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: JMIR Infodemiology

Date Submitted: May 15, 2024
Date Accepted: Mar 19, 2025

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

Natural Language Processing and Machine Learning Techniques for Analyzing Conversations About Nutritional Yeasts in the United States and France: Retrospective Social Media Listening Study

Jeanne JF, Malaab J, Vanhove A, Mourey F, Talmatkadi M, Schück S

Natural Language Processing and Machine Learning Techniques for Analyzing Conversations About Nutritional Yeasts in the United States and France: Retrospective Social Media Listening Study

JMIR Infodemiology 2025;5:e60528

DOI: 10.2196/60528

PMID: 40311119

PMCID: 12061346

Warning: This is an author submission that is not peer-reviewed or edited.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.

Nutritional Yeasts in Social Media Conversations in the United States and France : Analysis Using Natural Language Processing and Machine Learning Techniques

  • Jean-François Jeanne; 
  • Joelle Malaab; 
  • Antoine Vanhove; 
  • Florian Mourey; 
  • Manissa Talmatkadi; 
  • Stéphane Schück

ABSTRACT

Background:

Nutritional yeast, an inactive form of Saccharomyces cerevisiae, has recently gained popularity as a dietary supplement and healthy ingredient, particularly among those following plant-based diets. Rich in B vitamins, minerals, and protein, it has garnered attention for its health benefits. The rise of social media has further amplified discussions around health and nutrition, allowing for the sharing of information and personal experiences on an unprecedented scale. With this dramatic rise in social media use in recent years, there has been a surge in the application of data mining techniques to analyze the information generated on these platforms. Natural Language Processing (NLP) and Machine Learning (ML) have become invaluable tools in deciphering the vast, unstructured datasets of user-generated content.

Objective:

This study aims to analyze the digital discourse surrounding nutritional yeast, analyzing conversations across platforms in the US and France to uncover topics of discussion expressed by online communities.

Methods:

The present study is retrospective using data from social media geolocated in the US and France, posted by users of nutritional yeast between 2018 and 2023. Cleaning and filtering of data consisted in applying natural language processing methods and specific algorithms. In order to identify the most frequently discussed topics of conversation, Biterm Topic Modeling (BTM) was employed.

Results:

A total of 36,642 posts written by 28,069 users discussing nutritional yeast in 1,039 publicly available online sources were identified (34,292 posts in the US written by 26,154 users on 994 sources and 2,350 in France written by 1,915 users on 45 sources). Twitter emerged as the predominant source in the US (13,487/34,292 [39.6%]) and in France (1,982/2,350 [84.3%]). In the US, the conversation skewed towards nutritional yeast's role as a vital vegan nutrient source (12,345 [36.0%]), with a number of users highlighting its culinary versatility as a natural seasoning (8,093 [23.6%]) and health and skin benefits (6,173 [18.0%]). In France, discussions frequently centered on nutritional yeast’s dietary supplement regimens in various forms (1,177 [50.1%]), touching on its benefits alongside other supplements like castor oil, particularly noted for its effects on nails and hair (928 [39.5%]).

Conclusions:

This Social Media Listening (SML) study revealed that social media users in both the US and France actively engaged in discussions about nutritional yeast, highlighting its recognition for its health benefits and culinary versatility. These insights offer valuable opportunities for tailored marketing strategies that align with distinct market preferences. In the US, emphasizing nutritional yeast's significance in vegan nutrition and culinary innovation could effectively capture the attention of its audience. Conversely, in France, accentuating its holistic health benefits might resonate more strongly, presenting an opportunity to broaden its appeal and engagement within the market.


 Citation

Please cite as:

Jeanne JF, Malaab J, Vanhove A, Mourey F, Talmatkadi M, Schück S

Natural Language Processing and Machine Learning Techniques for Analyzing Conversations About Nutritional Yeasts in the United States and France: Retrospective Social Media Listening Study

JMIR Infodemiology 2025;5:e60528

DOI: 10.2196/60528

PMID: 40311119

PMCID: 12061346

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.