Wickets, tweets, and a 3-D printer

Share this post:

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.

More stories

A new supercomputing-powered weather model may ready us for Exascale

In the U.S. alone, extreme weather caused some 297 deaths and $53.5 billion in economic damage in 2016. Globally, natural disasters caused $175 billion in damage. It’s essential for governments, business and people to receive advance warning of wild weather in order to minimize its impact, yet today the information we get is limited. Current […]

Continue reading

DREAM Challenge results: Can machine learning help improve accuracy in breast cancer screening?

        Breast Cancer is the most common cancer in women. It is estimated that one out of eight women will be diagnosed with breast cancer in their lifetime. The good news is that 99 percent of women whose breast cancer was detected early (stage 1 or 0) survive beyond five years after […]

Continue reading

Computational Neuroscience

New Issue of the IBM Journal of Research and Development   Understanding the brain’s dynamics is of central importance to neuroscience. Our ability to observe, model, and infer from neuroscientific data the principles and mechanisms of brain dynamics determines our ability to understand the brain’s unusual cognitive and behavioral capabilities. Our guest editors, James Kozloski, […]

Continue reading