Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education

Abstract In the contemporary digital era, upholding research integrity assumes paramount importance for the reputation of higher education institutions and the advancement of science. This study undertakes an interdisciplinary computational investigation into the emotional response of the public to...

Full description

Saved in:
Bibliographic Details
Main Authors: GaoFeng Han, Fang Xia
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-07441-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331758182432768
author GaoFeng Han
Fang Xia
author_facet GaoFeng Han
Fang Xia
author_sort GaoFeng Han
collection DOAJ
description Abstract In the contemporary digital era, upholding research integrity assumes paramount importance for the reputation of higher education institutions and the advancement of science. This study undertakes an interdisciplinary computational investigation into the emotional response of the public to issues pertaining to research integrity, and the subsequent impact on social cognition. The study has constructed a database comprising 58,729 text data points, which have been sourced from social media (Twitter and Weibo), mainstream media reports, academic literature, and public commentary. The application of topic modeling using Latent Dirichlet Allocation (LDA) has enabled the identification of three core topics: “academic integrity issues,” “research governance and institutional transparency,” and “research ethics and accountability. “The implementation of sentiment analysis using the BERT deep learning model has quantified the presence and intensity of emotional reactions. The results obtained demonstrate that the public expresses significant concern and experiences significant negative emotions in relation to academic integrity issues, particularly on social media. Conversely, public discourse on research governance and institutional transparency is predominantly positive, while discussions on research ethics and accountability are more nuanced. These findings underscore the necessity to consider the diversity and dynamics of public emotions when formulating research integrity management strategies, providing novel insights for understanding and addressing the research integrity crisis and emphasizing the importance of sentiment analysis in strategy formulation.
format Article
id doaj-art-b0b12223640d4cd181aeea715eaa3cef
institution Kabale University
issn 3004-9261
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-b0b12223640d4cd181aeea715eaa3cef2025-08-20T03:46:24ZengSpringerDiscover Applied Sciences3004-92612025-07-017812510.1007/s42452-025-07441-zSentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher educationGaoFeng Han0Fang Xia1Anhui Wenda University of Information EngineeringAnhui Wenda University of Information EngineeringAbstract In the contemporary digital era, upholding research integrity assumes paramount importance for the reputation of higher education institutions and the advancement of science. This study undertakes an interdisciplinary computational investigation into the emotional response of the public to issues pertaining to research integrity, and the subsequent impact on social cognition. The study has constructed a database comprising 58,729 text data points, which have been sourced from social media (Twitter and Weibo), mainstream media reports, academic literature, and public commentary. The application of topic modeling using Latent Dirichlet Allocation (LDA) has enabled the identification of three core topics: “academic integrity issues,” “research governance and institutional transparency,” and “research ethics and accountability. “The implementation of sentiment analysis using the BERT deep learning model has quantified the presence and intensity of emotional reactions. The results obtained demonstrate that the public expresses significant concern and experiences significant negative emotions in relation to academic integrity issues, particularly on social media. Conversely, public discourse on research governance and institutional transparency is predominantly positive, while discussions on research ethics and accountability are more nuanced. These findings underscore the necessity to consider the diversity and dynamics of public emotions when formulating research integrity management strategies, providing novel insights for understanding and addressing the research integrity crisis and emphasizing the importance of sentiment analysis in strategy formulation.https://doi.org/10.1007/s42452-025-07441-zSentiment analysisTopic modelingScientific research integrity crisisPublic opinion researchHigher education
spellingShingle GaoFeng Han
Fang Xia
Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
Discover Applied Sciences
Sentiment analysis
Topic modeling
Scientific research integrity crisis
Public opinion research
Higher education
title Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
title_full Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
title_fullStr Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
title_full_unstemmed Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
title_short Sentiment analysis and topic modeling in the context of scientific integrity: implications for teaching and research in higher education
title_sort sentiment analysis and topic modeling in the context of scientific integrity implications for teaching and research in higher education
topic Sentiment analysis
Topic modeling
Scientific research integrity crisis
Public opinion research
Higher education
url https://doi.org/10.1007/s42452-025-07441-z
work_keys_str_mv AT gaofenghan sentimentanalysisandtopicmodelinginthecontextofscientificintegrityimplicationsforteachingandresearchinhighereducation
AT fangxia sentimentanalysisandtopicmodelinginthecontextofscientificintegrityimplicationsforteachingandresearchinhighereducation