Broadband penetration vs. Obama vote

I was reading how the Obama campaign talked about the "net roots." How about we plot internet broadband penetration vs. Obama's percentage of the vote and well by state:



I added a perfect fit line that shows where the states would be if the two measures were perfectly correlated. The red linear trend line showed what the states actually turned to cluster around: it was not parallel, i.e., only a so-so correlation. I know that I probably should have used normalized numbers for both measures but I ran out of time. Still, I think this was very intriguing: it did seem to correlate not too badly. I identified the outliers on the Democratic side: DC (always heavily Democratic), Vermont (Socialist senator!) and Hawaii (Obama's childhood home state); on the Republican side: Alaska (Palin's home state), Utah (heavily Mormon) and Wyoming (Cheney's home state). These were expected. Look then for the states that displayed the best correlation between broadband penetration and Obama vote (from left to right): West Virginia, Mississippi, South Carolina, Montana, Missouri—still not officially settled!—, North Carolina, Ohio, Minnesota, Virginia, Oregon and New Jersey. They were a mixture of "toss-up" states (MO, NC, OH, VA) and "blue" (MN, OR, NJ) or "red" states (WV, MS, SC, MT). Note that the blue states were at the high end of the scale (to the right), the red ones at the bottom (to the left) and the toss-ups in the centre. Delaware (Biden's home state), Illinois (Obama's other home state) and Arizona (McCain's home state) ended up on their partisan side but not in an outspoken way.

I tried a second approach using the Obama minus McCain percentage of the vote:



The perfect fit line ran parallel to the blue trend line: a good correlation this time around. Overall, the distribution of the states was very similar to the previous graph. Conclusion: the higher the broadband penetration, the higher the Democratic vote seemed to be. I guess that does confirm some of the analyses of the election I read. Nevertheless, I have to caution to read too much in these graphs, the more since my grasp of this type of statistics is a bit shaky...

By the way, a "classic" face-off of broadband vs. Obama yielded this interesting result:



Broadband has been popular with Googlers for a long time. Obama was more a recent phenomenon that ended up overtaking broadband in aggregate.

Update 11-14-08: My statistical skills were indeed lacking. Look at the comments for corrections and the like.

John McCain vs. Barack Obama (Election Night Speeches)

Last night, US president-elect Obama gave a victory speech in Chicago in front of a 100,000+ joyous crowd in Grant Park; McCain conceded in Phoenix on the back lawn of a luxury hotel with an at times bitter audience of 7,000. I followed the same methodology for their speeches as with the first, second and third presidential debates and the vice presidential debate; you can find some more detail about my methodology there. So let's start with the bubble graph displaying length of words, sentences as well as number of words:



Unsurprisingly, McCain kept it short in every way I measured. Using Wordle, I made all-inclusive word clouds.

John McCain





Barack Obama



McCain mentioned Obama quite a few times, he was after all conceding defeat. As the winner, Obama was looking more ahead, only mentioning his opponent in passing. McCain had many dominant words, esp. campaign, country, thank and variants on America. Obama was more focused with America, tonight, people and new standing out only.

Obama vs. McCain vs. Palin vs. Biden in the Last Month: Details

A post on the FiveThirtyEight.com blog (Google Traffic Suggests McCain Not Grabbing Voters' Attention) today looked up the Google-popularity of McCain and Obama, using Google Trends. The author wondered about the context of the Obama searches: maybe they were people looking for dirt, i.e., "proof" for the many slanderous allegations? Well, there's a way to a least get an idea of that and more: use Google Insights for Search
—my standard analysis tool.



I also included Palin and Biden to complete the presidential election picture. This graph showed again that Obama has been in the lead for the past month. Palin at times peaked higher than Obama and was most of the time more Google-popular than McCain. Except for his vice presidential debate, Biden led a quiet life out of the big spotlight ;-) Now, let's have a look at the details underlying this graph. First, the geographical differences for the candidates; then the context of the candidates' searches.
I started with Obama's regional search patterns:



The following states were the most interested in him: New Mexico, Colorado and North Carolina. The remainder of the top 10 were also seen as battleground states at one time or another, except of course the District of Columbia and Illinois. How was McCain's list?



Ohio, New Mexico and Pennsylvania led the top 10. Further down though, the battleground states didn't dominate with McCain: only three more. Furthermore, his home state Arizona wasn't in the top 10. Interesting... Next: Palin.



Her top three was made up of Alaska, Vermont and Oregon: all non-battleground states. In the remaining seven there was similarly only one state that could be called a battleground (Colorado). This seemed to point at her appeal being more as a celebrity than in the strict context of the campaign. Finally, where was Biden the most searched?



Delaware, Vermont and Alaska led his list. Maybe a lot of people in Alaska were trying to find out what their governor was up against? The only battleground state the Democratic VP candidate was Google-popular: Pennsylvania. he has been campaigning a lot there if I'm not mistaken.

In conclusion, Obama was the one who evoked he highest interest in the battleground states. That being said, in what light was he being searched: positive or negative? Here's the list of most common search terms for Obama:



The top 10 was basically positive with searches focusing on the race, polls and debates. The second list on the right shows the "rising" searches, i.e., searches that saw the fastest growth spurt but were not in the top 10. Nos. 4-8 were rather negative: (false) accusations of him not being qualified in a legal sense to run, the ACORN voter registration fraud allegations, the tenuous connection with a '60s terrorist. All in all, the rising searches displayed a half positive (Powell, ...), half negative interest. Republican mud-slinging had only a limited impact. On to his opponent, McCain:



His top 10 was similar to Obama: positive. The "risers" were also all basically positive. Next, Palin.



Five of her top 10 searches related to Tina Fey's parody of her on Saturday Night Live. I don't think that can be classified unequivocally as positive. The other five were the typical contexts of the campaign, debate, etc. When it came to rising searches, about half of them to had a connection with SNL. Last but not least ;-) , Senator Biden...



A basic, positive top 10 was accompanied by as much as four rising searches about the SNL sketch parodying the VP debate.

Clearly, the searches were mostly about the campaign except for some following up on accusations against Obama and regarding the Palin SNL saga.

Three-day average interest in Obama and McCain by state and top cities

Yesterday, I was conducting an experiment that took a while to complete. That's why I skipped a day. I was looking into Google searches for Obama and McCain over the last three days available (10-16 through 10-18) on Google Insights for Search, and well split up by US state plus the District of Columbia. I experimented with different analyses and this is what I came up with:



The states are displayed alphabetically. Let's give them ranked according to Obama share too:



The interest in Obama was the highest in Missouri, then came Nevada, Wyoming, and so on. The lowest Google-popularity for Obama or highest one for McCain in this three-day time span was in Delaware, then North Dakota and Massachusetts. So did this mean that Obama was ahead in Missouri but behind in Delaware, opinion-poll-wise? Of course not. I think these graphs show a snapshot of the attention being paid to the two main presidential candidates, e.g., on October 18, Obama held a 100,000-people rally in St. Louis, MO. What is measured is more something like the "buzz," how much the candidates are being talked about. You might say that it reflected the cumulative effect of campaigning: TV, radio, robocalls, appearances, mail, etc.

The analysis also yielded the top cities where people were looking for information on the candidates during the sam time span:





This confirmed my theory that the huge St. Louis Obama rally spiked Missouri: St. Louis was no. 1 for Obama. Second came Houston and then Tampa. McCain had the highest score in Boston, then San Francisco and Seattle. It seemed to me that these had more to do with Obama being so far ahead that people weren't thinking about the candidates much anymore.

John McCain vs. Barack Obama vs. Bob Schieffer

The third and last US presidential debate took place tonight at Hofstra University in Hempstead, NY. I started by following the same methodology as with the first and second debates and the vice presidential debate, amended regarding Wordle by my 10-5-08 post. So let's start with the bubble graph displaying length of words, sentences as well as number of words:



As usual, the moderator (Schieffer) spoke far less. Obama tended to use longer sentences. I did an extra analysis again, this time focusing on speaking turns and the number of words and sentences per turn:



McCain had the most speaking turns, followed closely by Schieffer. Obama clearly had the least. However, Obama used a lot more words per turn than McCain. Schieffer came in dead last as a moderator should. It seems to me that this pattern was the result of McCain interrupting Obama a lot and Schieffer attempting to stop this. In other words, McCain was more aggressive, pushy.

Next, the by now traditional word clouds.

John McCain





Barack Obama





Bob Schieffer



OK, now what did it all mean? McCain was talking most about Obama—hey, he did call him "Sen." at least—followed by America, and the trio of need, going and now. He did not once use his opponent's first name, Barack: he didn't want to portray him too much as a human being, I suppose? Obama on the other hand used John 8 times, often by itself. Otherwise, his biggest words were going and think. People, now and make came next. Only then do we get down to McCain, health and want. Obama was talking more to the voters, explaining policy. Finally, Schieffer used, of course, Sen. the most but it was more accompanied by McCain than Obama. This reinforced our impression that he was trying to reign McCain in a bit. One more funny thing: Schieffer's catch phrase is "all right": he used it 17 times hence the prominence of right in his word cloud (all is a common word that is filtered out by Wordle).

Barack Obama vs. John McCain vs. Audience vs. Tom Brokaw

The second US presidential debate took place tonight at Belmont University in Nashville, TN. I followed the same methodology as with the first debate and the vice presidential debate, amended regarding Wordle by my 10-5-08 post. So let's start with the bubble graph displaying length of words, sentences as well as number of words:



Obama and McCain were again close though the latter used a bit shorter sentences. Remarkably, the audience questions contained the longest words, more even than Brokaw's. The moderator also spoke about twice as much as his colleague Jim Lehrer did in the first debate. While splitting up the text in the different speakers' parts, something caught my eye: Brokaw seemed to thank McCain a lot but not Obama. Just to make sure, I counted all speakers' instances of thanking somebody:



What stood out on this measure? McCain made it a point to thank the audience speakers and secondly thanked Brokaw quite a few times. He even thanked Obama 1.5 times—I counted a sarcastic "thank you" only half. Maybe McCain's expressions of gratitude reflected his being more formal and/or older? Or maybe he was trying to counter his rather stern if not grumpy behavior during the first debate? Obama on the other hand didn't thank many people. He thanked two audience questioners but was mostly business. He didn't thank McCain once. Maybe that was a reaction to criticism that he was bending over backwards to him too much during the first debate? Brokaw thanked McCain a lot more than Obama but neglected the audience too.

Finally, we made the "word clouds" again.

Barack Obama





John McCain





Audience





Tom Brokaw



I'll conclude with a few quick observations. Obama's no. 1 word tonight was "going," followed by "got," "Sen." and "McCain." Policywise, "health" and "energy" stood out. As for McCain, "know" was tops—invocations of experience? Then came "going," "Obama" and esp. "America(n)(s)." The audience very much stressed "economic"—remember "It's the economy, stupid!" from Clinton's first presidential campaign? As expected, Brokaw said "Sen." most, followed by "McCain" and then "Obama."

Wordle

I realize now that I didn't use the superb Wordle online text analysis website properly: my bad! Of course, one should always read the instructions completely and go over the different settings before using any software. The default graph shows only 150 words but this can be changed. Also, one can, for instance, have the words arranged more or less alphabetically: this facilitates finding specific words. Here are the complete settings I'll be using from now on:

• language:
  

remove nos.

remove common English words

• font:
  

Teen

• layout:
  

max. words: word count rounded up to the next thousand
prefer alphabetical order
rounder edges
horizontal

• color:
  

Wordly
a little variance

The following three posts have now been amended with the improved "word clouds":

• Sarah Palin vs. Joe Biden vs. Glen Ifill (10-2-08)
  
• Barack Obama vs. John McCain vs. Jim Lehrer (9-26-08)
  
• Michelle Obama vs. Joe Biden vs. Barack Obama vs. Sarah Palin vs. Cindy McCain vs. John McCain (9-4-08)
  

Democratic Party vs. Republican Party vs. Green Party vs. Libertarian Party vs. Constitution Party (Part 3)

This is the last part of a three-part series of posts (part 1, part 2). We explained the method used for this experiment, i.e., analyzing "toss-up" states in the US presidential election by comparing Google Insights for Search and Pollster.com graphs in part 1. We continue with Ohio:





For the first couple of months of this year, the Democratic Party (DP) was ahead in Google-popularity in this state while McCain was ahead in the regression trend line of the polls. For the rest of the year, the DP and Republican Party (RP) lines related to one another in the same way as the Obama and McCain trend lines: first the DP/Obama in the lead, then the RP/McCain. However, in September, Obama again gained the upper hand. The RP stayed in the lead though. I wonder if there isn't some kind of delayed effect in these case, or maybe the high-sensitivity trend lines for the candidates overreacted to recent polls? Now we turn our attention to Pennsylvania.





This state too was kind of puzzling: the parties' graph showed a DP advantage for most of the year except in September when the RP overtook them, only to end in a tie. On the candidates' graph, McCain was ahead till Obama overtook him in April; the latter then put a lot of distance between him and his opponent after some tightening in the beginning of September. This seems related to the Republican-convention a.k.a. Palin-announcement bounce for McCain and the current financial-crisis bounce for Obama (see also, for instance, Ohio above). Next is Virginia:





Similarly to Pennsylvania, the DP had the edge till the RP bested them in September. McCain however was ahead but lost more and more till the race turned into a dead heat in June. In September, the same Palin bounce and the financial-crisis bounces gave the advantage to Obama. Finally, I looked into Missouri, a state that has gone in and out of the "toss-up" category quite a few times. It was in McCain's camp when I started this series of posts but is again in contention.





The DP dominated till the RP took over in September. McCain was in the lead the whole year but it's now a tie. One more thing: Nader, Barr and McKinney are an afterthought in the polls. This is partially due to them often not being included in polls in the first place and, when they are, they don't appear in enough of them to survive Pollster.com's high-sensitivity smoothing filter. To be fair, let me give you briefly what their poll standings were today when using normal smoothing, as well as their parties' Google-popularity for 2008 so far (shorter period didn't yield good data):



I quickly tested the correlation between the two measures by producing scatter graphs with a linear regression trend line added (without the Constitution Party as I had no poll data for their candidate).





Quick conclusion: it looked like there was no correlation, in other words the Google-popularity of third parties couldn't be used to try to predict the third-party candidates Pollster.com scores or vice versa. Which probably means that we didn't miss out by not having them on all but one state poll graph after all.

Democratic Party vs. Republican Party vs. Green Party vs. Libertarian Party vs. Constitution Party (Part 2)

We explained the method used for this experiment, i.e., analyzing "toss-up" states in the US presidential election by comparing Google Insights for Search and Pollster.com graphs, in Part 1. So let's get started right away with Minnesota:





We again obtained contrasting graphs. The Republican Party (RP) was overall more Google-popular than the Democratic Party (DP). In the Pollster.com graph, however, Obama was ahead the whole time. Also, McCain's trend line followed a similar path as the RP's line while the Obama trend line was almost an inversion of the DP line. Hmm... Next is North Carolina:





This was the first state we encountered that had an actual trend line for a third-party candidate, i.e., Barr, because there were enough opinion polls that included him so as to still show up in Pollster.com's high-sensitivity graph. It is often said that he might take votes away from McCain. True, McCain lost his lead at the end of September but Barr's low trend line, if anything, was diminishing somewhat through time. In this state too we found a contrast between the parties' graph and the candidates' graph: The DP was ahead but was bypassed by the RP at the end of August. Let's look at New Hampshire:





The Google-popularity graph suffered from the lack of enough data: did New Hampshirites not surf the web as much as the inhabitants of other states? Maybe they were "politicked out" after their prominent role during the primaries? For what it's worth, the DP was the leader till mid-September when the RP passed them by. The candidates' trend line graph did confirm the overall picture with McCain temporarily overtaking Obama in mid-September. Remember that the Pollster.com graphs give a continuous trend line while the Google Insights graphs show basically monthly averages connected by a line. This explained in a way Obama having already taken back the lead in the end while the RP was still ahead. I give you one more toss-up state today: Nevada.





In this state also the general picture was the same in both graphs. The DP/Obama was ahead for most of the year but by September the RP/McCain was trumping them narrowly. I will post the last part tomorrow.