Have you ever wondered what meme data looks like?
We answered that question by looking at a dataset based on data from the "WeRateDogs" Twitter account. The dataset was created by Greg Baker, a Computing Science instructor at Simon Fraser University in British Columbia (BC). Greg's inspiration for the dataset came from an article written by journalist David Montgomery.
WeRateDogs shares and scores funny dog pictures. Usually the dogs end up with a score above 10/10 (take a look at the example WeRateDogs tweet to the right). This account is also credited for creating meme language you may know, like "doggo" and "pupper."
We wanted to figure out if the scores given to dog pictures on WeRateDogs were increasing over time.
To do this, we created a scatterplot using the dataset.
- The red line in the scatterplot is the line of best fit. It shows us how the scores changed over time.
- The blue dots in the scatterplot represent tweets with a dog rating (like the WeRateDogs tweet above).
Data source: WeRateDogs Twitter account. Dataset creator: Greg Baker, Computing Science instructor, Simon Fraser University. OLS means "Ordinary Least Squares" which is a method for creating lines of best fit.
Reflect on what you see
Look and interact with the data visualization above. When you mouse-over the scatterplot, you’ll notice more information appears.
Think about the following questions:
- What do you notice about the scatterplot?
- What do you wonder about the data?
Use the fill-in-the-blank prompts to summarize your thoughts:
- “I used to think_______”
- “Now I think_______”
- “I wish I knew more about_______”
- “This data visualization reminds me of_______”
Learn how we visualized the data
Go to our walk-through (in Jupyter notebook format) to see how we used the data science process (formulating a question, gathering the data, analyzing the data with code, and creating the visualizations) to create the scatterplot.