":[57],"by":[58,63],"construction":[59],"groups":[62,76,113],"clustering":[64],"such":[65],"representations.":[66],"Unlike":[67],"many":[68],"existing":[69],"approaches,":[73],"which":[74,98],"discover":[75],"based":[77],"only":[78],"on":[79,115],"binary":[80],"relations":[81],"(e.g.":[82,107],"co-occurrence":[83],"article),":[89],"our":[90,141],"model":[91,120],"clusters":[92],"using":[94],"their":[95],"topic":[96],"distribution,":[97],"introduces":[99],"contextual":[100],"information":[101],"group":[104],"formation":[105],"process":[106],"some":[108],"belong":[110],"to":[111,124,131],"several":[112],"depending":[114],"specific":[117],"subject).":[118],"The":[119],"has":[121],"been":[122],"evolution":[126],"respect":[130],"topics":[132],"over":[133,143],"time.":[134],"also":[136],"illustrate":[137],"advantages":[139],"approach":[142],"simple":[145],"co-occurrence-based":[146],"extraction":[149],"method.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}