Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Mining MEDLINE: abstracts, sentences, or phrases?

J Ding1, D Berleant, D Nettleton

  • 1Department of Electrical and Computer Engineering, Iowa State University, Ames, Iowa 50011, USA.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|April 4, 2002
PubMed
Summary

This study compares text units for biochemical knowledge mining. Sentences offer the best balance of recall and precision for extracting interactions from scientific literature.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[Progress of cohort studies in countries from Asia and Europe].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2020
Same author

[Investigation of 603 medical staff occupational exposure with blood-borne pathogens].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2020
Same author

Knocking down LSD1 inhibits the stemness features of colorectal cancer stem cells.

Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas·2020
Same author

Broadband, millimeter-wave antireflection coatings for large-format, cryogenic aluminum oxide optics.

Applied optics·2020
Same author

Impact of inorganic salts on vase life and postharvest qualities of the cut flower of Perpetual Carnation.

Brazilian journal of biology = Revista brasleira de biologia·2020
Same author

Magnetic resonance imaging quantification and biodistribution of magnetic nanoparticles using T<sub>1</sub>-enhanced contrast.

Journal of materials chemistry. B·2020

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Computational Biology

Background:

  • Automated knowledge extraction from scientific literature is crucial for advancing biochemical research.
  • Existing methods utilize varying text units, including abstracts, sentences, and phrases, for fact extraction.
  • The optimal text unit for mining biochemical interactions remains an open question.

Purpose of the Study:

  • To compare the effectiveness of abstracts, sentences, and phrases as text units for automated biochemical knowledge mining.
  • To evaluate performance using standard information retrieval metrics: recall, precision, and effectiveness.
  • To determine which text unit yields the most impactful results for identifying biochemical term co-occurrences.

Main Methods:

Related Experiment Videos

  • Utilized MEDLINE database as the digital repository for scientific literature.
  • Implemented term co-occurrence analysis to identify interactions among biochemical terms.
  • Compared performance of abstracts, sentences, and phrases using recall, precision, and effectiveness measures.

    • Main Results:

    • Statistically significant differences were observed in the performance of abstracts, sentences, and phrases.
    • Sentences demonstrated a superior balance of recall and precision for mining biochemical interactions.
    • The choice of text unit significantly impacts the effectiveness of knowledge discovery.

    Conclusions:

    • Sentences are the most effective text unit for mining biochemical interactions from MEDLINE.
    • Findings provide guidance for optimizing automated knowledge extraction strategies.
    • This research contributes to more efficient and accurate biochemical knowledge discovery from scientific texts.