AutoEval: A NLP Approach for Automatic Test Evaluation System

Mayank Agarwal, Ritika Kalia, Vedant Bahel, Achamma Thomas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In this modern era, there is a need for automation in answer assessment systems as the world moves towards automation. Since online response evaluation is only available for option-based questions, the evaluator's job is made more difficult when evaluating theory answers. The teacher manually checks the answer and assigns the required grade. The current system necessitates more manpower and time to evaluate the response. In this paper, we demonstrate the working and operation of the 'AutoEval - Automatic Test Evaluation System', a computerized or automatic exam paper evaluation system. A manual paper evaluation is time-consuming and exhausting, but computerized exam paper evaluation aids in standardizing the paper correction process in an effective and reliable manner. The evaluation of response scripts is an essential part of evaluating students' results. In most cases, a response evaluation is performed manually, which can lead to bias. The assessment is based on several factors including the evaluator's mood swings and the inter-relationship between the student and evaluator. Furthermore, assessment and evaluation are a time-consuming and repetitive process. Natural language processing (NLP) methods are used to evaluate exam papers in a variety of ways. NLP is used to search for grammatical errors, as well as to perform syntactic analysis, semantic similarity and database storage.

Original languageEnglish
Title of host publication2021 IEEE 4th International Conference on Computing, Power and Communication Technologies, GUCON 2021
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9781728199511
DOIs
StatePublished - 24 Sep 2021
Externally publishedYes
Event4th IEEE International Conference on Computing, Power and Communication Technologies, GUCON 2021 - Kuala Lumpur, Malaysia
Duration: 24 Sep 202126 Sep 2021

Publication series

Name2021 IEEE 4th International Conference on Computing, Power and Communication Technologies, GUCON 2021

Conference

Conference4th IEEE International Conference on Computing, Power and Communication Technologies, GUCON 2021
Country/TerritoryMalaysia
CityKuala Lumpur
Period24/09/2126/09/21

Keywords

  • Automatic Evaluation
  • Gensim
  • Marks Scoring
  • Natural language Processing [NLP]
  • NLTK
  • Similarity Measure
  • Text Pre-processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Control and Optimization

Fingerprint

Dive into the research topics of 'AutoEval: A NLP Approach for Automatic Test Evaluation System'. Together they form a unique fingerprint.

Cite this