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

Emotion computing using Word Mover's Distance features based on Ren_CECps.

Fuji Ren1, Ning Liu1

  • 1Faculty of Engineering, Tokushima University, Tokushima, Japan.

Plos One
|April 7, 2018
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

R3DG: Retrieve, Rank, and Reconstruction with Different Granularities for Multimodal Sentiment Analysis.

Research (Washington, D.C.)·2025
Same author

Differently Implicational Bandler-Kohout Subproduct Method.

IEEE transactions on cybernetics·2025
Same author

Triple dimensional psychology knowledge encouraging graph attention networks to exploit aspect-based sentiment analysis.

Scientific reports·2025
Same author

Cross-Modal Data Fusion via Vision-Language Model for Crop Disease Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Dense skip-attention for convolutional networks.

Scientific reports·2025
Same author

ViE-Take: A Vision-Driven Multi-Modal Dataset for Exploring the Emotional Landscape in Takeover Safety of Autonomous Driving.

Research (Washington, D.C.)·2025
Same journal

Invaders taking over-Mollusc faunal change in volcanic barrier lakes of the Albertine Rift biodiversity hotspot.

PloS one·2026
Same journal

AI-driven molecular diversification and ligand-based optimization of macitentan derivatives targeting VEGFR1 and endothelin signaling pathways.

PloS one·2026
Same journal

Performance patterns and records in the world aquatics masters championships: Where do the most frequently represented nations among the top-ten masters swimmers come from?

PloS one·2026
Same journal

Modeling diurnal Temperature-Rainfall relationships under multicollinearity using PLS-SEM: A case study of Ghana.

PloS one·2026
Same journal

Organizational culture, social capital, and emergency capacity in primary healthcare institutions: A cross-sectional structural equation modeling study comparing ordinary and older communities.

PloS one·2026
Same journal

Impact of kidney function on the metabolome in the general population.

PloS one·2026
See all related articles

This study introduces an emotion-separated method (SeTF·IDF) and utilizes Word Mover's Distance (WMD) for improved Chinese text emotion classification. WMD features significantly outperform TF·IDF, enhancing visualization and cross-language applications.

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Affective Computing

Background:

  • Traditional TF·IDF methods have limitations in visualizing and classifying multi-label Chinese emotional corpora.
  • Improving feature representation is crucial for accurate text emotion classification.

Purpose of the Study:

  • To propose an emotion-separated method (SeTF·IDF) for enhanced sentence emotion labeling and visualization.
  • To investigate the effectiveness of Word Mover's Distance (WMD) as a feature representation for Chinese text emotion classification.
  • To evaluate the performance of WMD features against TF·IDF in both Chinese and English corpora.

Main Methods:

  • Developed an emotion-separated method (SeTF·IDF) for assigning distinct values to emotion labels.
  • Employed the Word Mover's Distance (WMD) algorithm for feature representation in text emotion classification.

Related Experiment Videos

  • Conducted experiments on the Ren_CECps (Chinese) and an English corpus using varying data splits (80/20 and 50/50).

    • Main Results:

    • The SeTF·IDF method demonstrated superior visual effects compared to TF·IDF in visualizing the Ren_CECps corpus.
    • WMD features achieved the best F1 scores in Chinese text emotion classification experiments across different training/testing splits.
    • WMD features showed significant improvements over dimension-reduced TF·IDF feature vectors.
    • Experiments on an English corpus confirmed the efficiency of WMD features in cross-language scenarios.

    Conclusions:

    • Word Mover's Distance (WMD) is a highly effective feature representation for Chinese text emotion classification.
    • WMD offers significant advantages over TF·IDF, particularly in enhancing visualization and achieving higher classification accuracy.
    • The proposed methods and findings have implications for cross-language emotion analysis and affective computing.