tweetfeel/biz Spots the Oprah Love

Tuesday, December 1st, 2009

In a story that had nothing to do with weightloss or people jumping on couches, the Oprah Winfrey show was in the news yet again on November 19th and 20th 2009. The announcement that Oprah had decided to end the Oprah Winfrey show after 25 years was a shocker for some people.  This stunning announcement is quite clear in a very simple chart of the volume of Oprah tweets. In the days before the announcement, the volume of tweets fluctuated slightly. Then suddenly, on Nov 19 and 20, tweets mentioning Oprah showed a tremendous spike. You don’t need to have color vision to know which is the blue line in the chart below.  The spike, however, lasted only a couple of days after which time the volume of tweets returned to its standard trend.

However, overall sentiment did  not show any major change. Sentiment hovered around 75% positive for the Oprah Show before Nov 19. Then, it then decreased very slightly to around 68% positive at the time of the announcement. Within just a few days though, sentiment had increased once more to about78% positive. Why is this happening?

What types of emotions were people exhibiting in their tweets? As shown in the pie chart below, nearly half of the emotions expressed by tweeple were those of love.  Even though fans might have been upset at the announcement, they were still very fond of Oprah and her show. The next most popular emotions were equally split between expressions of anger and sadness, each reflecting 19% of the pie, but not in sufficient volumes to cause a significant shift in the overall positivity of emotion. Surprise and courage were next in line, finishing off the last 8% and 6% of the pie.

These sample tweets show exactly why sentiment stayed high. Fans had no difficulty expressing both their love for Oprah and their sadness about the show.

• @Oprah SAD SAD SAD BUT,IF YOU LOVE SOMEONE LET THEM GO.I WOULD LOVE TO SEE ELLEN GO ON AT 4:00PM.WE WILL STILL SEE YOU LOVE SUE
• @Oprah I love your program,I loved having you on Twitter
• The Oprah Winfrey Show to end in 2011 after 25 years on air! http://news.bbc.co.uk/2/hi/entertainment/8370789.stm sad times…
• awww! Oprah is crying! I love her!

So, where do we think viewers will turn? One of the sample tweets should have given you a clue. If you look at the chatter, Ellen Degeneres seems to be unstoppable with 73% of the chatter among Oprah fans. Tyra Banks is next in line with 15% of the chatter, followed by Rachael Ray with 12% of the chatter. It would take a miracle for Tyra or Rachael to jump over Ellen, but who knows, maybe Oprah will still be number one… except on her OWN network.

Conversition Launches Enhanced Twitter Sentiment Product as tweetfeel/biz

Wednesday, November 4th, 2009

Conversition Strategies announces the launch of www.tweetfeel.com/biz, a subscription based service site that lets companies track the sentiment and content of Twitter chatter with accuracy and specificity.

Toronto, November 4, 2009: CONVERSITION releases www.tweetfeel.com/biz, a subscription service website that allows users to monitor the feelings Twitter users express towards products, companies, and other popular topics such as celebrities and movies. This new offering builds on the success of the free consumer version, and includes an increased focus on accuracy and comprehensiveness.

Tweetfeel.com/biz incorporates traditional research methodologies to ensure that the entire process of measuring and reporting sentiment is as valid and reliable as possible. After users specify the relevant search terms and keywords, www.tweetfeel.com/biz immediately begins to gather tweets in real-time. www.tweetfeel.com/biz then uses a multitude of complex algorithms to evaluate tweets in terms of both positive and negative sentiment.

Unique features available in www.tweetfeel.com/biz include the ability to create very specific and accurate search terms by specifying terms that must be searched and terms that must not be searched. Users can also build customized stories to monitor exactly how people are talking about each search term. These stories, or themes, allow users to identify the most popular and least popular topics, thereby permitting actionable insights to occur. Charts and graphs allow users to easily monitor changes in brand sentiment over time.

Tessie Ting explains, “Sentiment analysis is a difficult process in itself, but by developing a very comprehensive set of algorithms, and relying on our knowledge of valid research practices, www.tweetfeel.com/biz demonstrates a level of validity that makes brand tracking of Twitter data highly reliable and very simple.”

“This industry is no longer just about sentiment,” says Jean Davis. “It’s about understanding why people have positive or negative feelings towards something. Understanding the story behind the emotions turns raw data into useful data.”

For a personalized demonstration of www.tweetfeel.com/biz, please contact Jean Davis.

www.tweetfeel.com/biz offers subscriptions for individual or small business users as well as enterprise pricing.

About Conversition Strategies:

Conversition Strategies is a marketing research firm that listens to consumers by applying scientific research principles to the collection and analysis of online social data. Our strength lies in combining the expertise of respected market researchers with that of social media mavens. Our services are complementary to traditional market research methodologies and help you gain a more holistic view of how people engage in conversation regarding your product, service or brand.

For more information please feel free to contact:

Jeremy Chaput | jeremy@conversition.com | 647.998.3854

Jean Davis |  jean@conversition.com | 631.838.6460

http://www.conversition.com | http://www.tweeteel.com/biz | RESEARCH EVOLVED

Come See Us at TWRTCON and 140

Sunday, October 18th, 2009

tweetfeel/biz is 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 of tweetfeel/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!

Like tweetfeel? Vote For Us!

Thursday, October 15th, 2009

If you think tweetfeel is so fun and easy that everyone should know about us, nominate us for best Twitter app! Just click on this button and tell the Open Web Awards!

Sentiment Analysis 101

Friday, July 17th, 2009

tweetfeel gives you a taste of it, but really, what is sentiment analysis all about?

At it’s most basic level, sentiment analysis involves reviewing messages or conversations and evaluating the writer’s opinion towards the topic. For instance, someone who tweets a message such as “I like Chuck Norris” is telling people they have a positive opinion towards Chuck Norris. On the other hand, someone who writes “Chuck Norris sucks” clearly has a negative opinion. After assembling all of the messages that mention Chuck Norris, one can easily bucket them into messages with positive opinions and messages with negative opinions.

But, the easy part isn’t so easy. First, one needs to determine which sentiments are positive or negative. Obviously, we’re talking automated sentiment analysis so we need some solid indicators for positive opinions such as words like happy, love, or delightful. Solid indicators for negative opinions would be words such as hate, stupid, or ugly. Simply coming up with that list is difficult enough, but some words just aren’t so easy to assign to buckets. For instance, is “Way to go” positive or negative? People often use this phrase in a positive way but in recent years, it has become a very sarcastic remark that one uses in a negative fashion. The written word is full of words and phrases that have contradictory, ambiguous, or sarcastic meanings. Humans can only catch about 85% of those which means it’s pretty much impossible for an automated process to catch all of them either.

Another problem with bucketing messages is that people don’t think linearly. If I say “I love Chuck Norris and football sucks,” it’s clear to people that I’ve messaged two distinct opinions about two distinct topics. Once you start getting into more complicated grammar though, it can become impossible to tell which topic was rated which way. Automated evaluations of the message have a much harder time differentiating the two. It’s a topic of great interest to academics and eventually, we’ll figure it out.

In the end though, it’s not about individual messages. It’s not about me and what I have to say. It doesn’t matter that your uncle Bob is always wrong and that your Aunt Mary doesn’t know who Chuck Norris is. It doesn’t matter that 5% or 10% of the messages are in the wrong bucket. What matters is the collective wisdom, the wisdom that comes from large sample sizes. When you average opinions across hundreds or thousands of people, the final answer is usually the right one.

TweetFeel Testimonials

Wednesday, July 15th, 2009

Well, tweetfeel officially launched yesterday and we’ve had an amazing response! We are delighted to hear that so many people are having fun checking it out. In fact, so many people have been checking it out that we hit our Twitter API call rates and haven’t been able to run everybody’s search! Don’t worry, though. We’re speeded things up from our end so you should see some improvements soon!

We’ve been reading all the comments people are making about tweetfeel.  You’re right, it’s not perfect nor will it ever be perfect. But, it’s fun, it’s pretty quick, it’s pretty accurate, and it’s free. How can anyone resist that?

Below are just a few testimonials from our friends. Thanks guys!

1. bootdisk If you’ve not checked out http://www.tweetfeel.com/ yet – have a look, interesting way of measuring ‘feelings’ towards people’s tweets!
2. chrish10 @VolumeGroup im impressed with #tweetfeel, looks very good and extremely useful
3. LenKendall Have you checked out Tweetfeel.com? It’s a very cool tweet sentiment application. Simple/Pretty interface. http://is.gd/1ytSQ
4. zoodigital Nice twitter tool – http://www.tweetfeel.com
5. Legend_Kiiller Crazy! RT @mashable: TweetFeel: Real-Time Sentiment Search for Twitter – http://bit.ly/JpBsjabout
6. wearelondon tweetfeel.com cool error msg “We have failed you and we are sorry.Try another search term & we promise, we’ll do better…” (@AndrewGrill)
7. hridayramshenoy checking out TweetFeel. Damn good idea.
8. vishnugopal TweetFeel – Really cool. Try Windows Vista or Macbook pro http://tr.im/sdwU (via @brupm)

The Unveiling of TweetFeel

Tuesday, July 14th, 2009

TweetFeel has received a lovely welcome by the internet world. Here are just a few of the mentions from the last day or two.

TweetFeel gives instant brand feeling

by Dan Leahul, Brand Republic 14-Jul-09, 11:15
LONDON – TweetFeel, a new Twitter application which allows marketers to instantly gather the overall sentiment of their brands, has gone live as use of the microblogging website continues to surge after slowing slightly last month.

The Washington Post Publishes tweetfeel Review

Published July 13, 2009

TechCrunch Reviews tweetfeel

by Robin Wauters on July 13, 2009
TweetFeel is a new web service by marketing research startup Conversition Strategies that combines real-time search for Twitter with sentiment detection algorithms. The idea is for people to use TweetFeel to run search queries for products, celebrities, companies, brands etc. and thus get a notion of what the average Twitter user thinks of them in a matter of seconds…

Research Live Reviews tweetfeel

Published July 13, 2009
Social media research agency Conversition has developed a website through which people can search Twitter for mentions of brands, celebrities and products, and to see whether the tweets are positive or negative….

Mashable Reviews tweetfeel

By Adam Ostrow, July 13, 2009
TweetFeel is a new Twitter search tool along the same lines, but instead of showing one or the other, gives you a numerical score as to how positive or negative tweets are about a given topic. Its analysis is based not just on emoticons, but also words and phrases…

TweetFeel: What’s the Twitter feeling?

Friday, July 10th, 2009

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.