{"id":"https://openalex.org/W4415958028","doi":"https://doi.org/10.3389/frai.2025.1606431","title":"A review of AI-based business lead generation: Scrapus as a case study","display_name":"A review of AI-based business lead generation: Scrapus as a case study","publication_year":2025,"publication_date":"2025-11-06","ids":{"openalex":"https://openalex.org/W4415958028","doi":"https://doi.org/10.3389/frai.2025.1606431","pmid":"https://pubmed.ncbi.nlm.nih.gov/41312025"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2025.1606431","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1606431","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1606431/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1606431/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120279629","display_name":"Ahmet Kaplan","orcid":null},"institutions":[{"id":"https://openalex.org/I3125470973","display_name":"Istanbul Medipol University","ror":"https://ror.org/037jwzz50","country_code":"TR","type":"education","lineage":["https://openalex.org/I3125470973"]},{"id":"https://openalex.org/I4210101260","display_name":"T\u00fcrkisch-Deutsche Universit\u00e4t","ror":"https://ror.org/017bbc354","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210101260"]},{"id":"https://openalex.org/I53210213","display_name":"Istanbul Commerce University","ror":"https://ror.org/02v3kkq53","country_code":"TR","type":"education","lineage":["https://openalex.org/I53210213"]},{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ahmet Kaplan","raw_affiliation_strings":["Department of AI Engineering, Istanbul Medipol University, Istanbul, T\u00fcrkiye","Department of Computer Engineering, Istanbul University, Istanbul, T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI Engineering, Istanbul Medipol University, Istanbul, T\u00fcrkiye","institution_ids":["https://openalex.org/I3125470973"]},{"raw_affiliation_string":"Department of Computer Engineering, Istanbul University, Istanbul, T\u00fcrkiye","institution_ids":["https://openalex.org/I4210101260","https://openalex.org/I53210213","https://openalex.org/I67581229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058858156","display_name":"\u015eadi Evren \u015eeker","orcid":"https://orcid.org/0000-0002-7323-3695"},"institutions":[{"id":"https://openalex.org/I4210101260","display_name":"T\u00fcrkisch-Deutsche Universit\u00e4t","ror":"https://ror.org/017bbc354","country_code":"TR","type":"education","lineage":["https://openalex.org/I4210101260"]},{"id":"https://openalex.org/I53210213","display_name":"Istanbul Commerce University","ror":"https://ror.org/02v3kkq53","country_code":"TR","type":"education","lineage":["https://openalex.org/I53210213"]},{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Sadi Evren Seker","raw_affiliation_strings":["Department of Computer Engineering, Istanbul University, Istanbul, T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Istanbul University, Istanbul, T\u00fcrkiye","institution_ids":["https://openalex.org/I4210101260","https://openalex.org/I53210213","https://openalex.org/I67581229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120279630","display_name":"Rabia Yoruk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115558","display_name":"Wisdom Health (United States)","ror":"https://ror.org/02538qk16","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113968","https://openalex.org/I4210115558"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rabia Yoruk","raw_affiliation_strings":["OptiWisdom Inc, San Francisco, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OptiWisdom Inc, San Francisco, CA, United States","institution_ids":["https://openalex.org/I4210115558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120279629"],"corresponding_institution_ids":["https://openalex.org/I3125470973","https://openalex.org/I4210101260","https://openalex.org/I53210213","https://openalex.org/I67581229"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":3.5072,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94104661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"1606431","last_page":"1606431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.2493000030517578,"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":0.2493000030517578,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.09049999713897705,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.774399995803833},{"id":"https://openalex.org/keywords/lead","display_name":"Lead (geology)","score":0.5666999816894531},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4593000113964081},{"id":"https://openalex.org/keywords/mashup","display_name":"Mashup","score":0.4408000111579895},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4287000000476837},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4101000130176544},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.39410001039505005},{"id":"https://openalex.org/keywords/web-engineering","display_name":"Web engineering","score":0.37369999289512634}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.774399995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6855999827384949},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4973999857902527},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.4408000111579895},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.39410001039505005},{"id":"https://openalex.org/C97200028","wikidata":"https://www.wikidata.org/wiki/Q1196135","display_name":"Web engineering","level":5,"score":0.37369999289512634},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.3093000054359436},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C59241245","wikidata":"https://www.wikidata.org/wiki/Q4781497","display_name":"Web application security","level":4,"score":0.2816999852657318},{"id":"https://openalex.org/C2781468064","wikidata":"https://www.wikidata.org/wiki/Q1267117","display_name":"Lead time","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/frai.2025.1606431","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1606431","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1606431/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:41312025","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41312025","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:e6310807e5c640c69fd409694c98d0ba","is_oa":true,"landing_page_url":"https://doaj.org/article/e6310807e5c640c69fd409694c98d0ba","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 8 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2025.1606431","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1606431","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1606431/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415958028.pdf","grobid_xml":"https://content.openalex.org/works/W4415958028.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1114177902","https://openalex.org/W1489992655","https://openalex.org/W1552847225","https://openalex.org/W1880262756","https://openalex.org/W1964378344","https://openalex.org/W2022166150","https://openalex.org/W2073471108","https://openalex.org/W2080133951","https://openalex.org/W2120101509","https://openalex.org/W2127978399","https://openalex.org/W2145339207","https://openalex.org/W2147953360","https://openalex.org/W2151007976","https://openalex.org/W2592752392","https://openalex.org/W2783479218","https://openalex.org/W2798649495","https://openalex.org/W2911388033","https://openalex.org/W2913389685","https://openalex.org/W3027323858","https://openalex.org/W3027937825","https://openalex.org/W3120275071","https://openalex.org/W3155638005","https://openalex.org/W3195577433","https://openalex.org/W3207425841","https://openalex.org/W3208109776","https://openalex.org/W4226278401","https://openalex.org/W4231080135","https://openalex.org/W4242744113","https://openalex.org/W4288028050","https://openalex.org/W4292779060","https://openalex.org/W4297792667","https://openalex.org/W4318769934","https://openalex.org/W4360620450","https://openalex.org/W4385245566","https://openalex.org/W4385844420","https://openalex.org/W4386450904","https://openalex.org/W4386693657","https://openalex.org/W4396553888","https://openalex.org/W4408238802","https://openalex.org/W4408838347","https://openalex.org/W4415473808"],"related_works":[],"abstract_inverted_index":{"The":[0,136,181,240],"exponential":[1],"growth":[2],"of":[3,21,35,49,249],"open":[4,78],"web":[5,26,36,63,79,117,192],"data":[6,87],"provides":[7],"unprecedented":[8],"opportunities":[9],"for":[10,54,80],"business-to-business":[11],"(B2B)":[12],"lead":[13,56,106,166,171,189,214,238],"generation.":[14,239],"However,":[15],"automating":[16],"the":[17,33,77],"discovery":[18,167],"and":[19,40,58,84,92,102,123,132,140,176,178,211,221,231,263],"qualification":[20,172],"new":[22,247],"leads":[23,265],"from":[24,191],"unstructured":[25],"content":[27],"is":[28],"a":[29,46,184,198,246],"complex":[30],"challenge":[31],"requiring":[32],"integration":[34],"crawling,":[37,120],"information":[38],"extraction,":[39],"data-driven":[41],"analytics.":[42],"This":[43,219],"article":[44],"presents":[45],"comprehensive":[47],"review":[48,220],"artificial":[50],"intelligence":[51],"(AI)":[52],"methods":[53,69],"automated":[55],"generation":[57,248],"introduces":[59],"Scrapus,":[60],"an":[61,71,154],"AI-driven":[62],"prospecting":[64,252],"platform":[65],"that":[66,225],"unifies":[67],"these":[68],"into":[70],"end-to-end":[72],"system.":[73],"Scrapus":[74,129,160],"autonomously":[75],"crawls":[76],"company":[81],"information,":[82],"extracts":[83],"enriches":[85],"relevant":[86,114,188],"(using":[88],"natural":[89],"language":[90,110],"processing":[91],"knowledge":[93],"graphs),":[94],"matches":[95],"findings":[96],"to":[97,195,206,261],"user-defined":[98],"ideal":[99],"customer":[100],"profiles,":[101],"generates":[103],"concise":[104],"natural-language":[105],"summaries":[107],"using":[108],"large":[109],"models.":[111],"We":[112,151],"survey":[113],"literature":[115],"in":[116,145,165,201,254],"mining,":[118],"focused":[119],"entity":[121],"resolution,":[122],"text":[124],"summarization":[125],"-":[126],"highlighting":[127],"how":[128],"builds":[130],"upon":[131],"extends":[133],"prior":[134],"work.":[135],"system's":[137],"modular":[138],"architecture":[139],"AI":[141,256],"components":[142],"are":[143],"described":[144],"detail,":[146],"reflecting":[147],"accurate":[148],"implementation":[149],"details.":[150],"also":[152],"report":[153],"experimental":[155],"evaluation":[156],"on":[157],"real-world":[158],"data:":[159],"significantly":[161],"outperforms":[162],"baseline":[163],"approaches":[164],"rate,":[168],"extraction":[169,202],"accuracy,":[170],"(achieving":[173],"~90%":[174],"precision":[175],"recall),":[177],"summary":[179],"usefulness.":[180],"results":[182],"show":[183],"~3":[185],"\u00d7":[186],"higher":[187],"yield":[190],"crawling":[193],"due":[194],"reinforcement":[196,227],"learning,":[197,228],"substantial":[199],"increase":[200],"F1":[203],"(from":[204],"~0.77":[205],"~0.92)":[207],"through":[208],"transformer-based":[209,229],"NLP,":[210,230],"greatly":[212],"improved":[213],"scoring":[215],"over":[216],"traditional":[217],"methods.":[218],"case":[222],"study":[223],"demonstrate":[224],"combining":[226],"knowledge-enhanced":[232],"analysis":[233],"can":[234],"effectively":[235],"automate":[236],"B2B":[237],"advances":[241],"surveyed":[242],"here":[243],"point":[244],"toward":[245],"intelligent":[250],"sales":[251],"tools,":[253],"which":[255],"techniques":[257],"augment":[258],"human":[259],"expertise":[260],"identify":[262],"engage":[264],"at":[266],"scale.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-06T00:00:00"}