{"id":"https://openalex.org/W2167277496","doi":"https://doi.org/10.1145/1286240.1286257","title":"Visual features in genre classification of html","display_name":"Visual features in genre classification of html","publication_year":2007,"publication_date":"2007-09-10","ids":{"openalex":"https://openalex.org/W2167277496","doi":"https://doi.org/10.1145/1286240.1286257","mag":"2167277496"},"language":"en","primary_location":{"id":"doi:10.1145/1286240.1286257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1286240.1286257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighteenth conference on Hypertext and hypermedia","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/A5084833276","display_name":"Ryan Levering","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Levering","raw_affiliation_strings":["SUNY at Binghamton, Binghamton, NY"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015386539","display_name":"Michal Cutler","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Cutler","raw_affiliation_strings":["SUNY at Binghamton, Binghamton, NY"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100736933","display_name":"Yu Lei","orcid":"https://orcid.org/0000-0001-8482-3140"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":["SUNY at Binghamton, Binghamton, NY"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084833276"],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14799862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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":0.9984999895095825,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.996999979019165,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9944000244140625,"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":0.8228572607040405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5914538502693176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5689112544059753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5362099409103394},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5118814706802368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5094888806343079},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4152403771877289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228572607040405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5914538502693176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5689112544059753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362099409103394},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5118814706802368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5094888806343079},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4152403771877289},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1286240.1286257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1286240.1286257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighteenth conference on Hypertext and hypermedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.545.2869","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.545.2869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://webseer.sourceforge.net/papers/ht07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W577469600","https://openalex.org/W2121871415","https://openalex.org/W2132480243","https://openalex.org/W2137595860","https://openalex.org/W2163534337","https://openalex.org/W4300874750","https://openalex.org/W4403159200"],"related_works":["https://openalex.org/W4389443772","https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W4213212078","https://openalex.org/W4238809000","https://openalex.org/W2786646446","https://openalex.org/W2312871963","https://openalex.org/W2013265273","https://openalex.org/W2331739042","https://openalex.org/W2390930322"],"abstract_inverted_index":{"Automatic":[0],"genre":[1,40],"classification":[2,26,41,77],"historically":[3],"has":[4],"focused":[5],"on":[6,38],"extracting":[7],"textual":[8,51,79],"features":[9,19,35,56,73,80],"from":[10],"documents.":[11],"In":[12],"this":[13],"research,":[14],"we":[15],"investigate":[16],"whether":[17],"visual":[18,63,72],"of":[20,27,34],"HTML":[21,55,70],"documents":[22],"can":[23],"improve":[24],"the":[25,44],"fine":[28],"grained":[29],"genres.":[30],"Three":[31],"different":[32],"sets":[33],"were":[36],"compared":[37],"a":[39,59],"task":[42],"in":[43],"e-commerce":[45],"domain":[46],"-":[47],"one":[48,53],"with":[49,54,61],"just":[50],"features,":[52],"added,":[57],"and":[58,71],"third":[60],"additional":[62],"features.":[64],"Our":[65],"experiments":[66],"show":[67],"that":[68],"adding":[69],"provides":[74],"much":[75],"better":[76],"than":[78],"alone.":[81]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
