{"id":"https://openalex.org/W2160981577","doi":"https://doi.org/10.1109/nlpke.2009.5313736","title":"Data extraction from Web forums based on similarity of page layout","display_name":"Data extraction from Web forums based on similarity of page layout","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2160981577","doi":"https://doi.org/10.1109/nlpke.2009.5313736","mag":"2160981577"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2009.5313736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","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/A5087100783","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0003-2035-3148"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Information Processing Dept, Information Technology Institute, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Information Processing Dept, Information Technology Institute, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039649740","display_name":"Bicheng Li","orcid":"https://orcid.org/0000-0003-2218-3146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bicheng Li","raw_affiliation_strings":["Information Processing Dept, Information Technology Institute, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Information Processing Dept, Information Technology Institute, Zhengzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100707569","display_name":"Chen Lin","orcid":"https://orcid.org/0000-0002-2275-997X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Lin","raw_affiliation_strings":["Information Processing Dept, Information Technology Institute, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Information Processing Dept, Information Technology Institute, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087100783"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.17543428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9733999967575073,"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/T11478","display_name":"Caching and Content Delivery","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/metadata","display_name":"Metadata","score":0.8302392959594727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8249441981315613},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6390508413314819},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6358107328414917},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6260241270065308},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5681923627853394},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4761873781681061},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4484724998474121},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4329324960708618},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41833579540252686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09988534450531006}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8302392959594727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249441981315613},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6390508413314819},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6358107328414917},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6260241270065308},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5681923627853394},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4761873781681061},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4484724998474121},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4329324960708618},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41833579540252686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09988534450531006},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2009.5313736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2009.5313736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W857958923","https://openalex.org/W938539187","https://openalex.org/W2015551056","https://openalex.org/W2116216325","https://openalex.org/W2132613313","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2162340487","https://openalex.org/W2168358004","https://openalex.org/W4232071090"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2083329789","https://openalex.org/W2376574812"],"abstract_inverted_index":{"Web":[0,46,59,70,94],"forums":[1],"contain":[2],"a":[3],"wealth":[4],"of":[5,35,52,88,92,106,109],"information":[6,21],"resources.":[7],"Forum":[8],"data":[9,57],"can":[10],"be":[11,38],"widely":[12],"used":[13],"in":[14,76,128],"areas":[15],"such":[16],"as":[17],"Internet":[18],"community":[19],"mining,":[20],"retrieval":[22],"and":[23,27,40,130],"public":[24],"opinion":[25],"analysis":[26],"so":[28],"on.":[29],"This":[30],"paper":[31],"solves":[32],"the":[33,45,50,82,89,93,101,110,112],"problems":[34],"what":[36],"should":[37],"extracted":[39],"how":[41],"to":[42,55,66],"extract":[43,56,67,98],"from":[44,58,69,100],"forums.":[47],"Aimed":[48],"at":[49],"limitation":[51],"current":[53],"methods":[54],"forums,":[60],"an":[61],"automated":[62],"method":[63,74,124],"is":[64],"proposed":[65],"metadata":[68,99],"forum":[71,95],"pages.":[72],"The":[73],"processes":[75],"two":[77],"steps.":[78],"We":[79],"firstly":[80],"recognizes":[81],"topic-block":[83,102],"by":[84,103],"making":[85,104],"full":[86],"use":[87,105],"special":[90],"layout":[91],"pages,":[96],"then":[97],"statistical":[107],"regularity":[108],"metadata,":[111],"whole":[113],"process":[114],"done":[115],"without":[116],"manual":[117],"work.":[118],"Experimental":[119],"results":[120],"show":[121],"that":[122],"this":[123],"performs":[125],"well":[126],"both":[127],"adjustability":[129],"accuracy.":[131]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
