{"id":"https://openalex.org/W4410447993","doi":"https://doi.org/10.3233/shti250423","title":"Building a Modular Health Information Crawler: Leveraging Apache Nutch for the Tala-Med Search Engine","display_name":"Building a Modular Health Information Crawler: Leveraging Apache Nutch for the Tala-Med Search Engine","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410447993","doi":"https://doi.org/10.3233/shti250423","pmid":"https://pubmed.ncbi.nlm.nih.gov/40380532"},"language":"en","primary_location":{"id":"doi:10.3233/shti250423","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250423","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250423","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250423","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117573341","display_name":"Nanxing Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nanxing Deng","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039035898","display_name":"Martin Boeker","orcid":"https://orcid.org/0000-0003-2972-2042"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Boeker","raw_affiliation_strings":["Institute for AI and Informatics in Medicine (AIIM), TUM University Medical Center, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI and Informatics in Medicine (AIIM), TUM University Medical Center, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029151960","display_name":"Raphael Scheible","orcid":"https://orcid.org/0000-0003-2067-5569"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raphael Scheible","raw_affiliation_strings":["Institute for AI and Informatics in Medicine (AIIM), TUM University Medical Center, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI and Informatics in Medicine (AIIM), TUM University Medical Center, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.180848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"327","issue":null,"first_page":"622","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7391999959945679,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7391999959945679,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9133142232894897},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5972037315368652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5677587389945984},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4300384223461151},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28099197149276733}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9133142232894897},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5972037315368652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5677587389945984},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4300384223461151},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28099197149276733}],"mesh":[{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250423","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250423","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250423","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40380532","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40380532","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":"Studies in health technology and informatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti250423","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250423","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250423","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410447993.pdf","grobid_xml":"https://content.openalex.org/works/W4410447993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2152505903","https://openalex.org/W2054759010","https://openalex.org/W3202833648","https://openalex.org/W2066301148","https://openalex.org/W2626977282","https://openalex.org/W2566625334","https://openalex.org/W2733224566","https://openalex.org/W3182846679","https://openalex.org/W2081888991"],"abstract_inverted_index":{"Developed":[0],"in":[1],"2020,":[2],"the":[3,29,35,82,100,107,123,140],"tala-med":[4],"search":[5,77,129],"engine":[6],"provides":[7],"high-quality,":[8],"evidence-based":[9],"health":[10],"information":[11],"from":[12],"trustworthy":[13],"German":[14],"websites":[15,113],"while":[16],"ensuring":[17],"user":[18],"privacy.":[19],"However,":[20],"it":[21],"still":[22],"leaves":[23],"room":[24],"for":[25,51,67,70,76,131],"technical":[26],"improvements.":[27],"In":[28],"present":[30],"work,":[31],"we":[32],"are":[33],"replacing":[34],"Fess":[36],"crawler":[37,124],"with":[38,84],"Apache":[39],"Nutch":[40,47,69],"to":[41,62,98],"improve":[42],"scalability":[43],"and":[44,55,72,74,126],"customization,":[45],"as":[46],"offers":[48],"greater":[49],"flexibility":[50],"large-scale":[52],"web":[53],"crawling":[54,71],"indexing.":[56],"The":[57,91],"new":[58],"system":[59],"uses":[60],"Docker":[61],"integrate":[63],"five":[64],"services:":[65],"PostgreSQL":[66],"configurations,":[68],"indexing,":[73],"ElasticSearch":[75],"operations;":[78],"a":[79,128],"Manager":[80],"orchestrates":[81],"process":[83],"custom":[85],"configurations":[86],"via":[87],"extended":[88],"Nutch-REST":[89],"interface.":[90],"configuration":[92],"options":[93],"include":[94],"domain-specific":[95],"URL":[96],"filters":[97],"select":[99],"crawled":[101],"content.":[102],"A":[103],"test":[104],"crawl":[105],"demonstrated":[106],"system's":[108],"effectiveness,":[109],"processing":[110],"approximately":[111],"23k":[112],"over":[114],"65":[115],"hours.":[116],"Future":[117],"work":[118],"will":[119],"focus":[120],"on":[121],"deploying":[122],"long-term":[125],"generating":[127],"index":[130],"further":[132],"analysis.":[133],"We":[134],"have":[135],"published":[136],"our":[137],"code":[138],"under":[139],"MIT":[141],"license":[142],"at":[143],"https://gitlab.com/mri-tum/aiim/search-platform/crawler.":[144]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
