{"id":"https://openalex.org/W2149879421","doi":"https://doi.org/10.1145/2362456.2362462","title":"Extracting informative textual parts from web pages containing user-generated content","display_name":"Extracting informative textual parts from web pages containing user-generated content","publication_year":2012,"publication_date":"2012-09-05","ids":{"openalex":"https://openalex.org/W2149879421","doi":"https://doi.org/10.1145/2362456.2362462","mag":"2149879421"},"language":"en","primary_location":{"id":"doi:10.1145/2362456.2362462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2362456.2362462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023518080","display_name":"Nikolaos Pappas","orcid":"https://orcid.org/0000-0002-2004-8111"},"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"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikolaos Pappas","raw_affiliation_strings":["Idiap Research Institute, Rue Marconi, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Rue Marconi, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011872278","display_name":"Georgios Katsimpras","orcid":"https://orcid.org/0000-0003-3697-941X"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Katsimpras","raw_affiliation_strings":["University of the Aegean, Karlovassi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Aegean, Karlovassi, Greece","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737423","display_name":"Efstathios Stamatatos","orcid":"https://orcid.org/0000-0002-1336-9128"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Efstathios Stamatatos","raw_affiliation_strings":["University of the Aegean, Karlovassi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Aegean, Karlovassi, Greece","institution_ids":["https://openalex.org/I98805295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6746,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93964899,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.9652000069618225,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.953000009059906,"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/computer-science","display_name":"Computer science","score":0.8323097229003906},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8273035287857056},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7507648468017578},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6711719632148743},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49437689781188965},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4924810826778412},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4820345640182495},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4650498628616333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3344578146934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323097229003906},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8273035287857056},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7507648468017578},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6711719632148743},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49437689781188965},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4924810826778412},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4820345640182495},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4650498628616333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3344578146934509}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2362456.2362462","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2362456.2362462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:192564","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192564","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192564","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192564","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G4263088022","display_name":null,"funder_award_id":"287872","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5483342299","display_name":null,"funder_award_id":"FP7-ICT","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1515204522","https://openalex.org/W1803802947","https://openalex.org/W1822441068","https://openalex.org/W1931936418","https://openalex.org/W1989338554","https://openalex.org/W2004779840","https://openalex.org/W2005646337","https://openalex.org/W2019264297","https://openalex.org/W2064365756","https://openalex.org/W2072489225","https://openalex.org/W2084358158","https://openalex.org/W2088718234","https://openalex.org/W2096482843","https://openalex.org/W2101909884","https://openalex.org/W2117209866","https://openalex.org/W2146486820","https://openalex.org/W2147428516","https://openalex.org/W2154484245","https://openalex.org/W2161127713","https://openalex.org/W2166419939","https://openalex.org/W2470343719","https://openalex.org/W4243814950"],"related_works":["https://openalex.org/W2083329789","https://openalex.org/W2376574812","https://openalex.org/W2371661150","https://openalex.org/W2389795557","https://openalex.org/W2163588476","https://openalex.org/W4255475599","https://openalex.org/W2128127655","https://openalex.org/W2544674189","https://openalex.org/W2897171874","https://openalex.org/W1987716395"],"abstract_inverted_index":{"The":[0,24,103],"vast":[1],"amount":[2],"of":[3,17,26,41,69,91,113,128,144,155],"user-generated":[4,132],"content":[5,20,133],"on":[6,138],"the":[7,11,15,67,70,74,152,164],"Web":[8],"has":[9],"increased":[10],"need":[12],"for":[13,175],"handling":[14],"problem":[16],"automatically":[18],"processing":[19],"in":[21,38,95,162,180],"web":[22,27,71,75,96,115,176,183],"pages.":[23],"segmentation":[25],"pages":[28,97,129],"and":[29,49,73,110,117,148,168],"noise":[30],"(non-informative":[31],"segment)":[32],"removal":[33],"are":[34,62],"important":[35],"pre-processing":[36],"steps":[37],"a":[39,81,114,139,172,181],"variety":[40],"applications":[42],"such":[43],"as":[44,171],"sentiment":[45],"analysis,":[46],"text":[47],"summarization":[48],"information":[50],"retrieval.":[51],"Currently,":[52],"these":[53],"two":[54],"tasks":[55],"tend":[56],"to":[57,87,120],"be":[58],"handled":[59,63],"separately":[60],"or":[61],"together":[64],"without":[65],"emphasizing":[66],"diversity":[68],"corpora":[72],"page":[76,116,177],"type":[77,101,178],"detection.":[78,102],"We":[79],"present":[80],"unified":[82],"approach":[83],"that":[84],"is":[85,118],"able":[86,119],"provide":[88],"robust":[89],"identification":[90],"informative":[92,165],"textual":[93,166],"parts":[94,123,167],"along":[98],"with":[99],"accurate":[100],"proposed":[104],"algorithm":[105],"takes":[106],"into":[107],"account":[108],"visual":[109],"non-visual":[111],"characteristics":[112],"remove":[121],"noisy":[122],"from":[124],"three":[125],"major":[126],"categories":[127],"which":[130],"contain":[131],"(News,":[134],"Blogs,":[135],"Discussions).":[136],"Based":[137],"human":[140],"annotated":[141],"corpus":[142],"consisting":[143],"diverse":[145],"topics,":[146],"domains":[147],"templates,":[149],"we":[150,158],"demonstrate":[151],"learning":[153],"abilities":[154],"our":[156],"algorithm,":[157],"examine":[159],"its":[160,169],"effectiveness":[161],"extracting":[163],"usage":[170],"rule-based":[173],"classifier":[174],"detection":[179],"realistic":[182],"setting.":[184]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
