Warning: The crux of this post surrounds the word “shit.” It’s not used to be vulgar or profane, but to show what consumers are saying about brands online. If the word offends you, please move on. If you don’t and it still offends you, you were warned.

Talking with the folks at NetBase in preparation for Friday’s 11 for ’11 Webinar (see below), we came up with a fun little experiment to see A) How good NetBase is at really distinguishing between very similar phrases with very different meanings and B) Which brands are winning and losing in the online sentiment race … at least within these very small parameters.

There’s a major definition difference between saying something is “shit” versus saying something is “the shit.” They are, in fact, polar opposites. But having a sentiment analytics or online research tool that can automatically decipher which is which is tricky. We put NetBase to the task and found that it not only worked, but there are some brands out there that could use some help getting their online audiences to add the word “the” to the phrase.

Here are the brands that lost in the online battle of who is “shit” versus who is “the shit:”

Brands qualified as "Shit" online according to NetBase

Notice how dominant Blackberry is in being called “shit.” Odd also that all the major phone carriers are there. Maybe it’s not the phone carriers themselves, but just the technology in general that sucks.

Now here are the brands that “won” because they were called “the shit:”

Brands called "The Shit" according to NetBase

My only questions as interpret this data are A) McDonald’s? Really? And B) I’m thinking Taco Bell might be listed because it gives you “the shits.” So we may need to go decipher the data a bit. Then again, White Castle didn’t make it, so maybe I’m wrong. Heh.

Silly as it might be, these are potentially interesting bits of data for brands to have. So even though we focused on a little bawdy language today, know that there are online tools out there, like NetBase, that can help your company find and distinguish between the two.

As for the webinar, the last (11th) in the series is this Friday, (11/11 at 11 a.m PT, even), the NetBase gang thought it would be fun to have me do a webinar on my book. If you haven’t had the opportunity to hear my stories from the book talk, please join us! NetBase is giving away 250 copies of the book during the webinar, so just being an attendee gives you a chance to win.

Register for the webinar on the NetBase website and then block your calendar off for this Friday, Nov. 11 at 11 a.m. PT/2 p.m. ET for some good fun.

See you Friday!

Did you enjoy this blog post? If so, then why not:Leave Comment Below | Subscribe To This Blog | Sign Up For Our Newsletter |

About Jason Falls

Jason Falls

Jason Falls is a leading thinker, speaker and strategist in the world of digital marketing and is co-author of two books, No Bullshit Social Media: The All-Business, No-Hype Guide To Social Media Marketing and The Rebel's Guide To Email Marketing. By day, he leads digital strategy for Elasticity, one of the world's most innovative digital marketing and public relations firms. Follow him on Twitter (@JasonFalls).

Other posts by

Comments & Reactions

Comments Policy

Comments on Social Media Explorer are open to anyone. However, I will remove any comment that is disrespectful and not in the spirit of intelligent discourse. You are welcome to leave links to content relevant to the conversation, but I reserve the right to remove it if I don't see the relevancy. Be nice, have fun. Fair?

  • http://www.idatix.com Samantha

    See a trend there, cell phone carriers vs food. Very interesting. Also, this encouraged me to try Nutella.

  • http://www.idatix.com Samantha

    See a trend there, cell phone carriers vs food. Very interesting. Also, this encouraged me to try Nutella.

  • http://twitter.com/LadyAnne525 Anne Hogan

    Interesting!  I always love hearing about new ways to do sentiment analysis.  I registered for the webinar, and I’m looking forward to learning more on Friday!

  • http://twitter.com/LadyAnne525 Anne Hogan

    Interesting!  I always love hearing about new ways to do sentiment analysis.  I registered for the webinar, and I’m looking forward to learning more on Friday!

  • http://blog.socialmediahq.com Nick Robinson

    Brilliant idea. Would be interesting to see what comes up when you listen for mentions of criminal within political conversations :)

  • http://blog.socialmediahq.com Nick Robinson

    Brilliant idea. Would be interesting to see what comes up when you listen for mentions of criminal within political conversations :)

  • http://www.parcel2go.com Sarah Parker

    exactly how accurate is the sentiment? that’s what i would love to know. that’s the problem i find with most social media monitoring tools.

    • http://socialmediaexplorer.com JasonFalls

      Great question, and one I’ve asked for years. Sentiment scoring is never going to be more than about 65% accurate with a computer. In fact, put 100 people in a room and ask them each to score a paragraph of text and only 85% of them will agree, so even human scoring is not 100% accurate. But from my experience, NetBase’s algorithms and netnography understand more of the context around language and diction than other automated sentiment platforms. I based a lot of my recommendations and research on what they give because they’re as accurate as I’ve seen.

      They’re not without imperfections, but they have fewer than others.

    • http://socialmediaexplorer.com JasonFalls

      Great question, and one I’ve asked for years. Sentiment scoring is never going to be more than about 65% accurate with a computer. In fact, put 100 people in a room and ask them each to score a paragraph of text and only 85% of them will agree, so even human scoring is not 100% accurate. But from my experience, NetBase’s algorithms and netnography understand more of the context around language and diction than other automated sentiment platforms. I based a lot of my recommendations and research on what they give because they’re as accurate as I’ve seen.

      They’re not without imperfections, but they have fewer than others.

    • http://socialmediaexplorer.com JasonFalls

      Great question, and one I’ve asked for years. Sentiment scoring is never going to be more than about 65% accurate with a computer. In fact, put 100 people in a room and ask them each to score a paragraph of text and only 85% of them will agree, so even human scoring is not 100% accurate. But from my experience, NetBase’s algorithms and netnography understand more of the context around language and diction than other automated sentiment platforms. I based a lot of my recommendations and research on what they give because they’re as accurate as I’ve seen.

      They’re not without imperfections, but they have fewer than others.

  • http://www.mgtdesign.co.uk/ Zena

    Brilliant blog. Most blogs you read online are boring and don’t offer much information. This was really helpful.Its really a superb post.Keep in touch with us in future too.Thanks.

  • http://www.totallyseo.co.uk/ Yarout

    Nice article about light bulbs.I liked the post.Good job.Thanks for sharing such post.

  • Pingback: Black Friday? Try Blank Friday « MindCorp | Newsfeed