{"id":"https://openalex.org/W4400113939","doi":"https://doi.org/10.1109/mipro60963.2024.10569560","title":"Data Enrichment Pipeline Model for Web Classification Based on Web Scraping and Machine Learning","display_name":"Data Enrichment Pipeline Model for Web Classification Based on Web Scraping and Machine Learning","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4400113939","doi":"https://doi.org/10.1109/mipro60963.2024.10569560"},"language":"en","primary_location":{"id":"doi:10.1109/mipro60963.2024.10569560","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mipro60963.2024.10569560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th MIPRO ICT and Electronics Convention (MIPRO)","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/A5114183799","display_name":"Evegeniya Samsonova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102288","display_name":"Algebra University College","ror":"https://ror.org/019m6wk21","country_code":"HR","type":"education","lineage":["https://openalex.org/I4210102288"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"Evegeniya Samsonova","raw_affiliation_strings":["Algebra University,Zagreb,Croatia"],"affiliations":[{"raw_affiliation_string":"Algebra University,Zagreb,Croatia","institution_ids":["https://openalex.org/I4210102288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039555031","display_name":"Zlatan Mori\u0107","orcid":"https://orcid.org/0000-0002-5566-1581"},"institutions":[{"id":"https://openalex.org/I4210102288","display_name":"Algebra University College","ror":"https://ror.org/019m6wk21","country_code":"HR","type":"education","lineage":["https://openalex.org/I4210102288"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Zlatan Mori\u0107","raw_affiliation_strings":["Algebra University,Zagreb,Croatia"],"affiliations":[{"raw_affiliation_string":"Algebra University,Zagreb,Croatia","institution_ids":["https://openalex.org/I4210102288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015628945","display_name":"Goran Gvozden","orcid":"https://orcid.org/0000-0002-0242-4865"},"institutions":[{"id":"https://openalex.org/I4210102288","display_name":"Algebra University College","ror":"https://ror.org/019m6wk21","country_code":"HR","type":"education","lineage":["https://openalex.org/I4210102288"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Goran Gvozden","raw_affiliation_strings":["Algebra University,Zagreb,Croatia"],"affiliations":[{"raw_affiliation_string":"Algebra University,Zagreb,Croatia","institution_ids":["https://openalex.org/I4210102288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006615424","display_name":"Tomislav Hlupi\u0107","orcid":"https://orcid.org/0000-0003-0814-8774"},"institutions":[{"id":"https://openalex.org/I4210102288","display_name":"Algebra University College","ror":"https://ror.org/019m6wk21","country_code":"HR","type":"education","lineage":["https://openalex.org/I4210102288"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Tomislav Hlupi\u0107","raw_affiliation_strings":["Algebra University,Zagreb,Croatia"],"affiliations":[{"raw_affiliation_string":"Algebra University,Zagreb,Croatia","institution_ids":["https://openalex.org/I4210102288"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114183799"],"corresponding_institution_ids":["https://openalex.org/I4210102288"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07494309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9919000267982483,"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":0.8429676294326782},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7093040943145752},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4702075123786926},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42985448241233826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36145302653312683},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35802704095840454},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28465795516967773},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09039714932441711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429676294326782},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7093040943145752},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4702075123786926},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42985448241233826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36145302653312683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35802704095840454},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28465795516967773},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09039714932441711}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mipro60963.2024.10569560","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mipro60963.2024.10569560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th MIPRO ICT and Electronics Convention (MIPRO)","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":8,"referenced_works":["https://openalex.org/W2112335400","https://openalex.org/W2185978036","https://openalex.org/W2322938983","https://openalex.org/W2888377168","https://openalex.org/W2889866783","https://openalex.org/W3190429087","https://openalex.org/W6676918204","https://openalex.org/W6759325025"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W4400978025","https://openalex.org/W2918743509","https://openalex.org/W2734796617","https://openalex.org/W3083218341"],"abstract_inverted_index":{"With":[0],"the":[1,64,102],"digitization":[2],"of":[3,8,66,78],"sales":[4],"and":[5,11,22,46,55,80,96,99,114],"marketing,":[6],"growth":[7],"online":[9],"platforms,":[10],"e-commerce,":[12],"businesses":[13],"are":[14],"now":[15,42],"able":[16],"to":[17,112],"operate":[18],"globally":[19],"with":[20],"ease":[21,77],"fewer":[23],"restrictions.":[24],"Expanding":[25],"customer":[26],"reach":[27],"also":[28],"means":[29],"handling":[30],"larger":[31],"data":[32,44,85],"volumes,":[33],"which":[34],"is":[35],"often":[36],"addressed":[37],"through":[38],"automation.":[39],"Many":[40],"companies":[41],"utilize":[43],"pipelines":[45],"advanced":[47],"AI":[48],"systems":[49],"for":[50,72,90,109],"analytics,":[51],"operational":[52],"optimization,":[53],"faster":[54],"improved":[56],"decision-making.":[57],"This":[58],"paper":[59],"will":[60],"explain":[61],"in":[62],"details":[63],"creation":[65],"an":[67,97],"automated":[68],"lead":[69],"enrichment":[70],"pipeline":[71],"B2B":[73],"that":[74],"focuses":[75],"on":[76],"implementation":[79],"deployment.":[81],"Employing":[82],"a":[83,93,105],"web":[84],"extraction":[86],"tool,":[87,101],"machine":[88],"learning":[89],"website":[91],"classification,":[92],"cloud-based":[94],"database,":[95],"automation":[98],"orchestration":[100],"software":[103],"provides":[104],"readily":[106],"implementable":[107],"solution":[108],"smaller":[110],"enterprises":[111],"build":[113],"deploy.":[115]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
