We are excited to announce GetGlue’s first blog post solely focused on analyzing all of the data we’ve collected so far. We hope to be the go-to source for cool and interesting insights into social entertainment (think OkCupid style of charts). Our first post will be focused on last week’s movie data.
We’ve decided to start things off with rankings of the top movies, which we’ll continue to do every week.
Unsurprisingly, The Hangover: Part II, which opened last weekend, takes the top spot in our first top movies chart. We had been tracking the enormous amount of GetGlue user interactions with the movie before it released and could tell that it was going to fair well in the box office.
Now let’s take a look at how well GetGlue check-ins corresponded with box office revenue.
As you can see, there is a clear correlation between check-ins and box office dollars. The gray dotted line represents the average relationship between the two. For the mathematically inclined, to get the trend line we performed a simple linear regression and obtained an R2 value of 0.95. In other words, 95% of the variance in the data was explained by the trend line. A perfect correlation would have an R2 value of 1.0. The biggest deviation from the trend comes from Something Borrowed, which was expected to have a much higher weekend gross. One possible reason for variance in the data is the availability and promotion of stickers, which we realize can influence the amount of check-ins.
So now that we know that the number of check-ins to a movie pretty much corresponds to the revenue it’ll receive in theaters, can we predict how well a movie is going to do? In this next chart, we plotted the number of pre-release interactions (combination of visits, check-ins, likes, etc) of movies against their opening box office revenues.
This chart shows that GetGlue is a fairly good predictor of how well a movie is going to do. Again, we included the trend line. This time we obtained an R2 value of 0.85. The biggest deviation from the trend came from Fast Five, which based on the pre-release interactions was expected to gross much lower in its opening weekend than it actually did. Another thing to note is that we did not normalize the data for user growth or feature changes to the site, which also would have affected the number of interactions.
The last chart shows the number of movie check-ins by weekday.
As expected, the weekend grabs the lion’s share of check-ins, but surprisingly Sunday is the biggest movie day, not Friday or Saturday. One thing we didn’t do, however, is show where the check-ins are coming from. We expect most of the check-ins to come from in-theater viewings, but there are also check-ins coming from DVD and internet viewings.
Stay tuned for our next blog post, where we’ll delve into TV.