Community Spring Cleaning week is here! Join your fellow Maveryx in digging through your old posts and marking comments on them as solved. Learn more here!

Weekly Challenges

Solve the challenge, share your solution and summit the ranks of our Community!

Also available in | Français | Português | Español | 日本語
IDEAS WANTED

Want to get involved? We're always looking for ideas and content for Weekly Challenges.

SUBMIT YOUR IDEA

Challenge #89: Analyzing Social Data

DanielLing
8 - Asteroid

Simple union to combine all files and a small bit of cleaning the data

Spoiler
DanielLing_0-1574952896802.png
ozdogand
8 - Asteroid

summarizing the important tweets by retweeting count..

Spoiler
ozdogand_0-1576526577563.png
JamesCameron
8 - Asteroid

My Effort. Looked at tweets by day by hashtag, tweets by hour and top 10 tweeters

 

Spoiler
JamesCameron_0-1577550157765.png
joshuaburkhow
ACE Emeritus
ACE Emeritus

Trying to avoid the word cloud....

Joshua Burkhow - Alteryx Ace | Global Alteryx Architect @PwC | Blogger @ AlterTricks
Aswin
8 - Asteroid

My solution:

rmassambane
10 - Fireball
 
JonathanW
8 - Asteroid

 

I decided to union and aggregate the data by user, how many related tweets they made, the exposure in terms of followers and retweets, and what hashtags were used. 

 

 

Spoiler
JonathanW_0-1578627047531.png
sonyakasenkramer
8 - Asteroid

I decided to look at some summary statistics and identify highest users and highest used hashtags. There is an average of 3.8 hashtags per tweet, and the most commonly used hashtag is #SDGs. As it turns out, the top 19 users are responsible for 10% of total tweets. If we limit this to original content (filtering out retweets), there are 46 users who generate the top 10% of content. Looking at what gets retweeted, there is one user - ONE! - whose retweets account for 8.5% of all retweets. Next steps for me would be locating these users on a map, and generating some heatmaps for the hashtags.

ZenonH
8 - Asteroid

I kept it pretty simple but aimed to understand the relationship between followers and total tweets. I could probably find some more value in removing outliers, but the outliers were actually what I found interesting. The accounts with the most tweets are in the lowest group of followers, and the opposite is true for the accounts with the most followers (very few tweets).

Spoiler
Zenon_0-1581000025915.png
PeterH23
8 - Asteroid

@JefBus Your solution to challenge #89 is awesome. Great job.