Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jun 2, 2025
Date Accepted: Dec 25, 2025

The final, peer-reviewed published version of this preprint can be found here:

Breast Cancer Screening Knowledge and Sentiments in Singaporean Women: Mixed Methods Study Using Topic Modeling, Sentiment Analysis, and Structured Questionnaire Data

Ho PJ, Lim ZL, Liu J, Mohamed Riza NK, Chew YJ, Lim YY, Tan HL, Goh SA, Oh HB, Chin CH, Kwek SC, Zhang ZP, Ong DLS, Quek ST, Wijerathne S, Iau PTC, Hartman M, Li J

Breast Cancer Screening Knowledge and Sentiments in Singaporean Women: Mixed Methods Study Using Topic Modeling, Sentiment Analysis, and Structured Questionnaire Data

J Med Internet Res 2026;28:e78439

DOI: 10.2196/78439

PMID: 41805687

Breast Cancer Screening Knowledge and Sentiments in Singaporean Women: A Mixed-Methods Study Using Topic Modeling, Sentiment Analysis, and Structured Questionnaire Data

  • Peh Joo Ho; 
  • Zi Lin Lim; 
  • Jenny Liu; 
  • Nur Khaliesah Mohamed Riza; 
  • Ying Jia Chew; 
  • Yi Ying Lim; 
  • Hui Ling Tan; 
  • Su-Ann Goh; 
  • Han Boon Oh; 
  • Chi Hui Chin; 
  • Sing Cheer Kwek; 
  • Zhi Peng Zhang; 
  • Desmond Luan Seng Ong; 
  • Swee Tian Quek; 
  • Sujith Wijerathne; 
  • Philip Tsau Choong Iau; 
  • Mikael Hartman; 
  • Jingmei Li

ABSTRACT

Background:

Routine mammography screening attendance in Singapore is low (<40%), limiting early breast cancer detection. Conventional tools such as focus group discussions, interviews, and Likert-scale surveys have limitations in capturing attitudes.

Objective:

To gain deeper insight into women’s attitudes and perceptions toward routine mammography screening, through the analysis of unstructured text data.

Methods:

We included 4,169 participants (aged 35-59) from the BREAst screening Tailored for HEr (BREATHE) study. Breast cancer awareness was assessed using true/false statements, with participants considered “BC-aware” if scored >80%. Participants were asked if knowledge of screening made them more willing to attend screening (motivated, neutral) and to explain their choice. The association between willingness to attend screening and initial breast cancer awareness was examined using logistic regression. Free-text responses were compared between BC-aware and unaware groups. Biterm topic modelling and sentiment analysis were used to discover latent topics and sentiments within each subgroup.

Results:

Seventy-nine percent were “BC-aware”, and 94% felt more motivated to attend screening. BC-aware participants were more motivated (OR [95% CI]BC-aware vs BC-unaware(ref): 2.67 [2.05 to 3.46], p<0.001) and less likely to find the procedure embarrassing, expensive, inconvenient, or painful. Free-text analysis showed motivated participants focused on early detection benefits, while neutral participants emphasized mammography experiences. In contrast to the motivated group, neutral participants displayed more negative sentiments towards regular screening. Word clouds echoed these patterns.

Conclusions:

This study used a novel approach to examine attitudes and behaviour towards routine screening. Negative mammogram experiences emerged as a key barrier to participation.


 Citation

Please cite as:

Ho PJ, Lim ZL, Liu J, Mohamed Riza NK, Chew YJ, Lim YY, Tan HL, Goh SA, Oh HB, Chin CH, Kwek SC, Zhang ZP, Ong DLS, Quek ST, Wijerathne S, Iau PTC, Hartman M, Li J

Breast Cancer Screening Knowledge and Sentiments in Singaporean Women: Mixed Methods Study Using Topic Modeling, Sentiment Analysis, and Structured Questionnaire Data

J Med Internet Res 2026;28:e78439

DOI: 10.2196/78439

PMID: 41805687

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.