Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Apr 30, 2025)
Date Submitted: Dec 22, 2024
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Herbal medicine vs. cervical cancer screening: Comparing themes between English and Korean YouTube comments on cervical cancer
ABSTRACT
Background:
Health information and communication could be crucial global strategies to accelerate cervical cancer elimination because reliable and helpful health information on cervical cancer can support health decision-making. Online video platforms, such as YouTube, are comparatively new health information sources in contemporary society and can promptly convey online health information through videos and comments. However, there is a research gap regarding health information within comments, which is another way of conveying health information on YouTube platforms.
Objective:
This study aims to examine the health information landscape of comments on YouTube videos on cervical cancer. Furthermore, the frequent expressions and dominant themes in English and Korean comments were compared using natural language processing.
Methods:
We used natural language processing based on bigrams to examine the frequent bigrams and themes in comments on YouTube videos of patients with cervical cancer. This study identified 123 videos (English: n = 61, Korean: n = 62) on cervical cancer with high relevance in YouTube. It included 3,121 comments (1,732 in English and 1,389 in Korean), with 20,141 bigrams (consecutive word pairs) (8,891 in English and 11,250 in Korean) after pre-processing and tokenization. This study found seven themes in the English comments and ten in the Korean comments by applying the walktrap algorithm for community detection.
Results:
The results revealed that frequent bigrams and dominant themes differed between the English and Korean comments on YouTube videos on cervical cancer. The most frequent bigram in English comments was "herb(al)-medicine," while in Korean comments, it was “cervical cancer-screening.” Four of the seven themes in the English comments were related to promoting doctors' offices or YouTube channels, whereas the dominant theme in the Korean comments were concerns and questions about cervical cancer.
Conclusions:
This study provided evidence by comparing the results between English and Korean comments to overcome the Tower of Babel bias in infodemiology. Furthermore, it attempted to make a feasible multilanguage comparison of natural language processing for health communication research. As a source of health or cancer information, YouTube comments have characteristics multilingual, multicultural, and international. Therefore, language comparison using natural language processing could be a novel way to examine the infodemiology within YouTube comments.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.