Item Difficulty Prediction Using Item Text Features: Comparison of Predictive Performance across Machine-Learning Algorithms

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F23%3A00577144" target="_blank" >RIV/67985807:_____/23:00577144 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216208:11210/23:10470307 RIV/00216208:11110/23:10470307 RIV/00216208:11410/23:10470307

Výsledek na webu

<a href="https://dx.doi.org/10.3390/math11194104" target="_blank" >https://dx.doi.org/10.3390/math11194104</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/math11194104" target="_blank" >10.3390/math11194104</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Item Difficulty Prediction Using Item Text Features: Comparison of Predictive Performance across Machine-Learning Algorithms

Popis výsledku v původním jazyce

This work presents a comparative analysis of various machine learning (ML) methods for predicting item difficulty in English reading comprehension tests using text features extracted from item wordings. A wide range of ML algorithms are employed within both the supervised regression and the classification tasks, including regularization methods, support vector machines, trees, random forests, back-propagation neural networks, and Naïve Bayes. Moreover, the ML algorithms are compared to the performance of domain experts. Using f-fold cross-validation and considering the root mean square error (RMSE) as the performance metric, elastic net outperformed other approaches in a continuous item difficulty prediction. Within classifiers, random forests returned the highest extended predictive accuracy. We demonstrate that the ML algorithms implementing item text features can compete with predictions made by domain experts, and we suggest that they should be used to inform and improve these predictions, especially when item pre-testing is limited or unavailable. Future research is needed to study the performance of the ML algorithms using item text features on different item types and respondent populations.

Název v anglickém jazyce

Item Difficulty Prediction Using Item Text Features: Comparison of Predictive Performance across Machine-Learning Algorithms

Popis výsledku anglicky

This work presents a comparative analysis of various machine learning (ML) methods for predicting item difficulty in English reading comprehension tests using text features extracted from item wordings. A wide range of ML algorithms are employed within both the supervised regression and the classification tasks, including regularization methods, support vector machines, trees, random forests, back-propagation neural networks, and Naïve Bayes. Moreover, the ML algorithms are compared to the performance of domain experts. Using f-fold cross-validation and considering the root mean square error (RMSE) as the performance metric, elastic net outperformed other approaches in a continuous item difficulty prediction. Within classifiers, random forests returned the highest extended predictive accuracy. We demonstrate that the ML algorithms implementing item text features can compete with predictions made by domain experts, and we suggest that they should be used to inform and improve these predictions, especially when item pre-testing is limited or unavailable. Future research is needed to study the performance of the ML algorithms using item text features on different item types and respondent populations.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA21-03658S" target="_blank" >GA21-03658S: Teoretické základy výpočetní psychometrie</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Mathematics

ISSN

2227-7390

e-ISSN

—

Svazek periodika

11

Číslo periodika v rámci svazku

19

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

30

Strana od-do

4104

Kód UT WoS článku

001084249000001

EID výsledku v databázi Scopus

2-s2.0-85176471034