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

Relevance popularity: A term event model based feature selection scheme for text classification.

Guozhong Feng1,2,3, Baiguo An4, Fengqin Yang1

  • 1Key Laboratory of Intelligent Information Processing of Jilin Universities, School of Computer Science and Information Technology, Northeast Normal University, Changchun, 130117, China.

Plos One
|April 6, 2017
PubMed
Summary

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

Effects of different tissue substrates on the development and gut microbiota of Sarcophaga peregrina (Diptera: Sarcophagidae).

Journal of medical entomology·2026
Same author

A triplex RPA-LFA assay for the simultaneous detection of forensically important necrophagous insects in complex DNA mixtures.

Forensic science international. Genetics·2026
Same author

Sarcophaga africa (Diptera: Sarcophagidae): A forensically significant flesh fly.

Journal of forensic and legal medicine·2026
Same author

Filtering of artificial chimeric reads generated by ligation preparation method of nanopore sequencing.

iScience·2026
Same author

The role of pig manure-derived gut microbiota in accelerating the growth and development of Sarcophaga africa.

Insect science·2025
Same author

Chromosome-level genome assembly of the synanthropic fly Chrysomya megacephala: insights into oviposition location.

BMC genomics·2025
This summary is machine-generated.

This study introduces a novel feature selection method using a term event Multinomial naive Bayes model. The new approach, focusing on term frequency within documents, improves text classification accuracy over traditional methods.

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Information Retrieval

Background:

  • Feature selection enhances text classification by optimizing input features.
  • Traditional methods often rely on document frequency, overlooking term frequency within documents.
  • Term frequency presents a promising, yet underexplored, feature for classification accuracy.

Purpose of the Study:

  • To propose a novel feature selection scheme leveraging a term event Multinomial naive Bayes model.
  • To investigate the impact of term frequency within documents on classification performance.
  • To develop a new measurement for term selection based on probabilistic modeling.

Main Methods:

  • Developed a term event Multinomial naive Bayes probabilistic model.

Related Experiment Videos

  • Derived a factorizable matching score function based on prediction probability ratio.
  • Estimated model parameters to derive a term selection measurement.

    • Main Results:

    • The proposed method demonstrated superior performance compared to traditional feature selection techniques.
    • Experiments were conducted on benchmark English (20 Newsgroups) and Chinese (MPH-20) text datasets.
    • Evaluated using widely adopted text classifiers: naive Bayes and support vector machine.

    Conclusions:

    • The novel feature selection scheme based on term event probability significantly improves text classification.
    • The method effectively utilizes term frequency within documents, outperforming document frequency-based approaches.
    • The proposed technique offers a robust and accurate solution for feature selection in text classification.