Quantifying time-dependent Media Agenda and public opinion by topic modeling

Abstract

The mass media plays a fundamental role in the formation of public opinion, either by defining the topics of discussion or by making an emphasis on certain issues. Directly or indirectly, people get informed by consuming news from the media. Naturally, two questions appear: What are the dynamics of the agenda and how the people become interested in their different topics? These questions cannot be answered without proper quantitative measures of agenda dynamics and public attention. In this work we study the agenda of newspapers in comparison with public interests by performing topic detection over the news. We define Media Agenda as the distribution of topic's coverage by the newspapers and Public Agenda as the distribution of public interest in the same topic space. We measure agenda diversity as a function of time using the Shannon entropy and differences between agendas using the Jensen-Shannon distance. We found that the Public Agenda is less diverse than the Media Agenda, especially when there is a very attractive topic and the audience naturally focuses only on this one. Using the same methodology we detect coverage bias in newspapers. Finally, it was possible to identify a complex agenda-setting dynamics within a given topic where the least sold newspaper triggered a public debate via a positive feedback mechanism with social networks discussions which install the issue in the Media Agenda.

Can Interactive Dual Fields of Information Explain the Prevalent Phenomena

“…Our calculation with the assumption of burst gives results much better than the case without any bursts (see Figure 5(a)). This strongly indicates that the feature of <ξ> at around t≈t max is determined under the direct influence of the explosive transmission of information in the cyber world with the η, t 0 and a 0 of their respective values near the threshold given by (27).…”

“…So far as we discuss only in the region of t 0 <20, the condition for the burst to occur corresponds to the following inequality region for our case of calculation; The tipping point, that is the threshold for the beginning of burst, has been pointed out to widely exist in the region of economic and commercial activities together with the region of natural sciences [28]. The above equation (27) corresponds to the tipping point of our case. Under the condition of η and t 0 in the region where they do not exceed the tipping point, the oblivion occurs too fast for the <ξ> to grow remarkably even if the Ψ 1 becomes large.…”

“…When the a 0 is relatively stronger than the t 0 (that is the upper right part in Figure 8), the above unequal equation is satisfied so that the <ξ> becomes large with the increase of Ψ 1 . When the a 0 becomes much larger than the a thresh given by (27), on the other hand, the <ξ> grows to continuously hold a large value for a long time so that its feature may no more be called as a burst. Our calculation with the assumption of burst gives results much better than the case without any bursts (see Figure 5(a)).…”

“…It is well known at present that the SNS communication between a large number of general public induces the temporary or periodic occurrence of a strong cyber field in the cyber world as a result of the intensive exchange of vast amount of information between people at one time [22,23] In the cyber world, the expansion of information is also known to occur rapidly throughout a quite wide region of society by the network communication even by little supply of information [24][25][26][27][28]. In this case the awareness and attitude of the public are apt to be assembled toward a certain biased direction.…”

Topic Analysis of Traditional and Social Media News Coverage of the Early COVID-19 Pandemic and Implications for Public Health Communication

“…Beyond health crises, topic modeling has been applied to social media and traditional media coverage of various phenomena; for example, to derive the most interesting topics in a given era and time using content from historical newspapers 24 , to conduct discourse analysis on how Muslims are portrayed on social media vis-à-vis traditional media 25 , and to quantitatively describe differences in public opinion and mass media opinion 26 . These studies underscore the utility of topic modeling for automating topic discovery in large data sets which are increasingly the norm.…”