Instrumented Interconnecteds Intelligent

Waynes World

(Image: Wayne Watrach, Visual Media, IBM)

By Suman Mukherjee and Forsyth Alexander

As the world waits anxiously for the fourth installment of the popular Jurassic Park movie series to be released Friday, we thought it would be fun to look into the social buzz for the upcoming summer blockbuster.

As fans, we were curious about things like, where the most Twitter chatter was happening, how tweets were breaking down by gender, overall sentiment, peak times for chatter, and more.

So we uploaded some Twitter data about Jurassic World into Watson Analytics, IBM’s natural-language cloud-based analytics service, and within minutes began unearthing pretty interesting insights, such as: the country with the most tweets so far is Chile; on the whole, women are tweeting more than men; and Portugal has the highest number of positive tweets, but also the most negative.

For each bit of research and each question we asked, Watson Analytics provided a visualization that summarized the information so we could understand what we were seeing quickly and easily.

SP Jurassic World WA QsThat’s the great part about Watson Analytics – it’s all about opening up and extending the power of predictive analytics to people with little to no analytics experience to help them start making data-driven, strategic decisions.

Getting started is easy. After logging into Watson Analytics, we simply used the Twitter Data Connector in the service to import Twitter chatter for #jurassicworld from February 1 to May 29, 2015. As soon as we clicked on the imported Twitter dataset, the “guided” feature kicked-in and Watson Analytics shared exploration starting points. We didn’t have to type a word.

Based on the visualizations, we were able to see that:

  • Although Chile had the highest total of authors tweeting about the movie, Mongolia wasn’t far behind.
  • In April, women had more positive comments about the movie than in May.
  • Overall, sentiment for the movie was positive, which was to be expected. However, there was no appreciable change in the order of sentiment over time. Positive was highest for each day, followed by neutral, then negative and then ambivalent.
  • The global volume of all tweets (whether positive or negative) surged during the last five days of the month.

SP Jurassic MapThe surge of sentiment and tweets toward the end of May might be a reflection of the increased number of trailers being released, the Jurassic World tumblr page, and the fact that the release date was nearing. Regardless, such insights could be valuable for the later releases of the movie in other countries or could be used to drive earlier previews for more positive chatter sooner.

Adding language and city for even deeper insight into sentiment

We admit, we’re in the analytics business, but we were still fascinated by what we were learning about sentiment—and so fast. Now that we knew about which gender was tweeting more and when positive tweeting was at its highest, we once again took advantage of how Watson Analytics can process natural language by asking for sentiment about the movie by language, by cities and then by cities plus tweet type.

Watson Analytics answered our questions with scatter plots that showed:

  • Only neutral sentiment was expressed in Arabic and in Ukrainian.
  • The difference between positive sentiment and neutral sentiment in Norwegian was much higher than for other languages and the incidence of negative sentiment was quite low.
  • Negative sentiment was higher in most of the cities I looked at, with positive sentiment staying steady until it reached Los Angeles. Also, there was a huge spike in positive sentiment from authors in New Orleans.
  • The majority of negative sentiments came from shares and not original tweets.
Forsyth Alexander, Content Lead and Information Developer, Watson Analytics

Forsyth Alexander, Content Lead and Information Developer, Watson Analytics

Suman Mukherjee, IBM Technical Marketing Lead, IBM Business Analytics

Suman Mukherjee, Product Experience and Design, IBM Watson Analytics

The great thing about Watson Analytics is that it is accessible to people with little to no analytics skills. So, for example, a worldwide marketer for the studio or distributor or even a star’s publicist could use this information to adjust promotions or campaigns in the countries where Arabic and Ukrainian are spoken.

With our curiosity sated, we returned to work confident that Watson Analytics is embodying the quintessence of self-service analytics. Now, we can’t wait for the movie.
_______________________________________

Visit and sign up for Watson Analytics here: www.watsonanalytics.com.

Bookmark and Share

Previous post

Next post

57 Comments
 
June 27, 2016
5:03 am

Why Women? I wonder


Posted by: kamau
 
June 24, 2016
5:32 am

it will be interesting to know why only women led the tweeting
good thinking.


Posted by: Arthur
 
June 10, 2016
2:33 pm

keren bgt


Posted by: mobil honda semarang
 
April 11, 2016
12:59 am

keren banget kak infonya


Posted by: celana hernia
 
March 7, 2016
7:58 pm
March 7, 2016
7:57 pm

snapchat pc


Posted by: snapchat pc
 
March 7, 2016
7:45 pm

nice one
snapchat pc


Posted by: snapchatpc
 
March 5, 2016
9:29 am

nice


Posted by: imo for pc
 
January 6, 2016
2:40 am

The power of technology will continue endlessly to rule our life. From adventurous life to business


Posted by: Alex
 
November 17, 2015
4:14 am

thankssssss


Posted by: درب ضد سرقت
 
November 8, 2015
5:53 am

thanks


Posted by: تست جوش
 
June 21, 2015
8:30 pm

Great Article………….. Nice


Posted by: Usha
 
June 19, 2015
3:10 am

Great job,very informative.


Posted by: mercy nyambura
 
June 19, 2015
2:44 am

Great! It does show how Watson Analytics can be used in other domain and business areas.


Posted by: Abhay Pimprikar
 
June 18, 2015
2:47 pm

I know Watson can do much more than do counts and derive sentiment – since that’s also an out of the box deliverable of apps like IBM Modeler text analytics. What if Watson was to “participate in the conversation” rather than be a passive receiver. Companies are interested in products which will subtly (or not so subtly) promote a product. That would be the interesting conversation.


Posted by: Terry Taerum
 
June 18, 2015
11:17 am

While it’s temping to think that twitter feed represents a true data based indication of the sentiment of the population on the whole, in truth only a little over 40% of the global population is internet connected, and only a little over 20% of that 40% use twitter. And of those twitter users, by far the largest demographic are people between the ages of 18 and 29… something to keep in mind when drawing conclusions from this data.


Posted by: Robert Nawratil
 
June 18, 2015
10:26 am

Thanks, It’s a very interesting and nice sharing. I can see Watson Analytics is easy and quick for the practitioners can start the conversation with client.
On the other than, It’s only the start of entire story. We need to think further how to dive deeper to find insight that can bring values and build more attractive use cases. Believe the industry domain knowledge will be the critical part of the puzzle. Look forward to seeing the growth of social business.


Posted by: Tony Lin
 
June 18, 2015
3:03 am

I will be more interested in understanding the usage of Watson Analytic. I tried using it with few set of pre populated data. but I am not able to run the report


Posted by: Salahudeen
 
June 18, 2015
2:43 am

Watson and Twitter, awesome, its giving a deeper insight, and tells which product would really do good in which market. Movie is just an example. Thinking what this collaboration can do.


Posted by: Ashim Roy
 
June 17, 2015
6:56 pm

Very interesting read.


Posted by: Aldrin Pentero
 
June 17, 2015
1:09 pm

Great Article


Posted by: Soniya
 
June 17, 2015
9:19 am

Great article.


Posted by: Latitia
 
June 17, 2015
7:20 am

Superb experiential sharing from Watson Analytics.. looking forward to more interesting anecdotes in future, very exciting :)


Posted by: Bhanu
 
June 17, 2015
5:52 am

Building a smarter planet is a very informative blog. Thanks for the informative pieces.


Posted by: Rosy
 
June 17, 2015
5:49 am

Thanks for sharing this piece.


Posted by: Janet
 
June 17, 2015
5:47 am

Great analysis. Keep up


Posted by: Sarah
 
June 17, 2015
5:41 am

Great analysis. Keep up


Posted by: Tindi
 
June 17, 2015
5:36 am

Very informative, thanks for sharing.


Posted by: Sarah
 
June 17, 2015
4:46 am

Nice post on a topic of general interest. This showcases Watson’s capability in day to day life. (Do we have “pay per use” charging for Watson :) May be it can make help marketing teams to focus their campaigns or devise strategic interventions to move things in intended direction by finding gaps/observing trends/devise a new campaign around trend.
What I found missing was predictions but then may be I am asking for too much. The focus would have been just to see what trends emerge and share which is sufficient to raise the interest level and to present a facet of Watson.
Do keep sharing such pieces.


Posted by: Akhilesh
 
June 17, 2015
2:30 am

Although interesting, how does mining of similar info aid in business? What’s the real world implication? Does tweeting your opinion work in the favor of Universal Studios? This seems more a feather in the cap of those who created the promos for Jurassic World.
We’d like to see some real world implications, other than that this article doesn’t make for much than a kind of interesting read.


Posted by: Vik
 
June 17, 2015
2:06 am

Great analysis and piece of history. Awesome article.


Posted by: festus
 
June 16, 2015
1:22 pm

This is such an awesome article!! LOVE IT!! Jurrasic World is an incredible social success story – just also read the following about it on Adweek.com:

1. According to Moviepilot, the summer blockbuster added 353,000 Facebook fans last week, when it also generated 1.7 million tweets and 654,000 retweets.

2. What’s more, per Moviepilot, Jurassic World’s official trailer was viewed 5.8 million times last week on YouTube. In total, the action thriller’s clip—watch it below—has now been seen a whopping 66 million times since it was uploaded on Nov. 25.

Kudos to Universal Pictures’ social team behind all of these metrics.


Posted by: Samantha Klein
 
June 16, 2015
11:37 am

Considering the weekend opening, I would be interested in seeing the stats now


Posted by: Pamela Wetmore
 
June 16, 2015
11:30 am

Hi Jon, I fully share your thoughts, I’m convinced that Watson Analytics is able to dig much deeper into a topic.


Posted by: Jens Kraenzler
 
June 16, 2015
10:24 am

To take @Steen’s comments even further, maybe there is a certain TYPE of person who chooses to post their feelings on Twitter. This would skew the results and make a comparison to the population as a whole less meaningful.


Posted by: DG
 
June 16, 2015
9:20 am

While I do not doubt the enormous potential in Watson analytics I am not impressed with this twitter breakdown.
The previous entry by ‘TE’ says it pretty well.
Maybe twitter is just hard to decode – a lot of one-liners and more than average use of irony and sarcasm is probably not the best material to work with.
Also I think there would be vast cultural differences in how people express themselves on twitter.


Posted by: Steen T Petersen
 
June 16, 2015
8:54 am

very interesting, I was never knowing that Watson is so powerful and also not knowing that Twitter data can be handled so well to get the so real trend. Its very useful for business or for any social awareness
I feel we should not do more such data study like this and awake the world for change


Posted by: Deepak Srivastava
 
June 16, 2015
6:30 am

Its a very interesting data.


Posted by: Esther
 
June 16, 2015
5:19 am

This brings me into the ground of business analytics, even it’s only some very basic information. There are so many aspects to consider


Posted by: Eric Chao
 
June 16, 2015
1:04 am

This is really amazing. There is so much potential with what we can do with business analytic with the surge of data available in the hyper connected world


Posted by: Ibad ur Rehman
 
June 15, 2015
11:13 pm

Something that caught my attention was the two countries with more Authors: Chile, a country with 17M in total population (California has twice that population) and then Mongolia with barely 3M people.

Intermediately one will think either the movie was going to be total fiasco, since the large markets were not commenting much about it, or Twitter data is nor really an good indicator or Movie trends!! ?

Now that the movie has been released, the reality is quite the opposite. The film brought in a record breaking box office $524M around he world this past weekend, making it the highest-grossing global opening ever, and $208M in the US, setting also a record.

The later makes you wonder if twitter chatter is a good indicator, and/or if all Chileans and Mongolians went to the movies this past weekend?

TE


Posted by: TE
 
June 15, 2015
4:36 pm

Watson Analytics is designed to introduce analytics to people who generally do not use analytics. The point is that it builds visualizations automatically based on data that is uploaded into it or that it can connect to. If you were analyzing 25,000 tweets in a spreadsheet, would you necessarily be able to discern that New Orleans was the urban area with some of the most positive tweets about the movie? Both Suman and I learned some new things about what people were saying about the movie before it was released. Personally, I would never have guessed that the most tweets about the movie would be coming out of Chile and Mongolia. another feature of Watson Analytics. I thank you all for the comments and invite you to try Watson Analytics yourself: http://www.watsonanalytics.com


Posted by: Forsyth Alexander
 
June 15, 2015
12:22 pm

There is always a risk putting out future looking post like this one that can be easily validated by just waiting it out. OK so neither the Twitter itself nor the analytics got right about the movie’s huge opening far exceeded industry predictions. The summer box office is still young and there are over 10 money making machines in the lineup. I would encourage the authors to continue publishing their findings so they are given the chance to prove the value of Watson Analytics (or the value of Twitter, which just replaced its CEO.)


Posted by: Y C
 
June 15, 2015
11:50 am

Agree with previous post… I seem to be missing the “really interesting insights” or “predictive” parts. With $204M in sales, at $8 per ticket, one can estimate between 20-25M viewers. Granted, many more probably saw the trailers/previews – which explains the comments in February through May… The number of tweets reviewed seem to be less than 100k… Perhaps women commented more because of Chris Pratt, good looking and of Norwegian descent?


Posted by: Dennis Tirado
 
June 15, 2015
9:53 am

I found this article to be extremely interesting, especially having studied the IBM and Twitter Think Academy coursework. But I agree it might have been more impressive had Watson Analytics been able to project the first weekend’s box-office earnings. That’s not to minimize what this excercise showed about our ability to parse Twitter data and demonstrate trends.


Posted by: Oskar Back
 
June 15, 2015
7:35 am

Only neutral sentiment was expressed in Arabic and in Ukrainian. – if I am the producer/distributor of this movie how would this analytic point help me maximise my takings from these countries?


Posted by: shankar K
 
June 15, 2015
6:54 am

A couple of points in response to some comments;
Firstly, Watson Analytics is not Watson, the name comes from the fact it shares some cognitive DNA. The value in Watson Analytics is 3 things; the rapid, flexible and intelligent visualisation and automated data comprehension (a non-official term I just invented for the ability of the platform to recognise concepts like sales/revenue, geography, time), the simplicity of getting to predictive insights and the ability to share data driven insights from both those sources in a fast intuitive way with colleagues and others. While the value in Watson (sans Analytics) is in the digestion, contextualisation and cross referencing of immense volumes of data, particularly non-structured textual data.

Secondly – I agree that the insights in this are fairly shallow but is there another way to do these things;
1. access and filter the vast volume of twitter with nothing more than a couple of clicks?
2. recognise sentiment across that volume of data in seconds (it’s much more than just grepping “love” vs “hate”)
3. correlate geography, gender, influence (number of followers and retweets), over time all automatically so you can relate to real world events on an adhoc basis whenever you want?

imho, the best use cases come with insights into the reaction to real events and the value comes from the actions taken in response to those insights. A movie release is a big event for Universal (in this case) and I’d be interested in how box office takings have gone in the countries with disproportionate levels of tweets. What would that tell them and what could they do differently to improve results?

Finally, is there anyone who has generated a graph in Excel with a couple of clicks and then NOT spent 4 hours trying to get it to illustrate what they actually want to show? ;)


Posted by: Rob Hayden
 
June 15, 2015
5:31 am

Would be interesting to capture the perception based on the time at which the show is watched and compare it to another movie which is launched or to be Launched (may be from the same production)


Posted by: Rohit kumar Cherukuri
 
June 15, 2015
4:50 am

Really found interesting analytic data !! :)


Posted by: Manoj
 
June 15, 2015
2:46 am

Have watched the trailer, Its going to be hit. Another powerful analytic tool.


Posted by: Cavs
 
June 15, 2015
2:21 am

Its interesting as other commentators have said, the example is a bit facile, or the example isn’t taken near far enough to demonstrate anything much except ease of use. In other words, the insights revealed aren’t near deep enough,nor aligned to some specific business value outcome.


Posted by: Walter
 
June 14, 2015
9:28 pm

Twitter is more machine than human. Analytics is based on what?


Posted by: Santosh C J
 
June 14, 2015
2:34 pm

The link to the Jurassic World website needs to be fixed.


Posted by: Bob
 
June 13, 2015
4:00 pm

Amazing how easy it is to know the sentiment from Twitter chatter for a group of people on any #….


Posted by: Lilian Wu
 
June 12, 2015
6:46 pm

What’s really amazing to focus on here is how the data was brought together to create some seriously interesting analytic data. Well Done!


Posted by: Telematic Controls
 
June 12, 2015
3:25 pm

The Data Analytics creating the base for the Jurassic Future


Posted by: Kamal Sewani
 
June 12, 2015
8:31 am

Women lead in social network because they are good at multitasking.


Posted by: Ronoh Robert
 
Post a Comment