In 2019, more than 600 million voters cast their ballots in the world's largest election. Due to high illiteracy rates, India’s election commission historically has assigned visual symbols to political parties to help voters identify their candidate of choice.
These symbols include everyday items like a flower, an elephant.. and even a USB stick. To mark this major event, Al Jazeera created its first ever machine learning news game which challenged our digital audience to draw some of India's 2,300 political party symbols.
The results were enjoyable and insightful and demonstrated that innovative technology can engage global audiences.
One of the big discussions in 2019 was how newsrooms could innovate with technologies such as Machine Learning (ML) and Artificial Intelligence (AI).
These technologies can provide tremendous opportunities for journalists but, like any other technology, must have the right story to complement them.
As Al Jazeera Digital, one of our key considerations when producing data-driven pieces is always to ask ourselves how we can use them to amplify cultural and human stories from the global south to a global audience.
Following its launch, this interactive game quickly became one of our highest engaged stories on our website and across social platforms, specifically on Facebook. Tens of thousands of users from all over the world competed with one another in drawing a variety of symbols ranging from an elephant to a bicycle – and viewers from India challenged each other to draw their party symbols and to learn the meaning behind these symbols.
For digital storytellers these techniques open up new doors to experiment with formats that are more interactive and non-linear. This is vital given new techniques that often are considered out of reach for most news organizations. The interactive game, produced and developed over the course of three weeks by a single data journalist using open-source technologies, further makes the case that machine learning can combine with storytelling and that it is accessible to newsrooms. It can also be inexpensive.
The entire drawing experience can be run on a mobile phone (using your finger) or on a desktop device (using a mouse). No standalone mobile app needs to be downloaded – users simply can open the link and start playing.
The UI experience for the game was built using React.js, a Javascript framework that powers the drawing canvas and assigning scores for drawing the correct symbols.
With thousands of plays from viewers all over the world, the success of this project opened important possibilities for future machine learning based stories expected to become an integral part of the data-driven newsroom.
The biggest takeaway from this project is that machine learning can have its place in every data journalist's toolbox. As machine learning and artificial intelligence increasingly plays a role in journalism it is important for data journalists to experiment with new storytelling techniques that captivate global participation and engagement.
