The validity of constructed-response items like essays that are commonly used within informal diagnostics is threatened by many biases. Computer based essay scoring reduces these biases. Latent semantic analysis (LSA) is a statistical technique that allows the representation of human semantic knowledge structures within the computer, thus enabling automatic essay scoring. The article describes the basic steps for implementing a LSA-based system in German language and examines its performance on multiple-choice knowledge tests and essay scoring. It showed an equal performance compared to university students in classifying animal species and achieved medium to high correlations with human raters in essay scoring. Using added scores, the correlations reached values necessary for the reliability of standardized tests. Besides essay scoring, intelligent tutoring software and the extension of psychological models by semantic modules are further interesting field of applications of the LSA.
%0 Generic
%1 w2007automatische
%A Lenhard, Wolfgang
%A Baier, Herbert
%A Hoffmann, Joachim
%A Schneider, Wolfgang
%D 2007
%K caa freetext lsa
%T Automatische Bewertung offener Antworten mittels Latenter Semantischer Analyse
%U http://www.i4.psychologie.uni-wuerzburg.de/mitarbeiter/prof_dr_wolfgang_schneider/publikationen/
%X The validity of constructed-response items like essays that are commonly used within informal diagnostics is threatened by many biases. Computer based essay scoring reduces these biases. Latent semantic analysis (LSA) is a statistical technique that allows the representation of human semantic knowledge structures within the computer, thus enabling automatic essay scoring. The article describes the basic steps for implementing a LSA-based system in German language and examines its performance on multiple-choice knowledge tests and essay scoring. It showed an equal performance compared to university students in classifying animal species and achieved medium to high correlations with human raters in essay scoring. Using added scores, the correlations reached values necessary for the reliability of standardized tests. Besides essay scoring, intelligent tutoring software and the extension of psychological models by semantic modules are further interesting field of applications of the LSA.
@misc{w2007automatische,
abstract = {The validity of constructed-response items like essays that are commonly used within informal diagnostics is threatened by many biases. Computer based essay scoring reduces these biases. Latent semantic analysis (LSA) is a statistical technique that allows the representation of human semantic knowledge structures within the computer, thus enabling automatic essay scoring. The article describes the basic steps for implementing a LSA-based system in German language and examines its performance on multiple-choice knowledge tests and essay scoring. It showed an equal performance compared to university students in classifying animal species and achieved medium to high correlations with human raters in essay scoring. Using added scores, the correlations reached values necessary for the reliability of standardized tests. Besides essay scoring, intelligent tutoring software and the extension of psychological models by semantic modules are further interesting field of applications of the LSA.},
added-at = {2010-05-20T09:31:36.000+0200},
author = {Lenhard, Wolfgang and Baier, Herbert and Hoffmann, Joachim and Schneider, Wolfgang},
biburl = {https://www.bibsonomy.org/bibtex/2f80836d09b6ea6dc7b1b18574eb17db3/ifland},
date = {(2007)},
description = {Lehrstuhl für Psychologie IV: Publikationen},
interhash = {2fb63d9c630757e43041bff50d1b9e3a},
intrahash = {f80836d09b6ea6dc7b1b18574eb17db3},
keywords = {caa freetext lsa},
language = {de},
tech = {Diagnostica},
timestamp = {2010-05-20T09:31:36.000+0200},
title = {Automatische Bewertung offener Antworten mittels Latenter Semantischer Analyse},
url = {http://www.i4.psychologie.uni-wuerzburg.de/mitarbeiter/prof_dr_wolfgang_schneider/publikationen/},
year = 2007
}