A comparison of various machine learning algorithms and execution of flask deployment on essay grading

Aug 4, 2026

Upload by Jiven

Students’ performance is typically assessed by manually grading examination answers, which becomes cumbersome as student-teacher ratios grow. The shift toward online teaching during the COVID-19 pandemic increases the need for automated evaluation, especially for essay writing where standard grading systems do not fit. This paper compares machine learning and NLP approaches for automated essay scoring, addresses data imbalance via random oversampling, and evaluates models using accuracy, precision, recall, and F1-score.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Motivation for automated essay scoring

Background and use cases (TOEFL/IELTS/GRE, English literature)

Methods

Machine learning and NLP approaches for essay grading

Handling data imbalance with random over-sampling

Flask-based web application deployment

Evaluation

Metrics: accuracy, precision, recall, F1-score

Model comparison and best-performing algorithm

A comparison of various machine learning algorithms and execution of flask deployment on essay grading Udhika Meghana Kotha, Haveela Gaddam, Deepthi Reddy Siddenki, Sumalatha Saleti Department of Computer Science and Engineering, SRM University AP, Andhra Pradesh, India Article Info ABSTRACT | Article history:
Received Jul 11, 2022 Revised Jul 25, 2022 Accepted Aug 18, 2022 | Students ’ performance can be assessed based on grading the answers written by the students during their examination. Currently, students are assessed manually by the teachers. This is a cumbersome task due to an increase in the student-teacher ratio. Moreover, due to coronavirus disease (COVID-19) pandemic, most of the educational institutions have adopted online teaching and assessment. To measure the learning ability of a student, we need to assess them. The current grading system works well for multiple choice questions, but there is no grading system for evaluating the essays. In this paper, we studied different machine learning and natural language processing techniques for automated essay scoring/grading (AES/G) . Data imbalance is an issue which creates the problem in predicting the essay score due to uneven distribution of essay scores in the training data. We handled this issue using random over sampling technique which generates even distribution of essay scores. Also, we built a web application using flask and deployed the machine learning models. Subsequently, all the models have been evaluated using accuracy, precision, recall, and F1-score. It is found that random forest algorithm outperformed the other algorithms with an accuracy of 97.67%, precision of 97.62%, recall of 97.67%, and F1-score of 97.58% .
This is an open access article under the CC BY-SA license.
| | --- | --- | | Keywords:
Automated essay scoring
Count vectorizer Essay grading Flask deployment Machine learning | | Corresponding Author: Sumalatha Saleti Department of Computer Science and Engineering, SRM University AP Neerukonda, Guntur District, Andhra Pradesh, India Email: [sumalatha.s@srmap.edu.in](sumalatha.s@srmap.edu.in) 1. INTRODUCTION Automated essay scoring (AES) [1] is a specialized system used to assign scores to the essays written in the form of various computer programs. It works by extracting various special features such as word count, vocabulary, the density of error, paragraph structure, and length of sentences. It is mainly used for its validity and reliability which has now become a great attraction from schools, colleges, companies, and researchers. Evaluation and grading are considered to play crucial importance in English literature. Where AES was once considered a myth/impossible task/unattainable job is now being developed after many trials and errors and after many upgrades from previous versions are now induced into education systems. As of today, essays written by students from all over the place are graded by not only teachers or examiners but also machines. Currently, most of the AES systems are used for grading English essays in most of the European countries [2] . Many intellectuals argue that the nature of the essay grading leads to the mismatches in the scores given by human raters, which is a major injustice for many of the students. This may be eradicated if the proposed technique can be used to evaluate essays with a scope generated by the human rater. Such artificial intelligent systems attain relative productivity to AES by replicating the human intelligence and the behavior of electronic systems to soften the burden of educators. The literature field exams which test the student’s capability and knowledge in the subject like test of English as a foreign language (TOEFL) , international English language testing system (IELTS), and graduate record exam (GRE) are graded by both humans and machine learning based automated essay grading systems where both these grades are taken into consideration and

FAQs

What problem does automated essay scoring aim to solve?

It reduces the heavy workload and inconsistency of manual essay grading, especially when many students submit written answers and online assessment is adopted.

How does the study handle imbalanced essay-score data?

It uses a random oversampling technique to generate a more even distribution of essay scores in the training data.

Which model performs best and how is it assessed?

Random forest outperforms other algorithms, with evaluation using accuracy, precision, recall, and F1-score.

Aug 4, 2026

Upload by Jiven