Automaatika referaat (eng)
The Intelligent Essay Assessor which is used by a variety of proprietary electronic
portfolio systems. All of the products have the capacity to
receive text by web page and return feedback to both a student user and comprehensive
data base that may be accessed by teachers. In the paragraphs below, a short description
is given that illustrate the kinds of factors/dimensions/variables used in building AES
scoring models. References are provided for a more comprehensive descripiton of the
process.
The construction of e-rater v. 2.0, models is given in detail in Attali and Burstein
E-rater uses a sample of human-scored essay data for model building purposes.
E-rater identifies features and feature weights are assigned using a multiple regression
procedure. E-rater models can be built at the topic level, in which case a model is built
for a specific essay prompt. However, more often, e-rater models are built at the gradelevel.