This study is intended to provide diabetes-related health information
during the COVID-19 pandemic, by collecting and analyzing queries
posted in the diabetes-related online community. A total of 9,156 queries
from online community, dated between Dece...
This study is intended to provide diabetes-related health information
during the COVID-19 pandemic, by collecting and analyzing queries
posted in the diabetes-related online community. A total of 9,156 queries
from online community, dated between December 1, 2019, and May 3,
2022, were used in the study. After the collected data were
preprocessed for BERT topic modeling analysis, sentences were
embedded using the Ko-sentence-transformers model. Topics were
extracted after document clustering via UMAP and HDBSCAN algorithms.
Before nouns were extracted, TF-IDF was conducted at an exploratory
level, and topics were extracted using the c-TF-IDF for nouns and
verbs. From the extracted verbs, words with common definitions were
subject to substitution and unification processes, which enabled the
confirmation of multi-frequent verb categories by noun topics.
As per the results of topic modeling nouns, a total of nine topics
were extracted in the following order: dietary management, drug
management, gestational and childhood diabetes, management of diabetic
complications, use and cost of medical treatment, blood glucose
management, exercise treatment, COVID-19 vaccine and complications,
and diabetes in older adults. The top-three verb categories by noun
topics were permission, method, and possibility. Verb categories related
to method were often found in cases of diabetes in older adults (118 queries; 43.7%), blood glucose management (293 queries; 36.5%),
exercise treatment (222 queries; 48.5%), gestational and childhood
diabetes (494 queries; 43.3%), management of diabetic complications
(396 queries; 39.8%), and use and cost of medical treatment (437
queries; 47.2%). Verb categories related to permission were mostly found
in the topics COVID-19 vaccine and complications (99 queries; 32.1%),
dietary management (906 queries; 40.4), and drug management (488
queries; 36.8%).
Through topic modeling analysis, this study identified the topic
categories of diabetes-related queries that were posted in the online
community, thereby pinpointing the level and type of health information in
demand by subjects during the COVID-19 pandemic. The significance of
this study is that it provided baseline data for clinical nurses to deliver
education and management based on information demanded by subjects.