Abstract—The presentation of science in the mass media is
one of the most important questions facing social scientists who
analyze science. In this paper, we use topic modeling technique
to identify the scientific topic areas or themes most prevalent in
mass media over a given period of time to inform the discussion
about civic scientific literacy (CSL). Google Trends is used to
analyze public interests in science. The two sets of data are
compared and correlated to identify any relationship between
traditional media and the new media in impacting public
perceptions of new scientific developments and public’s general
understanding of science.
Index Terms—Data mining, civic science literacy, public
interest in science, mass media.
Ying Sun is with University at Buffalo, USA (email: sun3@buffalo.edu).
Cite: Ying Sun, "A Text Mining Approach to Analyze Public Media Science Coverage and Public Interest in Science," International Journal of Machine Learning and Computing vol. 4, no. 6, pp. 496-500, 2014.