Watching the volume of tweets about each of the three GOP candidates yesterday (Ron Paul didn’t really expend an effort), it’s fun to see how Rick Santorum’s tweet volume exploded as it became clear he won Alabama and Mississippi:
He had been running slightly better than Mitt all day and then boom, at the end of the day, tweets about him took off! Poor Newt is stuck in third on twitter, even if he came in second in the polls…
Mid-day today, the Business Insider ran a story suggesting that only 68 people wished Mitt happy birthday on Twitter. If true, that would have been a really striking lack of attention being paid to Mitt by the Twitterverse.
Unfortunately for BI, that number is off. A lot. Here’s a chart plotting the tweets that mention Mitt’s birthday by the hour on the 12th:
When the Business Insider article was posted, the birthday tweets were coming in at a rate of 200 an hour.
One interesting thing is that Mitt’s fans seem to be a procrastinating bunch — the tweets peaked dramatically in the last hour of the day! The total at the end of the day was 3573 birthday tweets, or about 10% of all tweets that mentioned Mitt yesterday.
Oh, happy belated birthday Mitt — it’s still your birthday in California!
The weekend was a busy time for the GOP contenders in real life — and in the Twitterverse. Here’s a breakdown of the mentions each candidate got:
We can see that Mitt has a slight advantage over Rick Santorum, with Newt in third and Ron Paul in distant fourth (I thought the Ron Paul supporters were more vocal than that?)
The top 20 hashtags mentioned in the posts are:
| hashtag | total |
| #tcot | 13,726 |
| #Santorum | 9,384 |
| #Romney | 9,014 |
| #250gas | 8,251 |
| #withNewt | 8,038 |
| #Newt | 6,475 |
| #GOP | 5,560 |
| #teaparty | 4,732 |
| #AL | 4,694 |
| #MS | 4,459 |
| #RonPaul | 4,000 |
| #OBAMA | 2,624 |
| #Gingrich | 2,359 |
| #tlot | 2,166 |
| #MSGOP | 2,086 |
| #ALGop | 2,085 |
| #GOP2012 | 2,009 |
| #KS | 1,983 |
| #p2 | 1,904 |
| #mitt2012 | 1,662 |
#tcot is for “top conservatives on twitter”. Interesting that the #Santorum hash tag gets slightly more play than the #Romney one does!
Here’s a quick analysis of how Mitt Romney is doing in Social Media. I looked at all tweets that mentioned him in a 24-hour period and analyzed the sentiment of the tweet. I then looked at how often Romney was mentioned with other candidates or topics and looked at how that affected his score.
Here’s the results:
| Romney + | Average Sentiment | # Tweets | % Tweets |
| + Ron Paul | 3.38 | 1256 | 4.4% |
| + Santorum | 2.05 | 7629 | 26.9% |
| + Health | 1.59 | 455 | 1.6% |
| All Tweets | 1.06 | 28413 | 100.0% |
| + Obamacare | 0.87 | 271 | 1.0% |
| + Gingrich | 0.62 | 3570 | 12.6% |
| + Tax | 0.18 | 316 | 1.1% |
| + Obama | 0.06 | 1859 | 6.5% |
| + Limbaugh | -0.49 | 115 | 0.4% |
| + Romneycare | -0.61 | 61 | 0.2% |
What’s really interesting is that Santorum is mentioned in over a quarter of the tweets that mention Romney, while New only shows up in less than an eighth. The twitterverse is validating that Mitt’s main challenger is Santorum.
We can also see that when Rush Limbaugh and Romneycare are mentioned, the tweets swing to the negative. Fortunately, there are very few tweets on the subject, and so Mitt can probably rest comfortable that these will not be big issues for him.
Sentiment measures the “feeling” of the tweet, with positive numbers represent happy emotions and negative numbers representing negative emotions. It is a crude measurement, although when averaged over a large number of tweets it becomes insightful.
Rush Limbaugh’s been a pretty hot topic lately, and he’s certainly been a popular discussion on Social Media.
In the 24 hours preceding 8pm EDT (which is midnight, GMT), there’s been roughly 14,000 tweets that include “limbaugh” in the contents, or about 10 a minute. Keep in mind that it’s a weekend, and Rush hasn’t said anything on the air since Friday …
Sentiment
Some breakdown of the sentiment in those tweets (click on chart to enlarge):
52% of the tweets registered as weakly or strongly negative, while 21% registered as weakly or strongly positive. That’s no surprise. No matter who’s talking about Rush or their position, they’re probably not happy about what’s going on. See the comments at the end about limits of sentiment analysis.
Hash Tags
One thing that is always interesting is the use of hash tags (#winning). These are unstructured and uncontrolled, and so it is purely convention that is adopted by Twitter users. For the posts that talk about Rush, the following are the top twenty hashtags:
| HashTag | Count | Percent |
| #p2 | 824 | 9% |
| #limbaugh | 585 | 6% |
| #stoprush | 583 | 6% |
| #tcot | 544 | 6% |
| #boycottrush | 536 | 6% |
| #gop | 262 | 3% |
| #taxpayerfunded | 245 | 3% |
| #flushrush | 232 | 3% |
| #rush | 194 | 2% |
| #snl | 186 | 2% |
| #waronwomen | 182 | 2% |
| #gamechange | 158 | 2% |
| #cnn | 147 | 2% |
| #fem2 | 126 | 1% |
| #tlot | 109 | 1% |
| #topprog | 107 | 1% |
| #ows | 102 | 1% |
| #rushlimbaugh | 94 | 1% |
| #teaparty | 93 | 1% |
| #news | 82 | 1% |
#p2 is the has tag for “Progressives on Twitter”. I was surprised to see it as the most popular tag. #tcot is “Top Conservatives on Twitter”. #fem2 is for feminists. #tlot is “Top Libertarians on Twitter”. What’s interesting is that there is no hashtag which is reaching critical mass. If you were to search for just #stoprush, for example, you would get only a tiny fraction of the posts about Limbaugh.
Twitter Users
There are no clear “top posters”; the most frequent poster is “Miaminonymous”, who appears to just retweet everything, with 131 posts.
The top 25 people mentioned in tweets are:
| User ID | count | % of Mentions |
| @thinkprogress | 480 | 4.0% |
| @hipstermermaid | 320 | 2.7% |
| @limbaugh | 310 | 2.6% |
| @huffingtonpost | 191 | 1.6% |
| @credomobile | 182 | 1.5% |
| @politico | 167 | 1.4% |
| @addthis | 158 | 1.3% |
| @shoq | 153 | 1.3% |
| @superguts | 152 | 1.3% |
| @denisleary | 152 | 1.3% |
| @billmaher | 133 | 1.1% |
| @youtube | 131 | 1.1% |
| @politicususa | 121 | 1.0% |
| @tmorello | 118 | 1.0% |
| @theblaze | 117 | 1.0% |
| @cdibona | 114 | 1.0% |
| @mediaite | 112 | 0.9% |
| @anonyops | 112 | 0.9% |
| @sandrafluke | 102 | 0.9% |
| @thedailybeast | 95 | 0.8% |
| @rushlimbaugh | 92 | 0.8% |
| @krystalball1 | 80 | 0.7% |
| @boingboing | 76 | 0.6% |
| @stoprush | 70 | 0.6% |
| @thedailyedge | 70 | 0.6% |
Interestingly, @limbaugh is not the twitter account Rush uses, @rushlimbaugh is.
Comments
What I make of this
Sentiment analysis is a mechanical assessment of the sentiment, positive or negative, in a tweet. It does not necessarily indicate approval (if positive) or disapproval (if negative) of a particular subject. Consider some contrived examples: “I hate the constant criticism of Rush” is negative, while “I am so happy that Rush is losing advertisers. I love the ones who are quitting” is very positive. The sentiment generally tells us whether the statement is happy and upbeat or negative and downbeat. In large numbers, it is a crude assessment of a topic like I am using it in this post.