Automated Essay Scoring - Exploring the Utility and Potential of the Large Language Models for the WrightRightNow Platform - Technical Report 2301

Oct 15, 2026

Uploaded by Rhys

Technical Report 2301 examines autoscoring student writing for the WriteRightNow (WRN) platform to reduce frequent, time-consuming grading by teachers. The report motivates the need by describing WRN’s current lack of automated essay scoring despite its customizable prompt library, revision feedback, and grading support. It evaluates large language models (LLMs) as a mechanism to assess coherence, relevance, and sophistication with consistent, rubric-aligned judgments, enabling efficient and real-time feedback.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Methodology

Source dataset for developing the scoring engines

Automated essay scoring approach using LLMs

Algorithm development and evaluation

Technical Report \# 2301 Automated Essay Scoring: Exploring the Utility and Potential of the Large Language Models for the WrightRightNow Platform Cengiz Zopluoglu, University of Oregon Gerald Tindal, University of Oregon Published by Behavioral Research and Teaching University of Oregon • 175 Education 5262 University of Oregon • Eugene, OR 97403-5262 Phone: 541-346-3535 • Fax: 541-346-5689 [http://brt.uoregon.edu](http://brt.uoregon.edu) Copyright © 2023. Behavioral Research and Teaching. All rights reserved. This publication or parts thereof, may not be used or reproduced in any manner without written permission. APA Reference: Zopluoglu, C. & Tindal, G. (2023). Automated Essay Scoring: Exploring the utility of and potential of the large language models for the WrightRightNow platform. University of Oregon: Behavioral Research and Teaching. Technical Report Number 2301. In this technical report, we present initial findings on autoscoring student writing to allow teachers using WriteRightNow to continue assigning writing prompts without facing the burden of frequent scoring. The University of Oregon is committed to the policy that all persons shall have equal access to its programs, facilities, and employment without regard to race, color, creed, religion, national origin, sex, age, marital status, disability, public assistance status, veteran status, or sexual orientation. This document is available in alternate formats upon request. Automated Essay Scoring: Exploring the Utility and Potential of Large Language Models for the WrightRightNow Platform WriteRightNow ([https://writerightnow.com](https://writerightnow.com)) is an innovative digital platform meticulously crafted to enhance writing instruction across various curricula. Central to its design is the customization of instructional content, allowing for a multi-faceted approach that caters to diverse student needs, including those with special educational requirements and English learners. WRN fosters organizational efficiency, enabling educators to systematically guide students from initial planning stages through to the completion of polished writing assignments. Promoting a collaborative educational environment, WRN facilitates best practices among educators, while encouraging student ownership in learning through engaging review cycles. A distinctive feature of WRN is its dynamic library of writing prompts, designed to stimulate critical thinking and intellectual curiosity across a multitude of subjects. Several other features allow teachers to actively engage students in the writing process, allowing revisions with feedback, providing summative grading, and graphing both qualitative and quantitative results. The software was designed to facilitate improvement in writing by writing. Despite its innovative features, WRN currently lacks an automated essay scoring system, a shortfall that places a significant grading burden on educators. Teachers find themselves inundated with a multitude of essays, making the grading process labor-intensive and time-consuming. This constraint detracts from the quality time that educators could invest in individualized student instruction and support, potentially compromising the overall educational experience. The integration of an automated essay scoring system within WRN could profoundly optimize this aspect of the educational process. Such a system would alleviate the grading burden on teachers, enabling a more efficient and streamlined evaluation process. It would enhance the platform’s functionality, allowing educators to focus more on fostering critical thinking and writing skills in students, rather than being overwhelmed by the administrative task of grading. The incorporation of this feature is essential for bolstering WRN’s efficacy and utility as a comprehensive educational tool, driving its evolution towards a more optimized and holistic writing instruction platform. The rise of large lang

FAQs

What problem does the report address for the WrightRightNow (WRN) platform?

WRN currently lacks an automated essay scoring system, which creates a significant grading burden for teachers as they review large numbers of essays.

How does the report propose to implement automated essay scoring?

The report proposes using large language models to evaluate student essays by analyzing syntax, semantics, and context, producing consistent scores aligned to grading rubrics and criteria.

What is the main goal of developing an essay scoring algorithm in this research?

The research aims to explore feasibility and usefulness of automating essay grading to improve efficiency, reduce educator workload, and enhance students’ writing and revision through timely feedback.

Oct 15, 2026

Uploaded by Rhys