Article · Trudy Universiteta · September 30, 2023

Using Machine Learning Models to Evaluate the Quality of Text Documents

Dinara Kaibassova, Olessya YUCHSHENKO, Bigul MUKHAMETZHANOVA, Zagira Saimanova, Margulan Nurtay

Abstract

This results of a study on the use of the machine learning method in the processing of text documents to assess the quality of students' written work are presented. Reviewing students' written work, such as exam essays or lab reports, can be quite a time-consuming process, although reviewing such as term papers has become a common time-consuming practice. One of the common problems that arise when evaluating text documents can be the low quality of the source data, which does not comply with the document formatting rules. During the experiment, data was obtained, consisting of several works for testing. The quality assessment indicators used in this study are the compliance of the explanatory note with the structural elements of the document. The best fit model for scoring has been validated against several machine learning algorithms and techniques such as k-nearest neighbors (kNN), support vector regression (SVR), and random forest. The result of the comparison shows that, having advantages in the learning process, kNN provided the highest prediction accuracy. The learning results of all algorithms are clearly presented in tables and graphic illustration

Text and Document Classification TechnologiesOnline Learning and AnalyticsHandwritten Text Recognition Techniquestext quality assessmentstudent writingessay scoring

Using Machine Learning Models to Evaluate the Quality of Text Documents

Abstract

More by Dinara Kaibassova