360Giving Data Visualization challenge

http://www.xavigimenez.net/360giving-grantmaking-themes

360Giving invited developers, researchers and anyone with an interest in the data to use its dataset to develop and visualise innovative solutions to two key questions facing the grantmaking sector.
Awarded with the 1st prize, this visualization provides insights around an strategic question: Who has funded what themes throughout the years?


360Giving launched a Data visualization challenge to answer questions to help funders to maximize their impact on the charitable causes they support. Such questions intend to give a better understanding of the grantmaking sector.

Here we look at one specific question, and by using Natural Language Processing techniques (Topic Modelling) we automatically discover the hidden thematic structure from the textual descriptions of its almost 500K of grant documents and provide an interactive visualization to answer strategic questions.


Discovering topics into unstructured data

With the text mining approach of Topic Modelling, given a corpus of unstructured text documents (e.g. news articles, tweets, etc) and without a prior annotation, a set of topics was obtained, each of which is represented by a set of top-ranked terms for the topic and associations for documents relative to the topic. In our case, here the text documents are the text fields that describe each grant (title and description). From that textual information, themes will emerge as well as the relativeness of the grants to each theme.


Top funding organizations

Selecting a specific topic reveals a more fine-grained analysis of the top contributors to the theme, analysing the granting activity by differents aspects, as the number of grants, the amount awarded and the relatedness of the grants to an specific topic.


The project also offers a detailed view of the grantmaking activity given an specific funder, revealing some pattern throught the time and highlighting those topic with more grantmaking activity.