Fig 1.
Time series showing the number of #BlackLivesMatter and #AllLivesMatter tweets from Twitter’s 10% Gardenhose sample.
The plot is annotated with several major events pertaining to the hashtags. Shaded regions indicate one-week periods where use of both #BlackLivesMatter and #AllLivesMatter peaked in frequency. These are the periods we focus on in the present study.
Fig 2.
Jensen-Shannon divergence word shift graph for the week following the non-indictment of Darren Wilson.
All word contributions are positive percentages of the total divergence, where bars to the left and right indicate the word was more common in #AllLivesMatter and #BlackLivesMatter respectively. Shading indicate the Shannon index (in bits) of tweets containing the given word. Lighter shading indicates the contribution is due to one or several popular retweets. Darker shading indicates the contribution is due to the word being used throughout many different tweets.
Fig 3.
Jensen-Shannon divergence word shift graph for the week following the death of two NYPD police officers.
See main text and the caption of Fig 2 for an explanation of the word shift graphs. The diversity of ‘merica’ appears to be high, however it is almost exclusively used in one popular retweet. This high diversity is due to alterations of the original retweet that added comments. Since these less popular, modified retweets contain different language from one another, and the original tweet has no other words used in it, the diversity surrounding ‘merica’ is artificially elevated. So, although uncommon, the diversity measure may be difficult to interpret in the case of popular one-word retweets.
Fig 4.
Jensen-Shannon divergence word shift graph for the week following the 2015 Grammy Awards and the Chapel Hill shooting.
See main text and the caption of Fig 2 for an explanation of the word shift graphs. This period reflects a time in which usage of both #BlackLivesMatter and #AllLivesMatter diverged due to focus on different events. Discussion within #AllLivesMatter reflects the Chapel Hill shooting, while discussion within #BlackLivesMatter reflects the 2015 Grammy Awards and the performances of Beyonce and John Legend that alluded to Black Lives Matter.
Fig 5.
Jensen-Shannon divergence word shift graph for the week encapsulating the peak of the Baltimore protests surrounding the death of Freddie Gray.
See main text and the caption of Fig 2 for an explanation of the word shift graphs. In this period, the conservative alignment of #AllLivesMatter is particularly prevalent, as seen in the hashtags #tcot (Top Conservatives on Twitter), #ccot (Conservative Christians on Twitter), and #rednationrising.
Fig 6.
#BlackLivesMatter topic network for the week following the death of two NYPD officers.
Fig 7.
#AllLivesMatter topic network for the week following the death of two NYPD officers.
Table 1.
Summary statistics for topic networks created from the full hashtag networks using the disparity filter at the significance level α = 0.03 [52].
Table 2.
The top 10 hashtags in the topic networks as determined by random walk betweeness centrality for each time period.
Some #AllLivesMatter topic networks have less than 10 top nodes due to the relatively small size of the networks.
Fig 8.
Notched box plots depicting the distributions of subsamples for effective lexical and hashtag diversity.
To control for how volume affects the effective diversity of #BlackLivesMatter and #AllLivesMatter, we break the time scale down into months and subsample 2,000 tweets from each hashtag 1,000 times. The notches are small on all the boxes, indicating that the mean diversities are significantly different at the 95% confidence level across all time periods.