A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study (doi:10.7910/DVN/M5PRZB)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Document Description

Citation

Title:

A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study

Identification Number:

doi:10.7910/DVN/M5PRZB

Distributor:

Harvard Dataverse

Date of Distribution:

2026-02-04

Version:

2

Bibliographic Citation:

Kang, Inmo; Park, Joonmo; Jeong, Heesoo; Chung, Seyoung; Jeon, Changmin; Moon, Seongwuk, 2026, "A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study", https://doi.org/10.7910/DVN/M5PRZB, Harvard Dataverse, V2

Study Description

Citation

Title:

A two-stage registry-anchored approach for precision improvement in organization name recognition from PubMed affiliation strings: a validation study

Identification Number:

doi:10.7910/DVN/M5PRZB

Authoring Entity:

Kang, Inmo (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Park, Joonmo (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Jeong, Heesoo (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Chung, Seyoung (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Jeon, Changmin (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Moon, Seongwuk (Graduate School of Management of Technology, Sogang Univeristy, Seoul, Korea)

Distributor:

Harvard Dataverse

Access Authority:

Moon, Seongwuk

Depositor:

(KCSE), Korean Councils of Science Editors

Date of Deposit:

2026-02-04

Holdings Information:

https://doi.org/10.7910/DVN/M5PRZB

Study Scope

Keywords:

Social Sciences

Abstract:

Dataset 1. The dataset analyzed during the current study.

Methodology and Processing

Sources Statement

Data Access

Notes:

<a href="http://creativecommons.org/publicdomain/zero/1.0">CC0 1.0</a>

Other Study Description Materials

Other Study-Related Materials

Label:

20251220_SciEdit_ROR corpus_Submit.json

Notes:

application/json

Other Study-Related Materials

Label:

Dataset 1. The dataset analyzed during the current study..csv

Notes:

text/comma-separated-values

Other Study-Related Materials

Label:

geo_data.json

Notes:

application/json

Other Study-Related Materials

Label:

Suppl. 1. Methods for constructing the ROR corpus, PubMed sample, and gold standard..pdf

Notes:

application/pdf

Other Study-Related Materials

Label:

Suppl. 2. Model implementation details..pdf

Notes:

application/pdf

Other Study-Related Materials

Label:

Suppl. 3. Evaluation metrics and baseline implementation..pdf

Notes:

application/pdf