Coastal risks and statistical learning: Analyzing Google trends with gtrendsR package | R-bloggers

Coastal risks and statistical learning: Analyzing Google trends with gtrendsR package
Posted on March 2, 2021 by Aurelien Callens in R bloggers | 0 Comments
[This article was first published on R on Aurélien Callens , and kindly contributed to R-bloggers ]. (You can report issue about the content on this page here )
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Share Tweet
I am currently in the third year of my PHD and it is time for me to synthesize all the work I have done by writing my thesis. One important step is the introduction which presents the general context and the contributions of my thesis in the research world. For my introduction, I decided to include the Google trend analysis of specific terms related to my PhD subject. For information, the aim of my PhD is to demonstrate the potential contributions of statistical learning methods in the study of coastal risk.
In this short post, we are going to use the R package gtrendsR to analyze the trends of specific words related to statistical learning such as “machine learning” or “data science” and also related to coastal risks: “coastal flood”, “storm surge”.
Analysis of specific terms for the whole world
In this first section, we are going to analyze the interest over time for several terms in the whole world. The gtrends function extracts the “hits” variable for a given term. This variable is a normalized measure of the interest made by Google Trends. The number of search is normalized by geography and time range, then the resulting numbers are scaled on a range of 0 to 100 based on a topic’s proportion to all searches on all topics. All the details are given in the support of Google Trends ( here ).
We can look at the interest over time for “data science”, “deep learning” and “machine learning”:
library(tidyverse) library(gtrendsR) words_stats