Building a Crowd-sourcing App in Facebook to Convert Unstructured Historical Content into Linked Open Data: a Case Study for Regreening Africa

From Master Projects
Jump to: navigation, search


About Building a Crowd-sourcing App in Facebook to Convert Unstructured Historical Content into Linked Open Data: a Case Study for Regreening Africa

  • This project has been fulfilled.
  • This project fits in the following Bachelor programs: {{#arraymap:|, |xXx|bachelorproject within::xXx|,}}
  • This project fits in the following masterareas: {{#arraymap:Information Sciences, Multimedia, Internet and Web Technology, Computational Intelligence and Selforganisation, Knowledge Technology and Intelligent Internet Applications|, |xXx|project within::xXx|,}}


Description

(this is a follow-up on a previous project in which a prototype app was built and partly evaluated)

Linked Data is a collective strategy to make available (raw) data on the Web for general purposes. It is not merely a philosophy: it is supported by mature Web-based technologies. These technologies are free and highly standardised, which will ensure an accelerated growth of a Linked Data Web. Much potentially useful data however today is locked on written paper. For example, governments in the Sahel region have recorded 1000s of pages of data about rainfall in their region. This data could be fruitfully combined with socio-agricultural data to support decisions in the re-greening initiatives.

There are a number of techniques to automate the conversion (like OCR) but they are very error-prone and require a lot of configuration. The Web however offers ways to mobilize crowds of people that could do the job manually given they are offered the right incentives. In this thesis you will build a crowd sourcing app in a popular social network such as Facebook. The app grants reputation (with rewards and badge) for contributing to tasks converting parts of documents into digital format. It will be important to devise the right size of the tasks. There should be a strong focus on HCI component to maximize the take up of the app; hence the effectivity of the crowd sourcing. You will involve experts in regreening to see which documents should be prioritized and what is the desired digital output format.