What is Data Mining?  Data mining is basically a process used to extract usable data from any larger set of raw data. Data Mining is primarily used by companies with a strong consumer focus – retail, financial, communication, and marketing organizations, to examine their transactional data and determine price, customer preferences, impact on sales, customer satisfaction and corporate profits. With data mining, a retailer can use point-of-sale records of customer purchases to develop products and promotions to appeal to specific customer segments. It would be impossible to process all this data without automation.

Google trend is a powerful tool used for data mining. It is now-a-days used especially by the data scientist or even a marketing analyst’s inventory. To the marketing department of any company or brand, google trends provides worthy information that could perhaps supersede findings from focus groups, on other metrics like brand health by the region, or brand topics of discussion over a period of time. Once you understand what the consumers for a particular brand are searching for, you can start building your messages around those areas of opportunity and interest. Google Trends can be used to find search terms with growing or decreasing popularity or it can be used to review periodic variations from the past such as seasonality.

It is possible to query up to five words or topics simultaneously in Google Trends.  Results are displayed in a graph that Google calls a “Search Volume Index” graph. Data in the graph can be exported into a .csv file, which can be opened in Excel and other spreadsheet applications.


We will write a custom essay sample on
What financial, communication, and marketing organizations, to examine
Specifically for you for only $16.38 $13.9/page

order now

 Google Trends can be used for objectiveness, availability, continual monitoring, large volume of respondents, timeliness, readability of searching results and internationality. It requires an elaborated strategy based on refined searched phrases and well established temporal, geographical and thematic ranges.


All the results obtained can be presented as separate graphs,

(a) Interest over time, which offers a historical trending,

(b) Regional Behavior, offering on how localized behavior was during that time.


‘R’ is a statistical tool and platform that is used to analyse the data extracted in the form of csv file from the google trends. Simultaneously, one can search five terms using Google Trends. More than five terms are not possible. Also it does not provide data in API format. These issues can be dodged using R especially by using ‘gtrends’ package ( library(gtrendsR) ).

Downloaded .csv file is first required to be accessed through R in such a way-

filename <- "trenddata.csv" We need to loop through each line and start pulling the data and stop pulling as soon as we encounter empty fields. In order to avoid the uncertainties of the final exported format, it is best to not hard code anything. To circumvent all this, we read the data line by line and store it all in one long string stringdata and add a line feed at the end of each line. We then use the read.table with textConnection to parse the stringdata into a flat file and append the dynamic column names pulled from csv file. Google Trends returns the date ranges for each observation, which can be separated by having Start_Date and End_Date column. Boxplots can be created with the help of year column created. We can also plot the data on R with the help of {ggplot2} library's plot method to verify that the data is correct. {ggplot2} has great plotting functions to smooth out noise and amplify trends for better understanding.      


I'm Dora!

Would you like to get a custom essay? How about receiving a customized one?

Click here