by Josh Andres, User Experience, Design,
Human Computer Interaction, IBM Research-Australia
What do 3-D printing, Twitter, and the sport of
cricket have in common? Probably not a whole lot to most people. But IBM
intern Rohit Ashok Khot and I have been experimenting with ways to explore the
benefits of visualizing personalized sports summaries in a tangible, 3-D form,
here in IBM’s research lab in Melbourne. Basing our study on a cricket series
between Bangladesh and India – two “heavy hitters” in the cricket world – we
combined the power of real-time analytics and social media with the
possibilities of 3-D printing.
Cricket is rich with data and trackable statistics
like overs, runs, and wickets taken, and social media has changed the way
people can follow along and contribute to the discussion of a match in real
time. So, we worked with cricket fans to determine which key metrics from a
match they would be most interested in, and began sketching out various designs
of models for a tangible summary of the match in 3-D printed form. In order to
investigate social media data and tangible visualizations, we thought of using
Twitter for its reach and simplicity, and then explored how we could make
visualizations more relevant and personal to users.
We followed three matches live on Twitter, as a test
group of 10 Twitter-using cricket fans incorporated the hashtag #BANvIND into their tweets about the
match action, in order to identify the relevant tweets for our experiment.
Cricket is big in Australia, and there are large communities of Indians and
Bangladeshis here, so we knew there would be a good following. The hashtag is
part of the Twitter ecosystem – users would be familiar, and we just tagged
along for the ride.
Rohit, who is working on his Ph.D. at RMIT in their
Exertion Games Lab, and I were able to extract game data to design and create a
3-D model using OpenJSCAD software. As the two teams batted and bowled, we
collected tweets over time to categorize and qualify based on “sentiment” – the
emotional state of the user behind the tweet. We followed the scoring in terms
of wickets taken and sixes scored as the match ebbed and flowed.
The 3-D print-out was where all of our analysis came
together. The base of the print, made of plastic, is a data model of the match
that provides a chronological summary in terms of runs scored (represented by a
large circle in the outer end of the spike) and the wickets taken (a smaller
circle in the inner part of the spike). Each bar represents a time period of
five “overs,” or set of five deliveries by the bowler (think “pitches” in
baseball). The second part of the print, and what makes it personal, is a
flower-shaped user excitement model.
The longer peak in the model denotes high
excitement levels amongst users, and the thickness of each “excitement spike”
denotes the volume of tweets during that over.
We took away a number of design themes to apply to
future studies featuring tangible models, and we have submitted this study for
publication. The participating fans enjoyed seeing their tweets and a match
summary in tangible form, and definitely enjoyed having the 3-D print-out as a
keepsake of the match. Their engagement was strongly dependent upon on the
excitement in the match and their attachment to the two teams.
This was an exciting application of social media
analysis for both of us, and for Shalia Pervin, an Internet of Things
expert and member of the Real Time Analytics group at the lab in Melbourne who
participated in the study. During a sporting event, fans broadcast their
emotions through their tweets.
So for us, exploring
user sentiment analysis in relation to the cricket match was a great
opportunity to create something truly unique for each individual through our
3-D printing technology. We plan to continue investigating social media data
and tangible visualizations through other platforms, sports, and user contexts.
We’re excited about the possibilities 3-D printing holds, especially as new
materials are developed.
Labels: 3D printing, ibm research - australia, sentiment analysis, social analytics