An article in the New York Times this week discussed a research project that is attempting to track the mood of Americans using Twitter as the data source. The project involves researchers from Northeastern University College of Computer and Information Sciences and Harvard Medical School. It is certainly reasonable that a group of scientists can develop algorithms that accurately predict the mood of Americans. However, Twitter data is not simply and instantly predictive of the general population of Americans. Given that only 7% of people who are online even use Twitter, it is risky, and can easily lead to wrong conclusions.
Want to see a real example? No problem.
Let’s look at consumer opinions related to one specific product, the iPad.
First, we gathered thousands of opinions from across the internet, from blogs, microblogs, forums, question and answer sites, personal sites, all of which mentioned the iPad. Sites like YouTube, Blogger, Twitter, and thousands more were included.
Then, we categorized all of the conversations into two groups, 1) everything from Twitter and 2) the entire internet space.
Next, we determined the level of emotion for every online conversation. Specifically, we determined whether the emotion of the conversations was extremely happy, somewhat happy, neutral, somewhat unhappy, or extremely unhappy.
Finally, we created the pretty little charts that you see on the right of this page.
What’s the first thing you notice from these charts?
Not one single chart has two bars that look the same. What is the percentage of tweets that reflect an extremely happy opinion? 15%. What is the comparable number for the entire internet? 5.6%. I hope it’s not just me, but 15% doesn’t look like 5.6%, not even if the 5.6% is averaged up to 6%. There is a big difference in the percentage of people who have extremely happy opinions on Twitter vs the entire Internet.
The same trend is apparent when we look at the percentage of people who are extremely unhappy with the iPad. 11.3% of tweeple are extremely unhappy compared to just 1.9% of the entire internet space. All five of the charts lead to the same conclusions. Twitter results do not equal Internet results.
It’s not 1 to 1
Clearly, the relationship between Twitter data and total internet data is not 1 to 1. It’s impossible to gather Twitter data, analyze the sentiment, and be confident that it represents a wide, more general audience.
Perhaps people on Twitter have more extreme opinions than everyone else; perhaps they are less likely to guard their remarks so that the more extreme opinions are shared; perhaps Twitter opinions are in fact the closest to the average American opinion. Whatever the reason, it is undeniable that the mood on Twitter is unlike anywhere else.
Prepare to be wrong. Prepare to explain contradictions. Generalize Twitter mood at your own risk.
We heard it all yesterday. The amazing, brilliant, stunning, and incredible Flipboard for the iPad had a few problems from server overloads to failed connections with twitter and facebook. Did that phase people at all? Let’s have a look at the most recent online conversations to see how consumer sentiment changed since yesterday.
Overall sentiment: A very slight decrease from 61% positive to 58% positive with 3% (as opposed to 0%) of opinions now in the negative zone. The problems with crashing and connection failures may have bothered a few people, but they just couldn’t damper overall spirits. The Flipboard is still “amazing,” “awesome,” “brilliant,” and “incredible.”
Recommendations: Remained stable at 58% positive. The app still comes highly recommended as the “greatest” thing since the last greatest thing.
Ease of use: Decreased from 70% positive to 62% positive. This is a noticeable decline but still stunningly high given that 30% positive is a score most brands would hope to achieve.
Fashionable: Decreased from 79% positive to 74% positive. A small decline but not nearly enough to take away from the app being “beautiful,” “sleek” and “very cool.”
eReader: Decreased from 68% positive to 64% positive. Today, we also saw 2% of the opinions fall into the negative zone, but overall, people like the app as an ereader.
Facebook: A small decrease from 68% positive to 65% positive. And, today brought 1% of scores into the negative zone, again likely because of the connection issues. People like how the works with facebook.
Twitter: Another small decrease from 65% positive to 61% positive, plus 1% of scores in the negatives also because of the connection issues. People still like how the app works with twitter.
.
For the most part, scores decreased by several points. However, since the average positive score for most brands is around 30%, the fact that Flipboard is still registering scores in the mid to high 60s, even after a decline from day 1 is a stunning achievement. With negative opinions reflecting only 1% or 2% of overall opinions, the Flipboard seems to have continued its winning streak directly into day 2.
Apparently, even the crashes and failed connections are unable to counter the boxes of chocolates and bouquets of roses that are being handed to this pretty little app. .
If you thought Old Spice was just for your grandfather, the brand is working hard to change your mind with a series of commercials starring @IsaiahMustafa. The commercials have become a viral hit and have expanded into short videos, each one a unique hilarious reply to people’s online tweets, youtube comments, and questions. Questions from real people, and celebrities like The Ellen Show, Alyssa Milano, and Ryan Seacrest, are all getting individual attention.
How are people describing this campaign? The top words include funny, original, hilarious, brilliant, and genius, definitely words I’d like my brand associated with. But on an aggregate level, the campaign has far surpassed any standards of making the grade. Compared to the average brand which generates about 30% positive opinions, the Old Spice campaign is achieving positive opinions in the 40%, 50%, and 60% ranges.
People appreciate the business side of things, including the product launch (66% positive), the creativity (59% positive), and that it’s a new and different approach (57% positive). But, they are also expressing their appreciation for Isaiah, a manly man himself, giving him top marks for his smile (59% positive), his teeth (57% positive) and his sex appeal (54%).
What isn’t so positive? The ever present fear factor associated with sexuality and homophobia, comments which generate 25% negative opinions. Fortunately though, this small minority of people can’t compete with the millions of people who are loving every minute.
Isaiah, keep on smelling like the man our men could smell like.
With the Golden Globes behind us, let’s have a look at whether viewers agreed with the judges’ choices. We gathered over 200 000 tweets from people chatting about the Golden Globes Awards and categorized them into tweets that were positive, neutral, or negative. We then selected all the tweets that were related to the Best Director of a Motion Picture category and analyzed the results. The chart below illustrates the percentage of tweets that were classified as positive, in other words, they showed a high degree of satisfaction or approval.
First of all, it is clear that even though James Cameron, the Director of Avatar, won in the category of Best Director, he wasn’t necessarily the winner in the viewers’ eyes. In fact, Reitman, the Director of Up in the Air, generated the most positive tweets with 45% of them being positive compared to 42% for Cameron. And, compared to Reitman generating 11% negative tweets, 14% of Cameron’s tweets were negative. It was a pretty close race for viewers, but Reitman came out just slightly ahead with 3% more positive tweets and 3% fewer negative tweets. And just behind Reitman and Cameron is Bigelow, the director of Hurt Locker. It appears that this still wasn’t the year to showcase the first female winner of this award.
At the other end of the spectrum was Tarantino who directed Inglourious Basterds. Tarantino only managed to generate 26% positive tweets. Further, 23% of tweets about him were negative. Some people just needed to display their displeasure at this loss. And finally, our sympathies go to Clint Eastwood, the Director of Invictus, who didn’t make it to our podium because so few people tweeted about him.
The Screen Actors Guild awards are coming up next. Grab some popcorn and let’s see what happens!
Jersey Shore is a new show focusing on a subculture that rarely takes the limelight on television, one populated by extreme personalities who call themselves guidos and guidettes. It has received a lot of heat for being offensive and racist towards Italian people. Some sponsors, such as Dominos Pizza and American Family Insurance, have pulled their ads from the show because of the controversy. In fact, UNICO National protested the show but this did not have an effect. On the other hand, some companies such as BeenVerified.com, a background checking service, have decided that Jersey Shore does in fact represent their brand and have since become sponsors.
What do tweeple think of all of this? As the blue line in the chart below shows, the volume of chatter has steadily increased since the show previewed on television. Given the controversy surrounding this show, the volume of chatter will no doubt continue to increase.
What is particularly interesting is the sentiment trend. For the week before the show premiered, tweeple shared a range of opinions about the show resulting in fewer than 50% of opinions being positive. However, most recently, and after the show has aired, sentiment drastically increased and currently sits at more than 80% positive. It seems that the initial fears of racism were outweighed by the many people who seem to enjoy the peculiarities of the characters portrayed on the show. Time will tell how other sponsors react as the show increases its audience base, and more people are exposed to the controversy.
Years past saw Cabbage Patch Kids (adults will remember), Tickle Me Elmos (adults’ kids will remember), and other hot toys tempt the imagination and money of millions of people. This year is no different with Zhu Zhu pets, the electronic hamster that promises all of the fun without the mess, becoming the Toy of the Year. The toys were on people’s minds for a while, but as the chart shows, it wasn’t until early November that chatter volume broke through the noise and registered a blip in the Twitter stream. This blip reoccurred in the middle of November when the toys began to run out and consumers were attempting to find locations where they could still purchase the toy.
Despite the ups and downs in the volume of chatter, sentiment towards these toys has been near perfect reaching almost 100% positive every single week for a couple of months now. The low price-point is no doubt a major factor for their popularity in this economy. Notice, however, that just recently, sentiment has started to decline. This is likely the results of two factors.
The toys have sold out nearly everywhere and consumers are expressing their dissatisfaction with being unable to purchase them.
Concerns have just been raised that the toys may be recalled due to health issues.
We will be certain to track how sentiment changes as more is learned about whether there is a potential hazard. Stay tuned!
Well, not literally, but Tiger Woods did crash his car and he is getting burned! But what do real folks think of the whole situation? The volume of tweets related to Tiger had been relatively low prior to November 27 at which time it registered a 9000% increase. Even now, several days later, the spike remains, though only about 4000% higher. If that’s not statistically significant, we don’t know what is!
Sentiment showed a similar significant change as a result of the incident. Sentiment was hovering around 100% positive until November 27 at which point it suddenly dropped when people learned about the accident and became concerned for his well-being. Now, instead of nearly 100% approval, Tiger is dealing with an approval rating of about 60%. And that’s a big drop for someone whose income depends on consumer approval.
But as we all know now, it wasn’t simply his well-being that peaked our interest and kept us going. On day 1 after the incident, 92% of the chatter was focused on the car crash or accident. This quickly transitioned, however, such that by day 4, just 43% of tweets were about the car crash and 57% were about a supposed extramarital affair, perhaps the transgression that Tiger today announced he was regretful for. One can only wonder how will this impact his marketability.
The lighter side of this whole incident though, is that the drama brought us a fantastic set of new jokes. Here are just a few of our favorites. Enjoy!
Police say Tiger Woods injuries are not serious, however he is feeling a little under par
Maybe Tiger Woods should change his name to ‘Cheetah’ Woods
What’s the difference between a Titleist and a Cadillac?? Tiger Woods can drive a Titleist 400 yards without hitting a tree
What’s the difference between a car and a golf ball? Tiger Woods can drive a ball 400 yards.
Tiger Woods is so rich that he owns lots of expensive cars. Now he has a hole in one.
Hollywood is making a film based on this incident: Crouching Tiger, Hidden Hydrant
tweetfeel/bizis ready to leave the nest and we’re ready to announce it at two upcoming conferences.
First off is TWTRCON in DC on October 22 where we are a sponsor and will be running demos oftweetfeel/biz.Then, on October 27, we will be at the 140 conference in LA also sponsoring and running demos for attendees. Both Jean and Tessie will be there signing autographs as well so be sure to stop at our booth! They’d also love to give you a personal demonstration of how you can use tweetfeel/biz to help your business. See you there!
We’ve been dying to share with you our great new app called tweetfeel. This new application scours Twitter for Tweets about brands of your choice and shows you how positively or negatively Twitter users feel about it. Whether it’s Dell or Poptarts or Madonna, we’ll show you a sample of recent tweets as well as an overall rating for the brand. It’s a quick way to get a feel for what people are thinking!
tweetfeel uses an algorithm that is more complicated than simply counting happy faces and sad faces. Because only a small sample of people use emoticons , apps doing it that way miss out on the majority of people who talk about brands using words. This means that tweetfeel produces results that are more accurate than other applications doing a similar thing
At the time of this post, Twitter tweets were 63% positive, Dell tweets were 53% negative, and Poptart tweets were 92% positive. Try out your favorite brands to see how they rank!
Follow tweetfeeldotcom on Twitter and we’ll share some results with you every day.
It’s been a busy few days! Jean flew in for three days of back to back Conversessions. We love it when she comes because it means an extra-large dose of passion, a tasty lunch on the house, and some animated gut-busting stories. My suggestion – Ask her about The Family Feud!
Once our US sales executive arrived as well, we settled in for the three day Conversession. Our main goal? evolisten. Oh, the things you can accomplish when you stick to the schedule! We reviewed and revised the project plans. We evaluated which verticals we were interested in, which ones we had contacts for, and which ones would be perfect to take advantage of our product. We worked through a huge array of business rules for our product and agreed on the top priorities. We went over our initial marketing plans and flushed them out in more detail. (Twitter is there if you’re curious.) We talked with Trademark lawyers to safe guard our brand names. Our accountant also dropped by to organize all things financial. We know it was a successful conversession because we left behind about 37 candy wrappers!
And at the end of it all, we took just a few more minutes at the computers before going home. And one last look at Jeremy’s wild shoes.
, apps doing it that way miss out on the majority of people who talk about brands using words. This means that 
