@inproceedings{rezayi-etal-2025-automated,
title = "Automated Scoring of Communication Skills in Physician-Patient Interaction: Balancing Performance and Scalability",
author = "Rezayi, Saed and
Ha, Le An and
Zhou, Yiyun and
Houriet, Andrew and
D{'}Addario, Angelo and
Baldwin, Peter and
Harik, Polina and
King, Ann and
Yaneva, Victoria",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar 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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.66/",
doi = "10.18653/v1/2025.bea-1.66",
pages = "891--897",
ISBN = "979-8-89176-270-1",
abstract = "This paper presents an automated scoring approach for a formative assessment tool aimed at helping learner physicians enhance their communication skills through simulated patient interactions. The system evaluates transcribed learner responses by detecting key communicative behaviors, such as acknowledgment, empathy, and clarity. Built on an adapted version of the ACTA scoring framework, the model achieves a mean binary F1 score of 0.94 across 8 clinical scenarios. A central contribution of this work is the investigation of how to balance scoring accuracy with scalability. We demonstrate that synthetic training data offers a promising path toward reducing reliance on large, annotated datasets{---}making automated scoring more accurate and scalable."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezayi-etal-2025-automated">
<titleInfo>
<title>Automated Scoring of Communication Skills in Physician-Patient Interaction: Balancing Performance and Scalability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saed</namePart>
<namePart type="family">Rezayi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">An</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Houriet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="family">D’Addario</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Polina</namePart>
<namePart type="family">Harik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</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">Bashar</namePart>
<namePart type="family">Alhafni</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">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>This paper presents an automated scoring approach for a formative assessment tool aimed at helping learner physicians enhance their communication skills through simulated patient interactions. The system evaluates transcribed learner responses by detecting key communicative behaviors, such as acknowledgment, empathy, and clarity. Built on an adapted version of the ACTA scoring framework, the model achieves a mean binary F1 score of 0.94 across 8 clinical scenarios. A central contribution of this work is the investigation of how to balance scoring accuracy with scalability. We demonstrate that synthetic training data offers a promising path toward reducing reliance on large, annotated datasets—making automated scoring more accurate and scalable.</abstract>
<identifier type="citekey">rezayi-etal-2025-automated</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.66</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.66/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>891</start>
<end>897</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Scoring of Communication Skills in Physician-Patient Interaction: Balancing Performance and Scalability
%A Rezayi, Saed
%A Ha, Le An
%A Zhou, Yiyun
%A Houriet, Andrew
%A D’Addario, Angelo
%A Baldwin, Peter
%A Harik, Polina
%A King, Ann
%A Yaneva, Victoria
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F rezayi-etal-2025-automated
%X This paper presents an automated scoring approach for a formative assessment tool aimed at helping learner physicians enhance their communication skills through simulated patient interactions. The system evaluates transcribed learner responses by detecting key communicative behaviors, such as acknowledgment, empathy, and clarity. Built on an adapted version of the ACTA scoring framework, the model achieves a mean binary F1 score of 0.94 across 8 clinical scenarios. A central contribution of this work is the investigation of how to balance scoring accuracy with scalability. We demonstrate that synthetic training data offers a promising path toward reducing reliance on large, annotated datasets—making automated scoring more accurate and scalable.
%R 10.18653/v1/2025.bea-1.66
%U https://aclanthology.org/2025.bea-1.66/
%U https://doi.org/10.18653/v1/2025.bea-1.66
%P 891-897
Markdown (Informal)
[Automated Scoring of Communication Skills in Physician-Patient Interaction: Balancing Performance and Scalability](https://aclanthology.org/2025.bea-1.66/) (Rezayi et al., BEA 2025)
ACL
- Saed Rezayi, Le An Ha, Yiyun Zhou, Andrew Houriet, Angelo D’Addario, Peter Baldwin, Polina Harik, Ann King, and Victoria Yaneva. 2025. Automated Scoring of Communication Skills in Physician-Patient Interaction: Balancing Performance and Scalability. In Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025), pages 891–897, Vienna, Austria. Association for Computational Linguistics.