@inproceedings{fulari-rusert-2024-utilizing,
title = "Utilizing Machine Learning to Predict Question Difficulty and Response Time for Enhanced Test Construction",
author = "Fulari, Rishikesh and
Rusert, Jonathan",
editor = {Kochmar, Ekaterina and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bea-1.45",
pages = "528--533",
abstract = "In this paper, we present the details of ourcontribution to the BEA Shared Task on Automated Prediction of Item Difficulty and Response Time. Participants in this collaborativeeffort are tasked with developing models to predict the difficulty and response time of multiplechoice items within the medical domain. Theseitems are sourced from the United States Medical Licensing Examination® (USMLE®), asignificant medical assessment. In order toachieve this, we experimented with two featurization techniques, one using lingusitic features and the other using embeddings generated by BERT fine-tuned over MS-MARCOdataset. Further, we tried several different machine learning models such as Linear Regression, Decision Trees, KNN and Boosting models such as XGBoost and GBDT. We found thatout of all the models we experimented withRandom Forest Regressor trained on Linguisticfeatures gave the least root mean squared error.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fulari-rusert-2024-utilizing">
<titleInfo>
<title>Utilizing Machine Learning to Predict Question Difficulty and Response Time for Enhanced Test Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rishikesh</namePart>
<namePart type="family">Fulari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Rusert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the details of ourcontribution to the BEA Shared Task on Automated Prediction of Item Difficulty and Response Time. Participants in this collaborativeeffort are tasked with developing models to predict the difficulty and response time of multiplechoice items within the medical domain. Theseitems are sourced from the United States Medical Licensing Examination® (USMLE®), asignificant medical assessment. In order toachieve this, we experimented with two featurization techniques, one using lingusitic features and the other using embeddings generated by BERT fine-tuned over MS-MARCOdataset. Further, we tried several different machine learning models such as Linear Regression, Decision Trees, KNN and Boosting models such as XGBoost and GBDT. We found thatout of all the models we experimented withRandom Forest Regressor trained on Linguisticfeatures gave the least root mean squared error.</abstract>
<identifier type="citekey">fulari-rusert-2024-utilizing</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.45</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>528</start>
<end>533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Utilizing Machine Learning to Predict Question Difficulty and Response Time for Enhanced Test Construction
%A Fulari, Rishikesh
%A Rusert, Jonathan
%Y Kochmar, Ekaterina
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F fulari-rusert-2024-utilizing
%X In this paper, we present the details of ourcontribution to the BEA Shared Task on Automated Prediction of Item Difficulty and Response Time. Participants in this collaborativeeffort are tasked with developing models to predict the difficulty and response time of multiplechoice items within the medical domain. Theseitems are sourced from the United States Medical Licensing Examination® (USMLE®), asignificant medical assessment. In order toachieve this, we experimented with two featurization techniques, one using lingusitic features and the other using embeddings generated by BERT fine-tuned over MS-MARCOdataset. Further, we tried several different machine learning models such as Linear Regression, Decision Trees, KNN and Boosting models such as XGBoost and GBDT. We found thatout of all the models we experimented withRandom Forest Regressor trained on Linguisticfeatures gave the least root mean squared error.
%U https://aclanthology.org/2024.bea-1.45
%P 528-533
Markdown (Informal)
[Utilizing Machine Learning to Predict Question Difficulty and Response Time for Enhanced Test Construction](https://aclanthology.org/2024.bea-1.45) (Fulari & Rusert, BEA 2024)
ACL