@inproceedings{venkata-ravi-ram-etal-2024-leveraging,
title = "Leveraging Physical and Semantic Features of text item for Difficulty and Response Time Prediction of {USMLE} Questions",
author = "Venkata Ravi Ram, Gummuluri and
Kesanam, Ashinee and
M, Anand Kumar",
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-1.46",
pages = "534--541",
abstract = "This paper presents our system developed for the Shared Task on Automated Prediction of Item Difficulty and Item Response Time for USMLE questions, organized by the Association for Computational Linguistics (ACL) Special Interest Group for building Educational Applications (BEA SIGEDU). The Shared Task, held as a workshop at the North American Chapter of the Association for Computational Linguistics (NAACL) 2024 conference, aimed to advance the state-of-the-art in predicting item characteristics directly from item text, with implications for the fairness and validity of standardized exams. We compared various methods ranging from BERT for regression to Random forest, Gradient Boosting(GB), Linear Regression, Support Vector Regressor (SVR), k-nearest neighbours (KNN) Regressor, MultiLayer Perceptron(MLP) to custom-ANN using BioBERT and Word2Vec embeddings and provided inferences on which performed better. This paper also explains the importance of data augmentation to balance the data in order to get better results. We also proposed five hypotheses regarding factors impacting difficulty and response time for a question and also verified it thereby helping researchers to derive meaningful numerical attributes for accurate prediction. We achieved a RSME score of 0.315 for Difficulty prediction and 26.945 for Response Time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="venkata-ravi-ram-etal-2024-leveraging">
<titleInfo>
<title>Leveraging Physical and Semantic Features of text item for Difficulty and Response Time Prediction of USMLE Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gummuluri</namePart>
<namePart type="family">Venkata Ravi Ram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashinee</namePart>
<namePart type="family">Kesanam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">M</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>This paper presents our system developed for the Shared Task on Automated Prediction of Item Difficulty and Item Response Time for USMLE questions, organized by the Association for Computational Linguistics (ACL) Special Interest Group for building Educational Applications (BEA SIGEDU). The Shared Task, held as a workshop at the North American Chapter of the Association for Computational Linguistics (NAACL) 2024 conference, aimed to advance the state-of-the-art in predicting item characteristics directly from item text, with implications for the fairness and validity of standardized exams. We compared various methods ranging from BERT for regression to Random forest, Gradient Boosting(GB), Linear Regression, Support Vector Regressor (SVR), k-nearest neighbours (KNN) Regressor, MultiLayer Perceptron(MLP) to custom-ANN using BioBERT and Word2Vec embeddings and provided inferences on which performed better. This paper also explains the importance of data augmentation to balance the data in order to get better results. We also proposed five hypotheses regarding factors impacting difficulty and response time for a question and also verified it thereby helping researchers to derive meaningful numerical attributes for accurate prediction. We achieved a RSME score of 0.315 for Difficulty prediction and 26.945 for Response Time.</abstract>
<identifier type="citekey">venkata-ravi-ram-etal-2024-leveraging</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.46</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>534</start>
<end>541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Physical and Semantic Features of text item for Difficulty and Response Time Prediction of USMLE Questions
%A Venkata Ravi Ram, Gummuluri
%A Kesanam, Ashinee
%A M, Anand Kumar
%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 venkata-ravi-ram-etal-2024-leveraging
%X This paper presents our system developed for the Shared Task on Automated Prediction of Item Difficulty and Item Response Time for USMLE questions, organized by the Association for Computational Linguistics (ACL) Special Interest Group for building Educational Applications (BEA SIGEDU). The Shared Task, held as a workshop at the North American Chapter of the Association for Computational Linguistics (NAACL) 2024 conference, aimed to advance the state-of-the-art in predicting item characteristics directly from item text, with implications for the fairness and validity of standardized exams. We compared various methods ranging from BERT for regression to Random forest, Gradient Boosting(GB), Linear Regression, Support Vector Regressor (SVR), k-nearest neighbours (KNN) Regressor, MultiLayer Perceptron(MLP) to custom-ANN using BioBERT and Word2Vec embeddings and provided inferences on which performed better. This paper also explains the importance of data augmentation to balance the data in order to get better results. We also proposed five hypotheses regarding factors impacting difficulty and response time for a question and also verified it thereby helping researchers to derive meaningful numerical attributes for accurate prediction. We achieved a RSME score of 0.315 for Difficulty prediction and 26.945 for Response Time.
%U https://aclanthology.org/2024.bea-1.46
%P 534-541
Markdown (Informal)
[Leveraging Physical and Semantic Features of text item for Difficulty and Response Time Prediction of USMLE Questions](https://aclanthology.org/2024.bea-1.46) (Venkata Ravi Ram et al., BEA 2024)
ACL