KIT | KIT-Bibliothek | Impressum | Datenschutz

Direct-to-Consumer Genetic Testing on Social Media: Topic Modeling and Sentiment Analysis of YouTube Users' Comments

Toussaint, Philipp A. ORCID iD icon 1; Renner, Maximilian 1; Lins, Sebastian 1; Thiebes, Scott ORCID iD icon 1; Sunyaev, Ali 1
1 Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB), Karlsruher Institut für Technologie (KIT)


With direct-to-consumer (DTC) genetic testing enabling self-responsible access to novel information on ancestry, traits, or health, consumers often turn to social media for assistance and discussion. YouTube, the largest social media platform for videos, offers an abundance of DTC genetic testing–related videos. Nevertheless, user discourse in the comments sections of these videos is largely unexplored.

This study aims to address the lack of knowledge concerning user discourse in the comments sections of DTC genetic testing–related videos on YouTube by exploring topics discussed and users' attitudes toward these videos.

We employed a 3-step research approach. First, we collected metadata and comments of the 248 most viewed DTC genetic testing–related videos on YouTube. Second, we conducted topic modeling using word frequency analysis, bigram analysis, and structural topic modeling to identify topics discussed in the comments sections of those videos. Finally, we employed Bing (binary), National Research Council Canada (NRC) emotion, and 9-level sentiment analysis to identify users' attitudes toward these DTC genetic testing–related videos, as expressed in their comments.
... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000150708
Veröffentlicht am 16.09.2022
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 09.2022
Sprache Englisch
Identifikator ISSN: 2564-1891
KITopen-ID: 1000150708
Erschienen in JMIR Infodemiology
Verlag JMIR Publications
Band 2
Heft 2
Seiten Art.-Nr.: e38749
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Vorab online veröffentlicht am 15.09.2022
Schlagwörter direct-to-consumer genetic testing, health information, social media, YouTube, sentiment analysis, topic modeling, content analysis, online health information, user discourse, infodemiology
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page