Everybody hated the How I Met Your Mother finale, right? Well, maybe not. The hour-long conclusion to the popular CBS sitcom was the target of much derision after it aired March 31. (See: Here, here, here, here, and here.)
But data, as it sometimes does, tells a different story. Most of the people surveyed by the social analytics platform Canvs felt good about the finale. More than twice as many people either enjoyed it or called it "great" than those who said it "sucked."
Canvs, which formally launched last week, uses sentiment analysis to figure out how people feel about TV shows and other entertainment. That analysis is then combined with scary-specific data profiling, so Canvs can tell its clients not just how people feel about what they're watching but what kinds of people feel certain ways.
The viewers who thought the How I Met Your Mother finale was "sad," for example, were also more likely than the average Twitter user to be teenaged girls interested in Taco Bell. More on that in a minute.
First, here's what Canvs found, based on Twitter reaction from about 117,000 viewers: More than half of reactions to the show were positive, while about one-fifth of them were clearly negative.
Here's the breakdown:
• 19 percent of people said the finale "sucked, not a fan"
• 18 percent enjoyed it
• 16 percent called it "great, glorious"
• 15 percent called it sad
• 13 percent reacted with "love, perfect"
• 12 percent "loved(d)" it
• 7 percent called it "great, sad"
As with any dataset, there are limitations. In this case, we're talking about 117,000 tweeting viewers—a bigger sample size than many telephone-based surveys, but still only 1 percent of the 12.9 million people who watched the finale. (To put that in context, though, presidential campaign polling routinely is based on sample sizes that represent 0.0001 percent of the actual population.) The Canvs analysis covered about 185,000 tweets, just a portion of the half-a-million tweets that Canvs identified as being related to the finale. The platform only analyzes tweets it is sure it can interpret accurately, founder and CEO Jared Feldman told me.
Feldman says his team obsesses over how we talk about what we feel. Computers aren't always so discerning, which makes much sentiment analysis flawed. An algorithm might recognize the word "enjoy" in a tweet that says, I really didn't enjoy the How I Met Your Mother finale, without realizing that the tweet isn't ultimately positive. You can teach a computer to recognize the "didn't" before "enjoy," but that doesn't go far enough, either.
Understanding how humans talk about their emotions is far more complex than accounting for qualifiers like "don't" and "can't," which is part of what makes machine-run sentiment analysis so thorny.
"Maybe you said, 'I can't effing stand how much I love this show,'" Feldman told me. "The computer's mind is blown... The way that 12-year-olds talk about loving Justin Bieber? There's no dictionary on the planet that captures that."
So Canvs uses an algorithm built on years of more nuanced human analysis known as "supervised sentiment analysis" in the industry. The result, Feldman says, is real-time conclusions at a level of sophistication that previously would have taken hours. Sentiment analysis is notoriously difficult to get right, and it's not really possible to tell from Canvs' interface whether the platform is as nuanced as Feldman says. It's user friendly and incredibly detailed, but using it requires faith in an unseen algorithm—one that Canvs is selling.
But Canvs gives its users plenty of opportunity to assess the data. For each reaction category—like "sucked, not a fan," or "great, glorious,"—you can dig more deeply into what people actually said. Canvs displays popular keywords from related tweets, user's handles, and the tweets themselves. Here's a glimpse of the breakdown of people who reacted with "enjoy:"
The graph lets you track minute-by-minute reactions throughout the show's airing, so you can see when "sad" spiked, for instance.
This analysis becomes valuable for companies that want demographic profiles that include how people feel. So Canvs reviews months of backdata—what you've tweeted, who you follow, where you're tweeting from—to deduce personal information like a viewer's age, gender, ethnicity, income levels, interests, brand loyalty, and so on. We already know that marketers are combing the internet for hints about customers, but Canvs shows how easy it is to get a detailed picture. Here's a glimpse at the people who thought the finale "sucked:"
Again, Feldman: "From one piece of text we can learn eight things about you. Say you mentioned [in a tweet] that you're going to Whole Foods after work. So you have an affinity to Whole Foods. You also said, 'after work,' which implies you're employed." Combine those clues with geolocation, gender, and age data, and Feldman says Canvs can confidently guess someone's income bracket. (These data subsets are smaller than the original 117,000-person cohort because specific information like location and gender aren't available for everyone.)
In the case of How I Met Your Mother, people who said they "love[d]" the finale were ever-so-slightly more likely than the rest of Twitter to live in Toledo, Ohio, and Fort Wayne, Indiana. Those who called it "great, glorious," were more likely than the average Twitter user to live in cities like Chicago, Philadelphia, and Los Angeles. People who said it "sucked" were more likely to like in New York, Philadelphia, and Boston. The Philly example is interesting because it shows up in connection with some of the strongest opinions about the show, even when viewers in Philadelphia didn't make up a significant percentage of the overall audience. Most tweets came out of New York, Chicago, Boston, Los Angeles, Houston, Atlanta, and Washington, D.C.
The finale audience as a whole skewed more female than male, and included big sports fans who are less interested in news and music than the average Twitter user. Members of this audience were more likely to follow celebrities like Taylor Swift, Daniel Tosh, and Neil Patrick Harris—one of the show's stars. And they were more likely to follow brands like Starbucks, McDonald's, and Taco Bell. Of course, the Taco Bell following may have more to do with Twitter than with How I Met Your Mother; Taco Bell's Twitter presence is legendary.
Taco Bae.— Taco Bell (@TacoBell) April 8, 2014
Looking at the level of detail in Canvs' demographic data, you can begin to see how TV networks and marketers might think about using publicly available personal data to get to audiences. Canvs already counts networks like BET, Comedy Central, and Viacom, among its clients. For advertisers, there's a reverse-engineering component to using this kind of data, too. Here's how Feldman puts it: "If I'm McDonald's, it'd be fantastic to know: The people who already care about me, what shows are they obsessed with?"
Canvs' very existence is a reminder about the remarkable ways corporations can piece together data profiles about individuals in the United States. That's not the case in several other parts of the world. Many European countries strictly regulate use of consumer data for the creation of advertising profiles. These sorts of profiles are fantastically valuable to marketers, but consumers are just beginning to understand the scope of what advertisers actually know about them. And knowing how a consumer feels is just another step toward figuring out what they want.
"The theory is that the people who love your show are going to be different than the people who hate your show," Feldman said. "We've actually figured out a way to capture how people love this show." And people really did love it, Feldman says of the How I Met Your Mother finale.
"Really, when the show was over, people were saying how perfect the ending was at a much larger scale," he said. "You may log into Twitter and see a random tweet [from someone who hated the ending]. But it turns out 10 times more people were saying how perfect the ending was, and you probably just didn't see it."
We want to hear what you think about this article. Submit a letter to the editor or write to firstname.lastname@example.org.