An Open Source System for Crowd Sourcing an African Language Short Story Corpus

Abstract

Many African languages are under resourced in having open access corpora for use in developing technological applications such as grammar checkers, spell checkers, speech to text, text to speech and machine translation tools. This may lead to a decline in all cultural traits associated with the peoples that speak these languages. To enable collection of textual corpora and long term preservation of positive cultural characteristics, the design considerations and implementation of an open source online short story competition collection and evaluation system are described. The system is written in PHP and can be relatively cheaply deployed on shared hosting servers available from many African hosting providers. This allows for the possibility of a decentralized collection of stories, as well as adaptation and improvements of the software to different types of short story competitions. The software has been used for two short story competitions across the African continent with the aim of providing stories suitable for children. Holding the competition online has enabled participation from a wide variety of locations, but most of the submissions have came from African countries with relatively good information technology infrastructure. Preparation for a third competition is in progress.