Are you ready for the DataKind Bangalore Sprint 2018?

Posted by Remya Padmadas on June 04, 2018

Do you love data? Do you believe algorithms can help decide what to binge watch on Netflix next and drive social change ? DataKind is an organisation that ‘brings together top data scientists with leading social change organisations to collaborate on cutting-edge analytics and advanced algorithms to maximize social impact.’ To describe the mission of DataKind in the words of it's co-founder, Jake Porway: "We are meticulously focused on bringing data science in all its forms to those who share our vision of a sustainable planet in which we all have access to our basic human needs. We envision a world where organizations tackling those problems have the same access to data science resources that Wall St. and Silicon Valley have."

StoryWeaver is one of four projects chosen for DataKind Bangalore’s Sprint 2018. Sprint consists of a series of events where volunteers of DataKind Bangalore use their Data Science skill to solve challenges experienced by their Non-profit partners. If you’d like to volunteer your skills to our project, read on for more details.

Using technology to address the global book drought

Pratham Books is a non-profit children’s book publisher with a mission is to see ‘a book in every child’s hand’ and was founded to address the lack of high quality, affordable, multilingual books in India. 


However, to even begin satisfying the reading needs of a multilingual country such as India, and create equitable access to books for all children we would need to massively scale the creation and distribution of multilingual content. The answer, we believed lay in technology and the power of open licensing.  

StoryWeaver: One platform. Many possibilities.

On StoryWeaver, users can access thousands of multilingual stories for children absolutely free. All content on the platform is openly licensed under CC-BY4.0, one of the most liberal Creative Commons Licenses. Users can read, download and print all stories and images on the platform, as well as use the tools embedded on StoryWeaver to create and translate content into more languages and versions. In the 2 years since launch we have grown from a repository of 800 stories in 24 languages to a digital repository of over 8000 stories in 111 diverse languages of the world. The 650,000 member strong StoryWeaver community is spread across 220 countries and have read our stories both online and offline over 2.6 million times.  

Project Scalability and Sustainability

StoryWeaver’s growth and ability to scale lies in the fact that the platform is Unicode compliant. This enables content to be transported to different devices easily, and also allows users to create content in their desired language without needing to download special Indic language keyboards. This is imperative, especially in a country like India where there are so many languages in varied scripts.

In addition, Unicode compliancy  has allowed us to add new languages with relative ease, even those with complex scripts like Khmer. Today, StoryWeaver offers users the chance to read, create and translate stories in a plethora of languages: from mainstream Indian and International languages, to tribal (Kora, Santali, Kurukh) and minority languages (Tibetan, Konkani), and even languages categorised as threatened or endangered (Southern Kurdish).


StoryWeaver has opened up a stream of collaborations with organizations, both in India and globally.

As a classroom tool, StoryWeaver provides educators access to thousands of stories, across genres, reading levels and in multiple languages, for use in the classroom. Teachers can tailor existing content to suit the needs of their students or create brand new teaching resources. Educators have used the platform to create early reading material in minority languages like Tibetan and endangered languages like Kurdish. Rural schools in Maharashtra have downloaded and projected our stories on to classroom walls with the help of Pragat Shikshan Sanstha. Communities Rising downloads and prints much needed books in Tamil and English for after school resource centres in Villupuram, Tamil Nadu. While organisations and schools like Mantra4Change, Akanksha and Tamarind Tree  create digital libraries for students and teachers using our content. Content from StoryWeaver has also been gamified on affordable learning apps for disadvantaged children to improve their English, while Bookshare uses StoryWeaver to create accessible content for print impaired children.

By harnessing the power of technology and open licenses and adding the creative power of a collaborative and engaged community, StoryWeaver is working towards addressing the scarcity of multilingual reading resources that exists not only in India but across the world.

Focus Area For DataKind Sprint

As content on StoryWeaver continues to exponentially grow, one of the spaces we wish to improve in is the discoverability of our content. Users on our platform should be able to easily find what they are looking for in our vast repository of 8000 books.

This will be possible with better tagging of our content. While there is a basic tagging process in place for all images and stories on platform, if every story published is automatically tagged with 10 - 25 relevant keywords, it would drastically improve the discoverability of content. Additional steps would include incorporating the most searched words in our tags and even incorporate geotags. We strongly believe these steps would greatly improve the user experience.

StoryWeaver would like to collaborate with DataKind Bangalore to build such a tool during Sprint 2018.

For more details about the Project Accelerator (First event of the Sprint) and to sign up, visit their meetup page here. Also, You may like to join DataKind Bangalore’s slack channel  #pratham_books to actively participate in various discussions.