STUDENT ASSESSMENT USING EDITING DISTANCE AND KEYWORDS MATCHIN.

Saved in:

Bibliographic Details
Title:	STUDENT ASSESSMENT USING EDITING DISTANCE AND KEYWORDS MATCHIN.
Authors:	POPESCU, Doru Anastasiu¹, BOLD, Nicolae¹, POPESCU, Ion Alexandru¹
Source:	Annals of the Faculty of Engineering Hunedoara - International Journal of Engineering. May2026, Vol. 24 Issue 2, p77-84. 8p.
Subjects:	Grading of students, Keyword searching, Web-based user interfaces
Abstract:	This paper presents an automated assessment model that is based on assessment tests formed of Short-Answer Items (SAQ). This type consists in a textual answer with a given maximum length. In order to compare the correct answer with the one given by the student, an algorithm that computes the editing distance (also known as Levenshtein distance) between the two answers and the existence of given keywords (semantic tags) is used. Within the model, an item is considered to be answered correctly if the obtainedediting distance is inferior to a threshold and the answer contains a set proportion or specific semantic tags. The model will also include the analysis of the optimal way of inputting the needed data by a user by introducing descriptive nontechnical requirements. In this matter, the threshold for the editing distance and the usage of semantic tags will be established using natural language-based descriptors (e.g., scales, fuzzy, proportions), offering an intuitive non-technical modality of inputting datathat is later mapped to the edit distance and required keywords. In order to implement the described model, a web application can be created. This web application extracts the items and the values needed in the assessment process from a database and computes the result automatically. The obtained data is then stored to be further analysed by an assessor or using an automated learning method. [ABSTRACT FROM AUTHOR]
	Copyright of Annals of the Faculty of Engineering Hunedoara - International Journal of Engineering is the property of University Politehnica Timisoara, Faculty of Engineering Hunedoara and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	This paper presents an automated assessment model that is based on assessment tests formed of Short-Answer Items (SAQ). This type consists in a textual answer with a given maximum length. In order to compare the correct answer with the one given by the student, an algorithm that computes the editing distance (also known as Levenshtein distance) between the two answers and the existence of given keywords (semantic tags) is used. Within the model, an item is considered to be answered correctly if the obtainedediting distance is inferior to a threshold and the answer contains a set proportion or specific semantic tags. The model will also include the analysis of the optimal way of inputting the needed data by a user by introducing descriptive nontechnical requirements. In this matter, the threshold for the editing distance and the usage of semantic tags will be established using natural language-based descriptors (e.g., scales, fuzzy, proportions), offering an intuitive non-technical modality of inputting datathat is later mapped to the edit distance and required keywords. In order to implement the described model, a web application can be created. This web application extracts the items and the values needed in the assessment process from a database and computes the result automatically. The obtained data is then stored to be further analysed by an assessor or using an automated learning method. [ABSTRACT FROM AUTHOR]
ISSN:	15842665