Oct 15, 2014

I had the pleasure of visiting the Facebook data science team last week, and we spent some time chatting about visual communication, something they care as much about as I do. Solomon reported about our conversation in this blog post. One topic is stacked bar charts, which are useful in limited situations, such as when the categorical variable has two or three levels.

Solomon used stacked bars in his fascinating post about how candidates from the two political parties are using Facebook messages in the run-up to mid-term elections. Be sure to read about it here. This is an example of good data journalism in which the outcomes of the analysis are presented simply, hiding the amount of technical work that went into its production.

This stacked bar chart is effective at pointing out the differences in the types of messages being sent out by party:

I do have one question, which is the placement of the 50-percent line. The line is very important to this chart, and I like the way it looks. When the line sits at 50 percent, it implies that the Republican and Democratic candidates were issuing about equal numbers of Facebook messages. If the share of total messages is not 50/50, then the reference line should sit elsewhere.

They later split the races by tosses-up versus uncompetitive, and use confidence intervals to communicate both the expected rate and the uncertainty of the estimate. The uncertainty bars in effect tell readers that there are many more uncompetitive elections than tosses-up.

The choice of the chart form is fine. But it makes me pull out my Tufte book. The data-ink ratio on this chart needs a little help. The gridlines can go. Even the 250 label on the x-axis can go. I might even go with just labelling the midpoints.

Lastly, this next chart is enlightening. Seems like older adults are much more likely to comment and/or like such political messages; men are more likely to comment while women are more likely to like. The small-multiples format helps us grasp the three-way analysis without much suffering.

Re the bottom chart: yes, the small multiples are interesting, but the usability/readability could be improved by a couple of fairly simple adjustments. As your introductory paragraph suggests, one of the key distinctions of interest is whether people COMMENT or LIKE a page. The other two dimensions of interest (gender, age groups) can be grasped by a user fairly easily, but the comment/like distinction is more difficult to determine because the labels are (1) sideways and (2) on the last place that people tend look when reading a page or chart: the right-hand vertical axis. It would help people decipher the chart more easily if the "Comment/Like" labels were on the left vertical axis, and if they were written horizontally. Small quibble - it's still a good chart.

The last chart could be a scatterplot instead. We can link the dots by the order of age and use color for gender.
There would be 12 dots and I think they will show a nice, clear pattern.
The age data is problematic here, because the classes are diffferent in size.

I really don't understand your explanation on the Page Posts by Competition graph. It seems like the scale on the x axis is Average (Number?) of Page post with SE bars and the y axis is just competitive and uncompetitive. This graph does not seem to say anything about the number of competitive or uncompetitive races as you state. It just seems to be saying the the number of comments are higher for toss up races vs uncompetitive races as would be expected.

Or am I missing something?

I love your blog, by the way. I'm working on my data visualization skills and your explanations really help me understand what works and what doesn't work.

@anne - the error bars give you an indication of the sample size.

So smaller error bars - as in the 'Less Competitive' category - tell you that there were more data in that category.

Yes, it is true. I see that facebook become a major media campaign politicians and future leaders in an area. Other social media is not very popular to campaign

Until 2018, 2019, and maybe 2020, Facebook still become to the most major social media sharing about political campaign..

The comments to this entry are closed.