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

Using discourse analysis to improve text categorization in MEDLINE.

Patrick Ruch1, Antoine Geissbühler, Julien Gobeill

  • 1Medical Informatics Service, University and Hospital of Geneva, Geneva, Switzerland. patrick.ruch@sim.hcuge.ch

Studies in Health Technology and Informatics
|October 4, 2007
PubMed
Summary
This summary is machine-generated.

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

The missing link in FAIR data policy: biodata resources in life sciences.

Scientific data·2026
Same author

Unlocking the potential of PubMed Central supplementary data files.

Bioinformatics advances·2025
Same author

Manuscript Classification to Support the Analysis of Biases in Publication Opportunities.

Studies in health technology and informatics·2025
Same author

Health workers' perspectives on self-monitoring of blood pressure by pregnant women: a qualitative study among community health workers, midwives, doctors and health system managers in Lombok, Indonesia.

BMJ global health·2025
Same author

"I believe it when there is an expert next to me:" a qualitative analysis on the perceptions and experiences of pregnant women to self-monitor blood pressure in Lombok, Indonesia.

BMC pregnancy and childbirth·2025
Same author

Value Propositions for Digital Shared Medication Plans to Boost Patient-Health Care Professional Partnerships: Co-Design Study.

Journal of participatory medicine·2025
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

This study improved automatic keyword assignment for scientific articles by incorporating argumentative structure analysis. Overweighting the METHODS section significantly boosted categorization effectiveness, enhancing text mining in digital libraries.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Bibliometrics

Background:

  • Automatic keyword assignment aids literature search and content summarization in medical informatics.
  • Current methods for assigning Medical Subject Headings (MeSH) include machine learning and linguistically-motivated approaches.
  • Existing techniques often overlook the rhetorical structure of scientific texts.

Purpose of the Study:

  • To evaluate the impact of argumentative structures on automatic text categorization effectiveness.
  • To enhance the performance of a combined linguistically-motivated and information retrieval categorizer.
  • To investigate the utility of discourse analysis for improving MeSH assignment.

Main Methods:

  • Developed an argumentative categorizer classifying abstract sentences into PURPOSE, METHODS, RESULTS, and CONCLUSION.

Related Experiment Videos

  • Utilized the OHSUMED collection as a benchmark for evaluation.
  • Modified the ranking of a MeSH categorizer based on the argumentative classification of sentences.

    • Main Results:

    • The enhanced categorizer achieved a statistically significant improvement of +2% (p<0.003).
    • Overweighting the METHODS section provided the most substantial boost in categorization effectiveness.
    • Moderate increases in effectiveness were observed by emphasizing RESULTS and CONCLUSION sections.

    Conclusions:

    • Argumentative features offer a modest but significant improvement for text categorization tasks.
    • Discourse analysis methods show promise for advancing text mining in scientific digital libraries.
    • Integrating rhetorical structure analysis can enhance automatic indexing and information retrieval.