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 Video

Updated: Feb 19, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.2K

Computerized summary scoring: crowdsourcing-based latent semantic analysis.

Haiying Li1, Zhiqiang Cai2, Arthur C Graesser2,3

  • 1Graduate School of Education, Rutgers - The State University of New Jersey, New Brunswick, NJ, 08901, USA. haiying.li@gse.rutgers.edu.

Behavior Research Methods
|November 5, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

3.7K
3.7K

You might also read

Related Articles

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

Sort by
Same author

Melanocortin-1 receptor expression as a predictive factor for postoperative outcomes in melanoma patients: a retrospective study.

Frontiers in immunology·2025
Same author

Genome-wide association study and candidate gene analysis of reproductive traits in Yili geese.

Poultry science·2025
Same author

Multifunctional alginate-sinapic acid/arginine-strontium hydrogel for promoting diabetic wound healing.

International journal of biological macromolecules·2025
Same author

Correction to: Hydrogen Sulfide Ameliorates Early Brain Injury Following Subarachnoid Hemorrhage in Rats.

Molecular neurobiology·2025
Same author

Poisson diffusion probabilistic model for low-dose SPECT sinogram denoising.

Medical physics·2025
Same author

The current clinical landscape of preterm infants less than 32 weeks of gestation receiving delivery room chest compression in Jiangsu Province, China.

Resuscitation plus·2025
Same journal

Exploring psychological tradeoffs: Developing and demonstrating an R Shiny app for Pareto optimization.

Behavior research methods·2026
Same journal

The performance of Bayesian fit measures in detecting misspecified multilevel structural equation modeling.

Behavior research methods·2026
Same journal

Psychometric functions from multiple responses : Dedicated to the memory of Colin L. Mallows.

Behavior research methods·2026
Same journal

Low-cost, open-source, full-stack software and Arduino-based hardware for control of commercially available animal behavior systems.

Behavior research methods·2026
Same journal

PyNeon: A Python package for the analysis of Neon multimodal mobile eye-tracking data.

Behavior research methods·2026
Same journal

Talking surveys: How photorealistic embodied conversational agents shape response quality, engagement, and satisfaction.

Behavior research methods·2026
See all related articles

A new crowdsourcing approach for latent semantic analysis (LSA) in computerized summary scoring (CSS) matches human performance. This method reduces the need for expert summaries, saving time and resources in automated assessment.

Area of Science:

  • Natural Language Processing
  • Educational Technology
  • Computational Linguistics

Background:

  • Latent Semantic Analysis (LSA) is crucial for Computerized Summary Scoring (CSS).
  • Traditional LSA methods rely on expert-generated or pre-graded summaries, which are costly and time-consuming.
  • Source texts, while less resource-intensive, do not accurately predict human summary scores.

Purpose of the Study:

  • To develop and evaluate a crowdsourcing-based LSA approach for CSS.
  • To compare the performance of crowdsourcing LSA against other LSA formulations.
  • To assess the impact of the number of crowdsourced summaries on performance.

Main Methods:

  • Developed a crowdsourcing-based LSA model for CSS.
  • Evaluated the crowdsourcing LSA method against seven other LSA methods using various summary sources (expert, crowdsourced, source texts).
Keywords:
Computerized summary scoringCrowdsourcingLSA similarity

Related Experiment Videos

Last Updated: Feb 19, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.2K
  • Compared model performance against human summary scores as the gold standard.

    • Main Results:

    • Crowdsourcing LSA demonstrated comparable performance to expert-good and crowdsourcing-good summaries in predicting human scores.
    • The crowdsourcing LSA method outperformed other evaluated LSA approaches.
    • Performance was not significantly affected by the number of crowdsourced summaries (10-100).

    Conclusions:

    • Crowdsourcing LSA offers a practical and efficient alternative for CSS, reducing human effort.
    • This approach provides a viable solution for small-scale CSS, benefiting instructors and automated assessment research.
    • It advances automated assessment by enabling semantic convergence on content without extensive human input.