Introduction

Hello everyone! I have prepared an analysis on two companies who have been heavily used during this quarantine. DoorDash and UberEats employ independent contractors to drive to restaurants and deliver orders to customers’ doorsteps. I thought this would be a perfect time to gather some insights on their Twitter accounts.

This was made possible by pulling tweets sent out by @DoorDash and @UberEats. The files I worked with contained the most recent 150 tweets sent out by DoorDash and UberEats as of 3:30 PM on 4/30.

I hope you enjoy :)

Loading Packages

A few R packages were necessary for this analysis. Tidyverse is a versatile package used to read in and wrangle the data, as well as visualize it. Stringr is a package used to manipulate obsrevations that are character-based, like the tweets themselves. HTTPUV and RTWEET authorize access to pull tweets into R.

## -- Attaching packages ---------------------------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.2.1     v purrr   0.3.3
## v tibble  2.1.3     v dplyr   0.8.3
## v tidyr   1.0.0     v stringr 1.4.0
## v readr   1.3.1     v forcats 0.4.0
## -- Conflicts ------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
## Warning: package 'httpuv' was built under R version 3.6.3
## Warning: package 'rtweet' was built under R version 3.6.3
## 
## Attaching package: 'rtweet'
## The following object is masked from 'package:purrr':
## 
##     flatten

Loading Data

Alright, let’s pull these datasets. We are loading the data directly from OneDrive using read_csv()

## Parsed with column specification:
## cols(
##   .default = col_character(),
##   created_at = col_datetime(format = ""),
##   display_text_width = col_double(),
##   is_quote = col_logical(),
##   is_retweet = col_logical(),
##   favorite_count = col_double(),
##   retweet_count = col_double(),
##   quote_count = col_logical(),
##   reply_count = col_logical(),
##   symbols = col_logical(),
##   ext_media_type = col_logical(),
##   quoted_created_at = col_datetime(format = ""),
##   quoted_favorite_count = col_double(),
##   quoted_retweet_count = col_double(),
##   quoted_followers_count = col_double(),
##   quoted_friends_count = col_double(),
##   quoted_statuses_count = col_double(),
##   quoted_verified = col_logical(),
##   retweet_created_at = col_datetime(format = ""),
##   retweet_favorite_count = col_double(),
##   retweet_retweet_count = col_double()
##   # ... with 19 more columns
## )
## See spec(...) for full column specifications.
## Parsed with column specification:
## cols(
##   .default = col_character(),
##   created_at = col_datetime(format = ""),
##   display_text_width = col_double(),
##   is_quote = col_logical(),
##   is_retweet = col_logical(),
##   favorite_count = col_double(),
##   retweet_count = col_double(),
##   quote_count = col_logical(),
##   reply_count = col_logical(),
##   symbols = col_logical(),
##   ext_media_type = col_logical(),
##   quoted_created_at = col_datetime(format = ""),
##   quoted_favorite_count = col_double(),
##   quoted_retweet_count = col_double(),
##   quoted_followers_count = col_double(),
##   quoted_friends_count = col_double(),
##   quoted_statuses_count = col_double(),
##   quoted_verified = col_logical(),
##   retweet_created_at = col_datetime(format = ""),
##   retweet_favorite_count = col_double(),
##   retweet_retweet_count = col_double()
##   # ... with 20 more columns
## )
## See spec(...) for full column specifications.
## Parsed with column specification:
## cols(
##   .default = col_character(),
##   created_at = col_datetime(format = ""),
##   display_text_width = col_double(),
##   is_quote = col_logical(),
##   is_retweet = col_logical(),
##   favorite_count = col_double(),
##   retweet_count = col_double(),
##   quote_count = col_logical(),
##   reply_count = col_logical(),
##   symbols = col_logical(),
##   ext_media_type = col_logical(),
##   quoted_created_at = col_datetime(format = ""),
##   quoted_favorite_count = col_double(),
##   quoted_retweet_count = col_double(),
##   quoted_followers_count = col_double(),
##   quoted_friends_count = col_double(),
##   quoted_statuses_count = col_double(),
##   quoted_verified = col_logical(),
##   retweet_created_at = col_datetime(format = ""),
##   retweet_favorite_count = col_double(),
##   retweet_retweet_count = col_double()
##   # ... with 19 more columns
## )
## See spec(...) for full column specifications.

First Insight: Whose Twitter account gets more buzz?

I am interested to see who averages more retweets and likes on Twitter.

As we can see: DoorDash averages more likes on these tweets (6.01), while UberEats averages 5.67 likes. Not much of a difference in my opinion. UberEats averages more retweets (2.61), while DoorDash averages 0.67 retweets. I think that is a relevant difference.

Insight 2: What applications do they typically use in sending out Tweets?

I am interested to see if they use a variety of applications to send out tweets. Whether that would be from a computer, or an iPhone, or perhaps an Android. Let’s take a look.

UberEats appears to favor two options in sending out tweets. 72 were sent out using the “Sprinklr” app, and 70 were sent out from the Web app on a computer. That accounts for 95% of their Tweets in the dataset.

DoorDash also appears to favor two options. 90 were sent out from the Web app on a computer, and 57 were sent out using the “TweetDeck” application. That accounts for 98% of their Tweets in the dataset.

This is nice to know because apps used by successful companies like these would be neat to check out.

Insight 3: How do they handle customer service?

Social media is a common place for customers to voice frustrations with companies. DoorDash and UberEats receive complaints daily. How responsive are they?

I conducted a deep scan of key words and phrases used by their accounts. DoorDash typically responded to complaints by mentioning their “support team”. UberEats on the other hand, typically responded to complaints with “help” or “ajuda”. This is where I learned that “ajuda” means help in Portuguese.

## # A tibble: 1 x 1
##   total
##   <int>
## 1    14
## # A tibble: 1 x 1
##   total
##   <int>
## 1    38
## # A tibble: 1 x 1
##   total
##   <int>
## 1    16

Here is a short list of my findings: 14 of the 150 tweets from DoorDash mentioned “support team” (9.3%).

38 of the 150 tweets from UberEats mentioned “ajuda” (25.3%).

An additional 16 tweets from UberEats mentioned “help” (10.7%).

We can gather one of two insights from this. UberEats is more responsive to complaints, or UberEats generates more complaints.

Conclusion

This begs the question you might ask yourself before choosing which service to use. Do you choose UberEats because of their active customer service team? Or do you choose DoorDash because they have fewer problems? I’ll leave that up to you to decide.