{"id":"https://openalex.org/W2142496162","doi":"https://doi.org/10.1109/snpd.2015.7176203","title":"Extracting news content with visual unit of web pages","display_name":"Extracting news content with visual unit of web pages","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W2142496162","doi":"https://doi.org/10.1109/snpd.2015.7176203","mag":"2142496162"},"language":"en","primary_location":{"id":"doi:10.1109/snpd.2015.7176203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2015.7176203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","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/A5036943629","display_name":"Wenhao Zhu","orcid":"https://orcid.org/0000-0002-9656-9781"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhao Zhu","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China","School of Computer Engineering and Science, Shanghai University Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]},{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027538261","display_name":"Song Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Dai","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China","School of Computer Engineering and Science, Shanghai University Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]},{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054294068","display_name":"Yang Song","orcid":"https://orcid.org/0000-0002-1310-7320"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China","School of Computer Engineering and Science, Shanghai University Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]},{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079647326","display_name":"Zhiguo Lu","orcid":"https://orcid.org/0000-0002-9044-2819"},"institutions":[{"id":"https://openalex.org/I2801919588","display_name":"Shanghai Library","ror":"https://ror.org/022d5rd48","country_code":"CN","type":"archive","lineage":["https://openalex.org/I2801919588"]},{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguo Lu","raw_affiliation_strings":["Library of Shanghai University, Shanghai, China","[Library of Shanghai University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Library of Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I2801919588","https://openalex.org/I113940042"]},{"raw_affiliation_string":"[Library of Shanghai University, Shanghai, China]","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036943629"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8115662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"5","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9679999947547913,"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/document-object-model","display_name":"Document Object Model","score":0.8508720397949219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8201602101325989},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.709649920463562},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6698045134544373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6158818602561951},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5950360298156738},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.524701714515686},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4321785271167755},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4240148365497589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35503077507019043},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34099894762039185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09529852867126465}],"concepts":[{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.8508720397949219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201602101325989},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.709649920463562},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6698045134544373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6158818602561951},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5950360298156738},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.524701714515686},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4321785271167755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4240148365497589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35503077507019043},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34099894762039185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09529852867126465},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snpd.2015.7176203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2015.7176203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1553019137","https://openalex.org/W1566513354","https://openalex.org/W1748877974","https://openalex.org/W1803802947","https://openalex.org/W1991565788","https://openalex.org/W2031517079","https://openalex.org/W2067367118","https://openalex.org/W2102694093","https://openalex.org/W2126226592","https://openalex.org/W2129428889","https://openalex.org/W2129595335","https://openalex.org/W2131240202","https://openalex.org/W2152056009","https://openalex.org/W2158051716","https://openalex.org/W2186770990","https://openalex.org/W2328581567","https://openalex.org/W2393035056","https://openalex.org/W2913389685"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2076910790","https://openalex.org/W2155199173","https://openalex.org/W2275993472","https://openalex.org/W2998827288","https://openalex.org/W1544491176","https://openalex.org/W2185387300"],"abstract_inverted_index":{"The":[0,136],"Document":[1],"Object":[2],"Model":[3],"(DOM)":[4],"provides":[5],"a":[6,48,66,78,98,143],"tree":[7,11,27,56,71],"structure":[8],"called":[9],"DOM":[10,26,55,70],"for":[12,91,146],"representing":[13],"with":[14,150],"objects":[15,30],"in":[16,31],"HTML.":[17],"Many":[18],"researchers":[19],"have":[20,47,65],"considered":[21],"using":[22],"leaf":[23],"nodes":[24],"of":[25,42],"as":[28],"basic":[29],"extracting":[32],"information":[33,43,60],"from":[34,131],"web":[35,38,129],"pages.":[36],"However,":[37],"pages":[39,130],"are":[40,95],"more":[41],"blocks":[44,61],"which":[45],"each":[46],"consistent":[49],"visual":[50,79,88,103,151],"format":[51],"rather":[52],"than":[53],"individual":[54],"nodes.":[57,72],"And":[58],"those":[59],"do":[62],"not":[63],"necessarily":[64],"direct":[67],"map":[68],"to":[69,115],"In":[73,118],"this":[74],"paper,":[75],"we":[76],"propose":[77],"oriented":[80],"extraction":[81,149],"method":[82,141],"that":[83,139],"extracts":[84],"news":[85,128,134,147],"content":[86,111,148],"by":[87,97],"unit":[89],"(vu,":[90],"short).":[92],"Visual":[93],"units":[94,152],"identified":[96],"top-down":[99],"approach":[100,122,145],"based":[101],"on":[102],"features":[104],"and":[105,153],"text":[106],"features.":[107],"After":[108],"that,":[109],"page":[110],"is":[112],"extracted":[113],"according":[114],"domain":[116,154],"characteristic.":[117,155],"experiments,":[119],"the":[120],"proposed":[121],"achieves":[123],"94.86%":[124],"accuracy":[125],"over":[126],"700":[127],"7":[132],"different":[133],"sites.":[135],"result":[137],"demonstrates":[138],"our":[140],"represents":[142],"promising":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
