{"id":"https://openalex.org/W2099843923","doi":"https://doi.org/10.1145/1390749.1390757","title":"Blogger, stick to your story","display_name":"Blogger, stick to your story","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2099843923","doi":"https://doi.org/10.1145/1390749.1390757","mag":"2099843923"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5103787089","display_name":"Jiyin He","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jiyin He","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071682310","display_name":"Wouter Weerkamp","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wouter Weerkamp","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056272341","display_name":"Martha Larson","orcid":"https://orcid.org/0000-0003-4229-5866"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martha Larson","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam","University of Amsterdam, (Amsterdam)"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"University of Amsterdam, (Amsterdam)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103787089"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":3.5391,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9285454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802324295043945},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6368133425712585},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5957006812095642},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5697636008262634},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5452291965484619},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.536310076713562},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5228065252304077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133775472640991},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41602906584739685},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39810341596603394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3927336633205414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3318592309951782},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09223067760467529},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08457523584365845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08351027965545654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07842221856117249},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07424640655517578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802324295043945},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6368133425712585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5957006812095642},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5697636008262634},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5452291965484619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536310076713562},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5228065252304077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133775472640991},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41602906584739685},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39810341596603394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3927336633205414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3318592309951782},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09223067760467529},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08457523584365845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08351027965545654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07842221856117249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07424640655517578},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1390749.1390757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/2362b955-2f72-4d02-aa9a-075ae056958d","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/blogger-stick-to-your-story-modeling-topical-noise-in-blogs-with-coherence-measures(2362b955-2f72-4d02-aa9a-075ae056958d).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"He, J, Weerkamp, W, Larson, M & de Rijke, M 2008, Blogger, stick to your story: Modeling topical noise in blogs with coherence measures. in D Lopresti, S Roy, K Schulz & L V Subramaniam (eds), Proceedings of SIGIR 2008 Workshop on Analytics for Noisy Unstructured Text Data (AND 08), July 24, 2008, Singapore. ACM International Conference Proceedings Series, vol. 303, Association for Computing Machinery, New York, NY, pp. 39-46, 2nd Workshop on Analytics for Noisy Unstructured Text Data (AND 2008), Singapore, 24/07/08. https://doi.org/10.1145/1390749.1390757","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/2362b955-2f72-4d02-aa9a-075ae056958d","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/blogger-stick-to-your-story-modeling-topical-noise-in-blogs-with-coherence-measures(2362b955-2f72-4d02-aa9a-075ae056958d).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM International Conference Proceedings Series, 303, 39 - 46","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G5898001847","display_name":null,"funder_award_id":"220-80-001017.001.190640.001.501640.002.501612.066.512STE-07-012","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G8126347896","display_name":null,"funder_award_id":"IST-033104","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W35093690","https://openalex.org/W143775383","https://openalex.org/W160659377","https://openalex.org/W1484772416","https://openalex.org/W1503333931","https://openalex.org/W1554728883","https://openalex.org/W1557207628","https://openalex.org/W1594274049","https://openalex.org/W1972594981","https://openalex.org/W1996764654","https://openalex.org/W2012790454","https://openalex.org/W2022828110","https://openalex.org/W2030524533","https://openalex.org/W2079168273","https://openalex.org/W2108743173","https://openalex.org/W2125508747","https://openalex.org/W2125620232","https://openalex.org/W2126226055","https://openalex.org/W2132957691","https://openalex.org/W2145036943","https://openalex.org/W2156152219","https://openalex.org/W2163219878","https://openalex.org/W2169213601","https://openalex.org/W2296207579","https://openalex.org/W2915135611","https://openalex.org/W4241122026","https://openalex.org/W4246858749","https://openalex.org/W6679162469"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3034410548","https://openalex.org/W1982640233","https://openalex.org/W4389011229","https://openalex.org/W2751754983","https://openalex.org/W3036953692","https://openalex.org/W2021920346","https://openalex.org/W4389443772","https://openalex.org/W4318372922","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Topical":[0,39],"noise":[1,27,40],"in":[2,93],"blogs":[3],"arises":[4],"when":[5],"bloggers":[6],"digress":[7],"from":[8],"the":[9,34,44,52,55,64,73,95,104,120],"central":[10],"topical":[11,26,56],"thrust":[12],"of":[13,25,36,54,58,72,89,103,114],"their":[14],"blogs.":[15],"We":[16],"introduce":[17],"a":[18,23,29,47,59,69,87,101],"method":[19],"to":[20,33,80,119],"explicitly":[21],"incorporate":[22],"model":[24,45],"into":[28,43],"language":[30,116],"modeling":[31,117],"approach":[32,118],"task":[35],"blog":[37,77,105,121],"distillation.":[38],"is":[41,98],"integrated":[42],"using":[46],"coherence":[48,74,96],"score,":[49],"which":[50,94],"reflects":[51],"tightness":[53],"structure":[57],"blog.":[60],"Tests":[61],"performed":[62],"on":[63],"TRECBlog06":[65],"corpus":[66],"show":[67],"that":[68],"naive":[70],"integration":[71],"score":[75,97],"as":[76],"prior":[78],"fails":[79],"achieve":[81],"performance":[82],"improvements.":[83],"Instead,":[84],"we":[85],"develop":[86],"set":[88],"more":[90],"sophisticated":[91],"models":[92,110],"weighted":[99],"by":[100],"function":[102],"retrieval":[106],"score.":[107],"The":[108],"proposed":[109],"help":[111],"improve":[112],"effectiveness":[113],"our":[115],"distillation":[122],"task.":[123]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}