{"id":"https://openalex.org/W4285416269","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534308","title":"Boilerplate Detection via Semantic Classification of TextBlocks","display_name":"Boilerplate Detection via Semantic Classification of TextBlocks","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W4285416269","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534308"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074042008","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-5549-2300"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["University of Massachusetts,Department of Computer Science,Lowell,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Department of Computer Science,Lowell,USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440079","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-3772-426X"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["University of Massachusetts,Department of Computer Science,Lowell,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Department of Computer Science,Lowell,USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9991000294685364,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/boilerplate-text","display_name":"Boilerplate text","score":0.8307644128799438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995447516441345},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5427517890930176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4818614423274994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4773856997489929},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4371544122695923},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4232638478279114},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4174846112728119},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33087944984436035},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.251728355884552}],"concepts":[{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.8307644128799438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995447516441345},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5427517890930176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4818614423274994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4773856997489929},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4371544122695923},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4232638478279114},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4174846112728119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33087944984436035},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.251728355884552},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W116870935","https://openalex.org/W1706374111","https://openalex.org/W1803802947","https://openalex.org/W1832693441","https://openalex.org/W1942083547","https://openalex.org/W2019577381","https://openalex.org/W2049488566","https://openalex.org/W2064675550","https://openalex.org/W2072489225","https://openalex.org/W2084358158","https://openalex.org/W2120101509","https://openalex.org/W2143612262","https://openalex.org/W2155364607","https://openalex.org/W2158051716","https://openalex.org/W2167859982","https://openalex.org/W2190474242","https://openalex.org/W2295318420","https://openalex.org/W2493916176","https://openalex.org/W2964079897","https://openalex.org/W3021347373","https://openalex.org/W3102354094","https://openalex.org/W4240344917","https://openalex.org/W6600000387","https://openalex.org/W6604697442","https://openalex.org/W6683035398"],"related_works":["https://openalex.org/W3121258117","https://openalex.org/W4379160565","https://openalex.org/W2146642953","https://openalex.org/W2507103705","https://openalex.org/W4210431233","https://openalex.org/W50124057","https://openalex.org/W2999218465","https://openalex.org/W4288026874","https://openalex.org/W2989347554","https://openalex.org/W3010940303"],"abstract_inverted_index":{"We":[0,22,46,57],"present":[1],"a":[2,15,36],"hierarchical":[3],"neural":[4],"network":[5],"model":[6],"called":[7],"SemText":[8,24,49,63],"to":[9],"detect":[10],"HTML":[11],"boilerplate":[12,70],"based":[13],"on":[14,25,54,72],"novel":[16],"semantic":[17],"representation":[18],"of":[19,29,39,62],"text":[20],"blocks.":[21],"train":[23],"three":[26],"published":[27],"datasets":[28],"news":[30],"webpages":[31],"and":[32,44],"fine-tune":[33],"it":[34,67],"using":[35],"small":[37],"number":[38],"development":[40],"data":[41],"in":[42],"CleanEval":[43],"GoogleTrends-2017.":[45],"show":[47],"that":[48,66],"achieves":[50],"the":[51,60],"state-of-the-art":[52],"accuracy":[53],"these":[55],"datasets.":[56],"then":[58],"demonstrate":[59],"robustness":[61],"by":[64],"showing":[65],"also":[68],"detects":[69],"effectively":[71],"out-of-domain":[73],"community-based":[74],"Q&A":[75],"webpages.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
