Automated essay evaluator

Date of Publication

2004

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Merlin Cruz

Defense Panel Member

Merin Cruz

Rachel Roxas

Lolita Villanueva-Reyes

Abstract/Summary

Evaluating essay portions of exams has always been labor-intensive for the teaching staff and human evaluators. To solve this problem, researches regarding automatic essay evaluation are ongoing, and practical implementation of such has risen just recently. This research presents Automated Essay Evaluator, a system that automates the evaluation of a large collection of essay-type documents using natural language processing (NLP) and Latent Semantic Analysis (LSA) technique. Rule-based natural language parsing is used for the grammar checking of the text while LSA is used to evaluate the content. Testing and evaluation were done to determine its performance in evaluating essays. Results show that the system is 85%-93% accurate in predicting the grammar grade, while it is 89%-98% accurate in predicting the content grade of essays.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU13691

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

1 v. (various foliations) : ill. (some col.) ; 28 cm. + technical manual & user's guide.

Keywords

Natural language processing (Computer science); Artificial intelligence; Information retrieval; Essay--Evaluation--Computer programs

This document is currently not available here.

Share

COinS