(UPDATE 2.0) Coronavirus (2019-nCoV) – Media Mining Client for Media Monitoring on Pandemic Outbreak

(UPDATE 2.0) Coronavirus (2019-nCoV) – Media Mining Client for Media Monitoring on Pandemic Outbreak

 

This report focuses on the demonstration of some of the capabilities of SAIL LABS Media Mining System (MMS) illustrating the media coverage of the Corona pandemic outbreak.

To access the full report, please contact us through the request form below.

Coronaviruses (CoV) are a large family of viruses that cause illness ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS-CoV) and Severe Acute Respiratory Syndrome (SARS-CoV).

A novel coronavirus (nCoV) is a new strain that has just recently been identified in humans.  The virus has killed at least 8.811 people and has infected more than 218.827 worldwide, mostly in China.*

This report focuses on the demonstration of some of the capabilities of SAIL LABS Media Mining System (MMS) illustrating the media coverage of the corona pandemic outbreak.

2) Some key benefits of SAIL LABS Media Mining System for pandemic outbreaks

  • Allows continuous assessment of media coverage and public opinion in real time
  • Suitable for monitoring punctual and permanent health promotion campaigns
  • Sentiment Analysis of traditional and social media regarding the perceived impact of a disease and government action
  • Event-based surveillance
  • Rapid data collection for fast decisions
  • Timely reporting mechanisms
  • Social media Intelligence
  • Enables to extract data from text or audiovisual sources in languages that the users do not speak thanks to automatic speech recognition and machine translation covering 32 languages
  • Enables situational awareness and situational understanding

3) Mentions of places in conenction with the COVID19

The Globe widget below displays locations mentioned by media with regards to the Coronavirus since the 6th of January 2020. The red circles represent cities and yellow, countries. The highest numbers of mentions in the media are connected to China in first place, followed by the United States, Italy, Iran and Japan (Figure 1).

For in depth correlations with other events of importance, an analyst can advance in his or her analysis associating the data delivered by the MMS with an external source of interest (e.g. data on financial market, number of consultations in hospitals, travel or logistic industry, and others).

In this use case, we compare the data provided by the MMS with the data from the Coronavirus´s situation by the World Health Organization (reports 1-51). In this example, the most frequently mentioned countries in the media might correlate or not with the highest number of confirmed cases.

Moreover, when the need of an external source becomes paramount for analysis, this can be added to the system under request.

Figure 1. World visualization with number of media mentions of countries and cities (6st of January – 18th of March).
Figure 2. *Source: SAIL LABS MMS (08.03.20). **Source: WHO Coronavirus´s situation report number (19.03.20).

4) Media Monitoring and evolution of confirmed cases

The following Trend Graphs show the mentions of different locations with regards to Coronavirus in different time frames (dots), and their correlation with the number of confirmed cases (lines), according to the situation reports of the World Health Organization. An interesting observation is that there is a precursor to actual occurrences in the monitored media.

Figure 3. Source: External data from WHO added to SAIL LABS MMS Visualizations.

 

The graphic above (Figure 3) demonstrates that Wuhan achieves its peak of mentions on the 28th of January. It is possible to note some activity in the media already on the 9th of January, as the virus was for the first time isolated in China on the 7th of January (WHO, situation report – 1).  According to WHO reports, the first case in Europe was confirmed on the 24th of January (France).

 

On the 30th of January the first case was detected in in Italy, and on the 25th of February in Austria (Figure 4). What is interesting to note is the public awareness ahead of the impact in several countries especially tangible in Italy and France well before the virus actually had high impacts. This allows the analysts to have situational understanding of the current media narrative and so enables them to advice those responsible for preparedness or policy of the current level of information the population is exposed to and their reaction to it as well as the impact of this or even possible consequences (such as large movements away from Milan in the days end of February). Also it is worth noting that these spikes have occurred around 8 days before the epidemic broke out strongly in those mentioned places

Figure 4. Source: External data from WHO added to SAIL LABS MMS Visualizations.

To access the full report, please contact us through the request form below.

5) Social Media as a source of information for pandemic outbreaks

Social media is a valuable source of information when it comes to real-time events as it is used for fast communication. The MMS Heat Map provides information about the locations associated with social media posts. It features the Direct Coordinates (coordinates available from posts directly if GPS information is available) and/or the Detected Locations (locations detected in the text, the so-called Named-Entities or NEDs), according to the selection set up by the user.



Figure 7. Social Media Heat Maps. Source: SAIL LABS MMS.

According to the Trend Graphs above (Figure 7), it is possible to see that around the time when the virus was for the first time isolated in China on the 7th of January, a small amount of traditional and social media mentions were already circulating, although mostly outside Europe. The evolution on the Trend Graphs demonstrate the impact of the epidemic outbreak in the number of media mentions along this time frame. These demonstrates how valuable it is to also monitor social media trends around the world, as noticing early unrest in far distant areas might also have an impact on decision-making. It is already known that social media might be an early source of powerful information, including areas where freedom of speech is more limited and the traditional media is under more control of the state.

 

To access the full report, please contact us through the request form below.

6) Brazil and the importance of the Key Opinion Leaders in social media

7) Inconsistencies between official report of cases and social media activity

7.1 Iran

7.2 Turkey

7.3 Syria

 

To access the full report, please contact us through the request form below.