Retrieval and classification of dental research articles.

W. C. Bartling, Titus Schleyer, S. Visweswaran

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Successful retrieval of a corpus of literature on a broad topic can be difficult. This study demonstrates a method to retrieve the dental and craniofacial research literature. We explored MeSH manually for dental or craniofacial indexing terms. MEDLINE was searched using these terms, and a random sample of references was extracted from the resulting set. Sixteen dental research experts categorized these articles, reading only the title and abstract, as either: (1) dental research, (2) dental non-research, (3) non-dental, or (4) not sure. Identify Patient Sets (IPS), a probabilistic text classifier, created models, based on the presence or absence of words or UMLS phrases, that distinguished dental research articles from all others. These models were applied to a test set with different inputs for each article: (1) title and abstract only, (2) MeSH terms only, or (3) both. By title and abstract only, IPS correctly classified 64% of all dental research articles present in the test set. The percentage of correctly classified dental research articles in this retrieved set was 71%. MeSH term inclusion decreased performance. Computer programs that use text input to categorize articles may aid in retrieval of a broad corpus of literature better than indexing terms or key words alone.

Original languageEnglish
Pages (from-to)115-120
Number of pages6
JournalAdvances in dental research
Volume17
StatePublished - 2003
Externally publishedYes

Fingerprint

Dental Research
Unified Medical Language System
MEDLINE
Reading
Tooth
Software

Cite this

Retrieval and classification of dental research articles. / Bartling, W. C.; Schleyer, Titus; Visweswaran, S.

In: Advances in dental research, Vol. 17, 2003, p. 115-120.

Research output: Contribution to journalArticle

Bartling, W. C. ; Schleyer, Titus ; Visweswaran, S. / Retrieval and classification of dental research articles. In: Advances in dental research. 2003 ; Vol. 17. pp. 115-120.
@article{e61c18bc3e9d402d9d7db86faa03a3c1,
title = "Retrieval and classification of dental research articles.",
abstract = "Successful retrieval of a corpus of literature on a broad topic can be difficult. This study demonstrates a method to retrieve the dental and craniofacial research literature. We explored MeSH manually for dental or craniofacial indexing terms. MEDLINE was searched using these terms, and a random sample of references was extracted from the resulting set. Sixteen dental research experts categorized these articles, reading only the title and abstract, as either: (1) dental research, (2) dental non-research, (3) non-dental, or (4) not sure. Identify Patient Sets (IPS), a probabilistic text classifier, created models, based on the presence or absence of words or UMLS phrases, that distinguished dental research articles from all others. These models were applied to a test set with different inputs for each article: (1) title and abstract only, (2) MeSH terms only, or (3) both. By title and abstract only, IPS correctly classified 64{\%} of all dental research articles present in the test set. The percentage of correctly classified dental research articles in this retrieved set was 71{\%}. MeSH term inclusion decreased performance. Computer programs that use text input to categorize articles may aid in retrieval of a broad corpus of literature better than indexing terms or key words alone.",
author = "Bartling, {W. C.} and Titus Schleyer and S. Visweswaran",
year = "2003",
language = "English",
volume = "17",
pages = "115--120",
journal = "Advances in dental research",
issn = "0895-9374",
publisher = "International Association for Dental Research",

}

TY - JOUR

T1 - Retrieval and classification of dental research articles.

AU - Bartling, W. C.

AU - Schleyer, Titus

AU - Visweswaran, S.

PY - 2003

Y1 - 2003

N2 - Successful retrieval of a corpus of literature on a broad topic can be difficult. This study demonstrates a method to retrieve the dental and craniofacial research literature. We explored MeSH manually for dental or craniofacial indexing terms. MEDLINE was searched using these terms, and a random sample of references was extracted from the resulting set. Sixteen dental research experts categorized these articles, reading only the title and abstract, as either: (1) dental research, (2) dental non-research, (3) non-dental, or (4) not sure. Identify Patient Sets (IPS), a probabilistic text classifier, created models, based on the presence or absence of words or UMLS phrases, that distinguished dental research articles from all others. These models were applied to a test set with different inputs for each article: (1) title and abstract only, (2) MeSH terms only, or (3) both. By title and abstract only, IPS correctly classified 64% of all dental research articles present in the test set. The percentage of correctly classified dental research articles in this retrieved set was 71%. MeSH term inclusion decreased performance. Computer programs that use text input to categorize articles may aid in retrieval of a broad corpus of literature better than indexing terms or key words alone.

AB - Successful retrieval of a corpus of literature on a broad topic can be difficult. This study demonstrates a method to retrieve the dental and craniofacial research literature. We explored MeSH manually for dental or craniofacial indexing terms. MEDLINE was searched using these terms, and a random sample of references was extracted from the resulting set. Sixteen dental research experts categorized these articles, reading only the title and abstract, as either: (1) dental research, (2) dental non-research, (3) non-dental, or (4) not sure. Identify Patient Sets (IPS), a probabilistic text classifier, created models, based on the presence or absence of words or UMLS phrases, that distinguished dental research articles from all others. These models were applied to a test set with different inputs for each article: (1) title and abstract only, (2) MeSH terms only, or (3) both. By title and abstract only, IPS correctly classified 64% of all dental research articles present in the test set. The percentage of correctly classified dental research articles in this retrieved set was 71%. MeSH term inclusion decreased performance. Computer programs that use text input to categorize articles may aid in retrieval of a broad corpus of literature better than indexing terms or key words alone.

UR - http://www.scopus.com/inward/record.url?scp=3242795899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3242795899&partnerID=8YFLogxK

M3 - Article

C2 - 2004116621

AN - SCOPUS:3242795899

VL - 17

SP - 115

EP - 120

JO - Advances in dental research

JF - Advances in dental research

SN - 0895-9374

ER -