{"id":"https://openalex.org/W4386937931","doi":"https://doi.org/10.1007/978-3-031-41774-0_24","title":"Evaluating Web Crawlers with\u00a0Machine Learning Algorithms for\u00a0Accurate Location Extraction from\u00a0Job Offers","display_name":"Evaluating Web Crawlers with\u00a0Machine Learning Algorithms for\u00a0Accurate Location Extraction from\u00a0Job Offers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386937931","doi":"https://doi.org/10.1007/978-3-031-41774-0_24"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-41774-0_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-41774-0_24","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5077565916","display_name":"Pawe\u0142 Drozda","orcid":"https://orcid.org/0000-0003-3163-9408"},"institutions":[{"id":"https://openalex.org/I47996466","display_name":"University of Warmia and Mazury in Olsztyn","ror":"https://ror.org/05s4feg49","country_code":"PL","type":"education","lineage":["https://openalex.org/I47996466"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Pawe\u0142 Drozda","raw_affiliation_strings":["Emplocity S.A., Warsaw, Poland","Faculty Mathematics and Computer Science, University of Warmia and Mazury, Olsztyn, Poland"],"affiliations":[{"raw_affiliation_string":"Emplocity S.A., Warsaw, Poland","institution_ids":[]},{"raw_affiliation_string":"Faculty Mathematics and Computer Science, University of Warmia and Mazury, Olsztyn, Poland","institution_ids":["https://openalex.org/I47996466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103191019","display_name":"Bartosz A. Nowak","orcid":"https://orcid.org/0000-0002-2577-4470"},"institutions":[{"id":"https://openalex.org/I47996466","display_name":"University of Warmia and Mazury in Olsztyn","ror":"https://ror.org/05s4feg49","country_code":"PL","type":"education","lineage":["https://openalex.org/I47996466"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartosz A. Nowak","raw_affiliation_strings":["Emplocity S.A., Warsaw, Poland","Faculty Mathematics and Computer Science, University of Warmia and Mazury, Olsztyn, Poland"],"affiliations":[{"raw_affiliation_string":"Emplocity S.A., Warsaw, Poland","institution_ids":[]},{"raw_affiliation_string":"Faculty Mathematics and Computer Science, University of Warmia and Mazury, Olsztyn, Poland","institution_ids":["https://openalex.org/I47996466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033454791","display_name":"Arkadiusz Talun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arkadiusz Talun","raw_affiliation_strings":["Emplocity S.A., Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Emplocity S.A., Warsaw, Poland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091418953","display_name":"Leszek Bukowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leszek Bukowski","raw_affiliation_strings":["Emplocity S.A., Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Emplocity S.A., Warsaw, Poland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077565916"],"corresponding_institution_ids":["https://openalex.org/I47996466"],"apc_list":null,"apc_paid":null,"fwci":0.754,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74432769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.9980000257492065,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7484708428382874},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6809055805206299},{"id":"https://openalex.org/keywords/listing","display_name":"Listing (finance)","score":0.635028600692749},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.62126624584198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458233952522278},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5362085700035095},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5235069394111633},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43406206369400024},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42337167263031006},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4223434031009674},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.41804251074790955},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.41296613216400146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33926624059677124},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1639673113822937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484708428382874},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6809055805206299},{"id":"https://openalex.org/C2779820595","wikidata":"https://www.wikidata.org/wiki/Q798505","display_name":"Listing (finance)","level":2,"score":0.635028600692749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.62126624584198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458233952522278},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5362085700035095},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5235069394111633},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43406206369400024},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42337167263031006},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4223434031009674},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.41804251074790955},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.41296613216400146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33926624059677124},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1639673113822937},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-41774-0_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-41774-0_24","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W184286324","https://openalex.org/W1930624869","https://openalex.org/W2067885219","https://openalex.org/W2147833714","https://openalex.org/W2217032200","https://openalex.org/W2295598076","https://openalex.org/W2397079304","https://openalex.org/W2554912333","https://openalex.org/W2778981424","https://openalex.org/W2807873899","https://openalex.org/W3087552146","https://openalex.org/W3094387562","https://openalex.org/W3102944478","https://openalex.org/W4200146754","https://openalex.org/W4205814217","https://openalex.org/W4212883601","https://openalex.org/W4235051704","https://openalex.org/W4236137412","https://openalex.org/W4239510810","https://openalex.org/W4250546562","https://openalex.org/W4251780656","https://openalex.org/W4304098281","https://openalex.org/W4312431595"],"related_works":["https://openalex.org/W293204540","https://openalex.org/W3024364549","https://openalex.org/W4360847453","https://openalex.org/W4386259002","https://openalex.org/W4206019083","https://openalex.org/W1976265003","https://openalex.org/W2795534283","https://openalex.org/W2054476758","https://openalex.org/W1554695299","https://openalex.org/W4385192698"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
