Skip to content

Commit

Permalink
Closes #1495: Recalibrate affiliation matching confidence level for c…
Browse files Browse the repository at this point in the history 
…ases without affiliation country code specified

First recalibration round after introducing the first group of false positives.
  • Loading branch information
@marekhorst
marekhorst committed Dec 20, 2024
1 parent bb41b24 commit ae2f12c
Show file tree
Hide file tree
Showing 4 changed files with 24 additions and 7 deletions.
6 changes: 3 additions & 3 deletions ...src/main/java/eu/dnetlib/iis/wf/affmatching/match/FirstWordsHashBucketMatcherFactory.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -79,9 +79,9 @@ public static ImmutableList<AffOrgMatchVoter> createNameFirstWordsHashBucketMatc
return ImmutableList.of(
createNameCountryStrictMatchVoter(0.981f, new GetOrgNameFunction()),
createNameStrictCountryLooseMatchVoter(0.966f, new GetOrgNameFunction()),
createSectionedNameStrictCountryLooseMatchVoter(0.917f, new GetOrgNameFunction()),
createSectionedNameLevenshteinCountryLooseMatchVoter(0.910f, new GetOrgNameFunction()),
createSectionedNameStrictCountryLooseMatchVoter(0.882f, new GetOrgShortNameFunction()),
createSectionedNameStrictCountryLooseMatchVoter(0.815f, new GetOrgNameFunction()),
createSectionedNameLevenshteinCountryLooseMatchVoter(0.816f, new GetOrgNameFunction()),
createSectionedNameStrictCountryLooseMatchVoter(0.682f, new GetOrgShortNameFunction()),
commonAffOrgNameWordsVoter);
}

Expand Down
4 changes: 2 additions & 2 deletions ...rc/main/java/eu/dnetlib/iis/wf/affmatching/match/MainSectionHashBucketMatcherFactory.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -114,8 +114,8 @@ public static ImmutableList<AffOrgMatchVoter> createAlternativeNameMainSectionHa
return ImmutableList.of(
createNameCountryStrictMatchVoter(1f, new GetOrgAlternativeNamesFunction()),
createNameStrictCountryLooseMatchVoter(1f, new GetOrgAlternativeNamesFunction()),
createSectionedNameStrictCountryLooseMatchVoter(1f, new GetOrgAlternativeNamesFunction()),
createSectionedNameLevenshteinCountryLooseMatchVoter(1f, new GetOrgAlternativeNamesFunction())
createSectionedNameStrictCountryLooseMatchVoter(0.987f, new GetOrgAlternativeNamesFunction()),
createSectionedNameLevenshteinCountryLooseMatchVoter(0.988f, new GetOrgAlternativeNamesFunction())
);
}

Expand Down
17 changes: 16 additions & 1 deletion iis-wf/iis-wf-affmatching/src/test/resources/experimentalData/input/all_organizations.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -61086,4 +61086,19 @@
{"id":"20|dedup_wf_001::fd702fb85b83582332dfdc6c8cdeff18","name":"Norsk Landbruksrådgiving","shortName":"NLR","countryName":"Norway","countryCode":"NO","websiteUrl":"http://www.nlr.no/"}
{"id":"20|dedup_wf_001::fa02c455756943e58e7fb08e5a7576d9","name":"National Aerospace Laboratory","shortName":"NLR","countryName":"Netherlands","countryCode":"NL","websiteUrl":"http://www.nlr.nl/"}
{"id":"20|dedup_wf_001::8541f5855b79a9a508bab2d16d3c9a5e","name":"North Little Rock Health Department","shortName":"NLR","countryName":"United States","countryCode":"US","websiteUrl":"http://nlr.ar.gov/"}
{"id":"20|dedup_wf_001::351db7072f44f66a3d8ee47b88dac2ee","name":"Netherlands Leprosy Relief","shortName":"NLR","countryName":"Netherlands","countryCode":"NL","websiteUrl":"http://leprosyrelief.org/"}
{"id":"20|dedup_wf_001::351db7072f44f66a3d8ee47b88dac2ee","name":"Netherlands Leprosy Relief","shortName":"NLR","countryName":"Netherlands","countryCode":"NL","websiteUrl":"http://leprosyrelief.org/"}

{"id":"20|openorgs____::f5f8a6f2df34e11a00157845bdba14f1","name":"Department of Education","shortName":"Department of Education","countryName":"Philippines","countryCode":"PH","websiteUrl":"http://www.deped.gov.ph/"}
{"id":"20|pending_org_::74114f0833bfb23f09d6fcd263b77d5a","name":"Department of Education","shortName":"TAFE","countryName":"Australia","countryCode":"AU","websiteUrl":"https://www.education.gov.au"}
{"id":"20|openorgs____::22c14af7928c73f46f00abe2f33a5d84","name":"Department of Education","shortName":"Department of Education","countryName":"Ireland","countryCode":"IE","websiteUrl":null}
{"id":"20|ror_________::dfde3ffe0c274d69dd15506b8ab26545","name":"Department of Education","shortName":"DENI","countryName":"United Kingdom","countryCode":"GB","websiteUrl":"https://www.deni.gov.uk/"}
{"id":"20|pending_org_::ae2099bec3e47f7567554a0148083543","name":"DEPARTMENT OF EDUCATION","shortName":"DEPARTMENT OF EDUCATION","countryName":"UNKNOWN","countryCode":"UNKNOWN","websiteUrl":null}
{"id":"20|openorgs____::9d7fa3f561ff71105cbd355db80771ce","name":"Department of Education","shortName":"DENI","countryName":"United Kingdom","countryCode":"GB","websiteUrl":"https://www.deni.gov.uk/"}
{"id":"20|pending_org_::bcc20762d34a86a99848c6168100f784","name":"Department of Education","shortName":"Department of Education","countryName":"UNKNOWN","countryCode":"UNKNOWN","websiteUrl":null}
{"id":"20|openorgs____::535ab088eeda944e72c195b359142ad9","name":"Department of Education","shortName":"Department of Education","countryName":"Spain","countryCode":"ES","websiteUrl":"http://www.hezkuntza.ejgv.euskadi.eus/r43-2722/en"}






4 changes: 3 additions & 1 deletion ...iis-wf-affmatching/src/test/resources/experimentalData/input/docs_with_aff_real_data.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -159,4 +159,6 @@
{"id":"50|od_______908::77e4ff0ae0a493b0a64acbdead7dc5d8","affiliations":[{"organization":"Center of Excellence in Biotechnology Research, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh 11451, Kingdom of","rawText":"Center of Excellence in Biotechnology Research, King Saud University, Riyadh 11451, Kingdom of Saudi Arabia"},{"organization":"Biomarkers Research Program, Biochemistry Department, College of Science, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"PO Box, 2455, Riyadh 11451, Kingdom of","rawText":"Biomarkers Research Program, Biochemistry Department, College of Science, King Saud University, PO Box, 2455, Riyadh 11451, Kingdom of Saudi Arabia"},{"organization":"Prince Mutaib Chair for Biomarkers of Osteoporosis, Biochemistry Department, College of Science, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh 11451, Kingdom of","rawText":"Prince Mutaib Chair for Biomarkers of Osteoporosis, Biochemistry Department, College of Science, King Saud University, Riyadh 11451, Kingdom of Saudi Arabia"},{"organization":"Clinical Pharmacy Department, College of Pharmacy, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh 11451, Kingdom of","rawText":"Clinical Pharmacy Department, College of Pharmacy, King Saud University, Riyadh 11451, Kingdom of Saudi Arabia"},{"organization":"College of Food Science & Agriculture, Department of Food Science & Nutrition, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh, Kingdom of","rawText":"College of Food Science & Agriculture, Department of Food Science & Nutrition, King Saud University, Riyadh, Kingdom of Saudi Arabia"},{"organization":"Department of Health Administration, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh, Kingdom of","rawText":"Department of Health Administration, King Saud University, Riyadh, Kingdom of Saudi Arabia"},{"organization":"Health Affairs for Riyadh Region, Ministry of Health","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh, Kingdom of","rawText":"Health Affairs for Riyadh Region, Ministry of Health, Riyadh, Kingdom of Saudi Arabia"},{"organization":"Department of Clinical Lab Sciences, College of Applied Medical Sciences, King Saud University","countryName":"Saudi Arabia","countryCode":"SA","address":"Riyadh 11451, Kingdom of","rawText":"Department of Clinical Lab Sciences, College of Applied Medical Sciences, King Saud University, Riyadh 11451, Kingdom of Saudi Arabia"}],"title": null,"abstract": null,"language": null,"keywords": null,"externalIdentifiers": null,"journal": null,"year": null,"publisher": null,"references": null,"authors": null,"volume": null,"issue": null,"pages": null,"publicationTypeName": null,"text": ""}
{"id":"50|od_______908::77e52f5d2ecf1ad4e1fcd5d2ab6b79c2","affiliations":[{"organization":"INRA","countryName":"France","countryCode":"FR","address":null,"rawText":"INRA, France"},{"organization":"Northeastern University","countryName":"United States of America","countryCode":"US","address":null,"rawText":"Northeastern University, United States of America"}],"title": null,"abstract": null,"language": null,"keywords": null,"externalIdentifiers": null,"journal": null,"year": null,"publisher": null,"references": null,"authors": null,"volume": null,"issue": null,"pages": null,"publicationTypeName": null,"text": ""}
{"id":"50|dedup_wf_001::6e9c8dd0ff2c33c49a207b43a3bdcae6","affiliations":[{"organization":"Department of Medical Oncology, The s econd a ffiliated h ospital of Zhejiang University s chool of Medicine","countryName":null,"countryCode":null,"address":"h angzhou, Zhejiang Province, People's republic of china","rawText":"Department of Medical Oncology, The s econd a ffiliated h ospital of Zhejiang University s chool of Medicine, h angzhou, Zhejiang Province, People's republic of china"},{"organization":"cancer institute, Key laboratory of cancer Prevention and intervention, chinese n ational Ministry of education","countryName":null,"countryCode":null,"address":"h angzhou, Zhejiang Province, People's republic of china","rawText":"cancer institute, Key laboratory of cancer Prevention and intervention, chinese n ational Ministry of education, h angzhou, Zhejiang Province, People's republic of china"},{"organization":"nlr","countryName":null,"countryCode":null,"address":"Mlr, WBc, neutrophil, monocyte","rawText":"nlr, Mlr, WBc, neutrophil, monocyte"}],"title":null,"abstract":null,"language":null,"keywords":null,"externalIdentifiers":null,"journal":null,"year":null,"publisher":null,"references":null,"authors":null,"volume":null,"issue":null,"pages":null,"publicationTypeName":null,"text":""}
{"id":"50|dedup_wf_001::42330b7e2ea76d9fff4c9556fcb57f88","affiliations":[{"organization":"Institute of Physics, M. Curie-Sklodowska University","countryName":null,"countryCode":null,"address":"Radziszewskiego 10, Pl 20-031 Lublin","rawText":"Institute of Physics, M. Curie-Sklodowska University, Radziszewskiego 10, Pl 20-031 Lublin"}],"title":null,"abstract":null,"language":null,"keywords":null,"externalIdentifiers":null,"journal":null,"year":null,"publisher":null,"references":null,"authors":null,"volume":null,"issue":null,"pages":null,"publicationTypeName":null,"text":""}
{"id":"50|dedup_wf_001::42330b7e2ea76d9fff4c9556fcb57f88","affiliations":[{"organization":"Institute of Physics, M. Curie-Sklodowska University","countryName":null,"countryCode":null,"address":"Radziszewskiego 10, Pl 20-031 Lublin","rawText":"Institute of Physics, M. Curie-Sklodowska University, Radziszewskiego 10, Pl 20-031 Lublin"}],"title":null,"abstract":null,"language":null,"keywords":null,"externalIdentifiers":null,"journal":null,"year":null,"publisher":null,"references":null,"authors":null,"volume":null,"issue":null,"pages":null,"publicationTypeName":null,"text":""}

{"id":"50|doi_dedup___::f15c0d796f8825294e2dacb172bb87f5","affiliations":[{"organization":"Department of Education, University of Catania","countryName":null,"countryCode":null,"address":"I-95124 Catania, Italy; [email protected]","rawText":"Department of Education, University of Catania, I-95124 Catania, Italy; [email protected]"}],"title":null,"abstract":null,"language":null,"keywords":null,"externalIdentifiers":null,"journal":null,"year":null,"publisher":null,"references":null,"authors":null,"volume":null,"issue":null,"pages":null,"publicationTypeName":null,"text":""}

0 comments on commit ae2f12c

Please sign in to comment.