Improving topic modeling performance on social media through semantic relationships within biomedical terminology
PLOS ONE · 21.02.2025 · 20 (2) · e0318702
DOI: 10.1371/journal.pone.0318702 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 21.02.2025. Verfasst von Yi Xin und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Vanderbilt University, Nashville, Tennessee, United States of America. Hauptthemen laut MEDLINE: Social Media, Semantics, Terminology as Topic. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NLM NIH HHS, NHGRI NIH HHS.
Abstract (Originalsprache)
Topic modeling utilizes unsupervised machine learning to detect underlying themes within texts and has been deployed routinely to analyze social media for insights into healthcare issues. However, the inherent messiness of social media hinders the full realization of this technique’s potential. As such, we hypothesized that restricting medical concepts in social media texts to specific related semantic types and applying topic modeling to these concepts could be a feasible approach to overcome the challenge of traditional topic modeling for social media texts. Therefore, we developed a semantic-type-based topic modeling pipeline to discover self-reported health-related topics. This pipeline integrated semantic type information and Systematized Medical Nomenclature for Medicine (SNOMED) precoordinated expressions into a traditional topic modeling approach to enhance effectiveness in clustering meaningful, distinct topics. Using social media texts regarding statins for illustration, we evaluated the efficacy of this new approach and validated a newly identified topic using real-world clinical data. Based on expert evaluations, this approach resulted in more novel, distinguishable, and meaningful health-related topics compared to traditional topic modeling. In addition, our electronic health record validation for a newly identified topic in two real-world clinical databases indicated that statin users had a higher prevalence of depression or anxiety compared to matched non-users. Our results indicate that this new topic modeling pipeline can improve the extraction of themes from noisy online discussions, thereby contributing to deeper insights for healthcare research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, Vanderbilt University, Nashville, Tennessee, United States of America.
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
- Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
ORCID-Profile: Yi Xin, Monika E Grabowska, V Eric Kerchberger, Alyson L Dickson, Wei-Qi Wei
Förderung
- NIGMS NIH HHS
- NLM NIH HHS
- NHGRI NIH HHS
- NHLBI NIH HHS
- NIAID NIH HHS
- NIA NIH HHS
- Foundation for the National Institutes of Health
Zitieren
APA
Xin, Y., Grabowska, M. E., Gangireddy, S., Krantz, M. S., Kerchberger, V. E., Dickson, A. L., Feng, Q., Yin, Z., & Wei, W. Q. (2025). Improving topic modeling performance on social media through semantic relationships within biomedical terminology. PLOS ONE, 20(2), e0318702. https://doi.org/10.1371/journal.pone.0318702
Vancouver
Xin Y, Grabowska ME, Gangireddy S, Krantz MS, Kerchberger VE, Dickson AL, et al. Improving topic modeling performance on social media through semantic relationships within biomedical terminology. PLOS ONE. 2025;20(2):e0318702. doi:10.1371/journal.pone.0318702
BibTeX
@article{Xin2025,
author = {Xin, Yi and Grabowska, Monika E and Gangireddy, Srushti and Krantz, Matthew S and Kerchberger, V Eric and Dickson, Alyson L and Feng, Qiping and Yin, Zhijun and Wei, Wei-Qi},
title = {Improving topic modeling performance on social media through semantic relationships within biomedical terminology},
journal = {PLOS ONE},
year = {2025},
volume = {20},
number = {2},
pages = {e0318702},
doi = {10.1371/journal.pone.0318702}
}
EUVIMED