Abstract: COVID-19 pandemic has made tremendous impact on the whole world, both the
real world and the media atmosphere. Our research conducted a text analysis
using LDA topic model. We first scraped 1127 articles and 5563 comments on SCMP
covering COVID-19 from Jan 20 to May 19, then we trained the LDA model and
tuned parameters based on the $C_v$ coherence as the model evaluation method.
With the optimal model, dominant topics, representative documents of each topic
and the inconsistency between articles and comments are analyzed. Some factors
of the inconsistency are discussed at last.