@inproceedings{bless-etal-2025-analyzing,
title = "Analyzing the Evolution of Scientific Misconduct Based on the Language of Retracted Papers",
author = "Bless, Christof and
Waldis, Andreas and
Parfenova, Angelina and
A. Rodriguez, Maria and
Marfurt, Andreas",
editor = "Ghosal, Tirthankar and
Mayr, Philipp and
Singh, Amanpreet and
Naik, Aakanksha and
Rehm, Georg and
Freitag, Dayne and
Li, Dan and
Schimmler, Sonja and
De Waard, Anita",
booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sdp-1.6/",
doi = "10.18653/v1/2025.sdp-1.6",
pages = "57--71",
ISBN = "979-8-89176-265-7",
abstract = "Amid rising numbers of organizations producing counterfeit scholarly articles, it is important to quantify the prevalence of scientific misconduct.We assess the feasibility of automated text-based methods to determine the rate of scientific misconduct by analyzing linguistic differences between retracted and non-retracted papers.We find that retracted works show distinct phrase patterns and higher word repetition.Motivated by this, we evaluatetwo misconduct detection methods, a mixture distribution approach and a Transformer-based one.The best models achieve high accuracy ({\ensuremath{>}}0.9 F1) on detection of paper mill articles and automatically generated content, making them viable tools for flagging papers for closer review.We apply the classifiers to more than 300,000 paper abstracts, to quantify misconduct over time and find that our estimation methods accurately reproduce trends observed in the real data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bless-etal-2025-analyzing">
<titleInfo>
<title>Analyzing the Evolution of Scientific Misconduct Based on the Language of Retracted Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Bless</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Waldis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelina</namePart>
<namePart type="family">Parfenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">A. Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Marfurt</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 Fifth Workshop on Scholarly Document Processing (SDP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">De Waard</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">979-8-89176-265-7</identifier>
</relatedItem>
<abstract>Amid rising numbers of organizations producing counterfeit scholarly articles, it is important to quantify the prevalence of scientific misconduct.We assess the feasibility of automated text-based methods to determine the rate of scientific misconduct by analyzing linguistic differences between retracted and non-retracted papers.We find that retracted works show distinct phrase patterns and higher word repetition.Motivated by this, we evaluatetwo misconduct detection methods, a mixture distribution approach and a Transformer-based one.The best models achieve high accuracy (\ensuremath>0.9 F1) on detection of paper mill articles and automatically generated content, making them viable tools for flagging papers for closer review.We apply the classifiers to more than 300,000 paper abstracts, to quantify misconduct over time and find that our estimation methods accurately reproduce trends observed in the real data.</abstract>
<identifier type="citekey">bless-etal-2025-analyzing</identifier>
<identifier type="doi">10.18653/v1/2025.sdp-1.6</identifier>
<location>
<url>https://aclanthology.org/2025.sdp-1.6/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>57</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing the Evolution of Scientific Misconduct Based on the Language of Retracted Papers
%A Bless, Christof
%A Waldis, Andreas
%A Parfenova, Angelina
%A A. Rodriguez, Maria
%A Marfurt, Andreas
%Y Ghosal, Tirthankar
%Y Mayr, Philipp
%Y Singh, Amanpreet
%Y Naik, Aakanksha
%Y Rehm, Georg
%Y Freitag, Dayne
%Y Li, Dan
%Y Schimmler, Sonja
%Y De Waard, Anita
%S Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-265-7
%F bless-etal-2025-analyzing
%X Amid rising numbers of organizations producing counterfeit scholarly articles, it is important to quantify the prevalence of scientific misconduct.We assess the feasibility of automated text-based methods to determine the rate of scientific misconduct by analyzing linguistic differences between retracted and non-retracted papers.We find that retracted works show distinct phrase patterns and higher word repetition.Motivated by this, we evaluatetwo misconduct detection methods, a mixture distribution approach and a Transformer-based one.The best models achieve high accuracy (\ensuremath>0.9 F1) on detection of paper mill articles and automatically generated content, making them viable tools for flagging papers for closer review.We apply the classifiers to more than 300,000 paper abstracts, to quantify misconduct over time and find that our estimation methods accurately reproduce trends observed in the real data.
%R 10.18653/v1/2025.sdp-1.6
%U https://aclanthology.org/2025.sdp-1.6/
%U https://doi.org/10.18653/v1/2025.sdp-1.6
%P 57-71
Markdown (Informal)
[Analyzing the Evolution of Scientific Misconduct Based on the Language of Retracted Papers](https://aclanthology.org/2025.sdp-1.6/) (Bless et al., sdp 2025)
ACL