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

Incorporating conditional random fields and active learning to improve sentiment identification.

Kunpeng Zhang1, Yusheng Xie2, Yi Yang2

  • 1University of Illinois at Chicago, Chicago, IL, USA.

Neural Networks : the Official Journal of the International Neural Network Society
|May 27, 2014
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Random Sampling Method01:09

Random Sampling Method

11.8K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. Data are the result of sampling from a population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest. Among the various sampling methods used by...
11.8K

You might also read

Related Articles

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

Sort by
Same author

Novel human monoclonal antibodies with enhanced sensitivity for lipoarabinomannan antigens present in urines of TB patients.

bioRxiv : the preprint server for biology·2026
Same author

REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis.

IEEE transactions on medical imaging·2026
Same author

Fecal Microbiome and Serum Metabolome Profiles of the Ovarian Failure Mouse Model.

Applied biochemistry and biotechnology·2026
Same author

KRAS<sup>G12V/A146T</sup> mutations are associated with nCRT resistance via enhanced DNA double-strand break repair and support a deep learning prediction framework in LARC.

Cellular & molecular biology letters·2026
Same author

Exposure to dimethyl phthalate induces oxidative stress and autophagy in gill of Zebrafish via the PI3K/AKT/mTOR pathway: Protective role of 1,8-cineole.

Aquatic toxicology (Amsterdam, Netherlands)·2026
Same author

Optimizing Ternary Preparation Parameters of Thin-Film Nanocomposite Membranes for Tailored Selectivity via Interpretable Machine Learning.

Environmental science & technology·2026

This study introduces a new method for sentiment analysis that considers sentence context and structure, improving accuracy by 5%-15% on customer reviews. Active learning strategies were also explored to enhance sentiment labeling with limited data.

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Computational Linguistics

Background:

  • Existing sentiment analysis methods often overlook sentence context and structure.
  • State-of-the-art approaches typically focus on individual sentences, limiting their understanding of nuanced meaning.

Purpose of the Study:

  • To develop an improved sentiment identification method incorporating sentence structure, context, and syntactic information.
  • To investigate the impact of human interaction and active learning on sentiment labeling accuracy with limited data.

Main Methods:

  • Conditional Random Fields (CRFs) were employed to integrate contextual and structural features.
  • Two distinct active learning strategies were proposed and evaluated for efficient data labeling.
Keywords:
Active learningConditional random fieldsCustomer reviewsSentiment analysis

Related Experiment Videos

Main Results:

  • The proposed method achieved a 5%-15% improvement in accuracy on Amazon customer reviews.
  • The approach outperformed existing supervised learning and rule-based sentiment identification techniques.

Conclusions:

  • Incorporating sentence structure and context significantly enhances sentiment analysis accuracy.
  • Active learning strategies are effective for improving sentiment labeling, especially with constrained training datasets.