Skip to main content

User account menu

  • Log in
Home
  • Home
  • Data Sharing Resources
  • Browse our Data
  • Help

Breadcrumb

  1. Home
  • Temple University
  • Trina D. Spencer

Displaying results 1 - 4 of 4 (Go to Advanced Search)
Search for ALL of these words
Search for ANY of these words
EXCLUDE all of these words
Project
Favorite
Login or Register to use this feature.
Automated Narrative Scoring Using Large Language Models
Description: The analysis of narratives often accompanies comprehensive language assessments of students. While analyzing narratives can be time-consuming and labor-intensive, recent advances in large language models (LLMs) indicate that it may be possible to automate this process.
Investigators: Saman Enayati, Ziyu Yang, Slobodan Vucetic, Trina D. Spencer
View Full Item
Dataset
Favorite
Login or Register to use this feature.
Test Data
Part of Project: Automated Narrative Scoring Using Large Language Models
Description: Narrative language samples elicited using the ALPS Oral Narrative Retell and Oral Narrative Generation tasks from diverse K-3 students. The test data set was drawn randomly from the larger corpus of narrative language samples.
Investigators: Saman Enayati, Ziyu Yang, Slobodan Vucetic, Trina D. Spencer
View Full Item
Dataset
Favorite
Login or Register to use this feature.
Training Data
Part of Project: Automated Narrative Scoring Using Large Language Models
Description: Narrative language samples elicited using the ALPS Oral Narrative Retell and Oral Narrative Generation tasks from diverse K-3 students. The training data set was drawn randomly from the larger corpus of narrative language samples.
Investigators: Saman Enayati, Ziyu Yang, Slobodan Vucetic, Trina D. Spencer
View Full Item
Dataset
Favorite
Login or Register to use this feature.
TwoRaters
Part of Project: Automated Narrative Scoring Using Large Language Models
Description: Narrative language samples elicited using the ALPS Oral Narrative Retell and Oral Narrative Generation tasks from diverse K-3 students. The tworaters data set was drawn randomly from the larger corpus of narrative language samples. These samples were scored by two raters for reliability purposes.
Investigators: Saman Enayati, Ziyu Yang, Slobodan Vucetic, Trina D. Spencer
View Full Item
Start New Search

Content Type

  • Dataset (3)
  • Project (1)

Constructs

Assessments

Participant Type

Special Populations

Educational Environments

Project Methods

Developmental Designs

Persons

  • [x] Trina D. Spencer (4)
  • Saman Enayati (4)
  • Slobodan Vucetic (4)
  • Ziyu Yang (4)

Organizations

  • [x] Temple University (4)
  • University of South Florida (7)
  • University of Kansas (6)
  • Northern Arizona University (2)
  • Kansas University Medical Center (1)
  • Rush University (1)
  • University of Kentucky (1)
  • University of Louisville (1)

This repository is a collaboration between the FSU Department of Psychology, the Florida Center for Reading Research, and the FSU Libraries. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

On March 25, 2025, the NIH requested that we post this text: "This repository is under review for potential modification in compliance with Administration directives."

Questions or Comments? Contact us or report a problem.

Bottom Row Footer Links

  • Terms of Service
  • Privacy FAQ
  • About

NIH logo Grant #R01HD095193