{"id":"https://openalex.org/W2284522302","doi":null,"title":"Cleaning Web Pages for Relevant Text Extraction and Text Categorization","display_name":"Cleaning Web Pages for Relevant Text Extraction and Text Categorization","publication_year":2013,"publication_date":"2013-01-30","ids":{"openalex":"https://openalex.org/W2284522302","mag":"2284522302"},"language":"en","primary_location":{"id":"mag:2284522302","doi":null,"is_oa":false,"landing_page_url":"https://www.ijert.org/research/cleaning-web-pages-for-relevant-text-extraction-and-text-categorization-IJERTV2IS1330.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Engineering Research and","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Amit Chauhan","orcid":"https://orcid.org/0000-0001-6508-2156","observed_orcids":["https://orcid.org/0000-0001-6508-2156"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Chauhan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6508-2156","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083032032","display_name":"Himanshu Uniyal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himanshu Uniyal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005317548","display_name":"Bhasker Pant","orcid":"https://orcid.org/0000-0002-6070-5104","observed_orcids":["https://orcid.org/0000-0002-6070-5104"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhasker Pant","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6070-5104","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6188,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76209165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9789999723434448,"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":0.9789999723434448,"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":0.016899999231100082,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0010999999940395355,"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/text-extraction","display_name":"text extraction","score":0.9409999847412109},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7729858160018921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262413501739502},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6581705808639526},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5527849197387695},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4827639162540436},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43097180128097534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33478844165802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25609639286994934}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2284522302","doi":null,"is_oa":false,"landing_page_url":"https://www.ijert.org/research/cleaning-web-pages-for-relevant-text-extraction-and-text-categorization-IJERTV2IS1330.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Engineering Research and","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W180238871","https://openalex.org/W1943553835","https://openalex.org/W1989338554","https://openalex.org/W2019264297","https://openalex.org/W2040075907","https://openalex.org/W2149684865","https://openalex.org/W2167859982"],"related_works":["https://openalex.org/W7136060856","https://openalex.org/W2184356805","https://openalex.org/W3209840194","https://openalex.org/W6884994139","https://openalex.org/W2898765162","https://openalex.org/W7095163355","https://openalex.org/W2189277793","https://openalex.org/W158294556","https://openalex.org/W7095436851","https://openalex.org/W2920358471"],"abstract_inverted_index":null,"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2016-06-24T00:00:00"}
