Subscribe to DSC Newsletter

Which drink is more popular Tea, Coffee, Beer, Wine?

If number of searches were an indicator for gauging the popularity of a drink between Tea, Coffee, Beer and Wine then who wins the contest?

Let us analyze who wins the popularity contest by comparing the number of searches for each of the terms.

Data collection method: Each of the keywords Tea, Coffee, Beer and Wine were used with Google Trends to extract the weekly data and then plotted as below. Year 2015 is excluded due to partial year.

Which drink is gaining popularity and which is losing?

A simple group bar chart trended over years should give a clear picture for the winners and losers.

Image

As can be seen by the super imposed trend lines, Tea and Beer have been gaining increasing popularity whereas Coffee has been on the decline since 2012. The popularity of wine has been on the decline since 2005 and has found a constant level since 2011-2012

Let us flip the dimensions and view them as a stacked area chart

Image

There was a dip in the overall popularity of the four drinks as seen by the trough between years 2007 through 2011.

Now let us aggregate the searches by Quarter and see if there are any cyclical patterns

Image

Interestingly all the peaks on the above chart occur during the 4th quarter of every year.

Let us zoom in and see it by the month.

Image

Interestingly, we see there is a peak for roughly every 1 or 2 months interval.

And finally the searches by each week

Image

Click here to view the interactive popularity of searches between Tea Coffee Beer and wine

Views: 5003

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Nilesh Jethwa on July 13, 2015 at 12:12pm

Thanks Luiz,

  Actually you are right, this data is not exact number of searches but normalized data as you mentioned from Google Trends. I should not have used the term google searches in the article and clarified that it is normalized data.

Comment by Luiz Felipe Freitas on July 13, 2015 at 12:08pm

Nice post, Nilesh.
How did you get the number of searches? I can only see Google Trends data normalized in a 0 to 100 scale.

Comment by Nilesh Jethwa on July 12, 2015 at 6:18am

Max,

Not sure but the spikes could be an after effect of other events. For e.g, let say a popular health blog or magazine published article about benefits of drinking tea, this might lead people into googling more about tea. A beer company increased their marketing on certain days of the month could lead people googling more about beer and so on.. but this is just a wild guess and if there was a way to gather all the press releases and news item corresponding to the spike days we could prove the theory!

Comment by Max Galka on July 11, 2015 at 5:18pm

Interesting analysis. Any theories about why there are the spikes?

Follow Us

Videos

  • Add Videos
  • View All

Resources

© 2017   Data Science Central   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service