DATA: Data Assembler for Text Analysis

<< Below is an abstract of the ongoing DATA project in collaboration with the IIIT-Delhi.

The DATA project intends to facilitate computer-assisted textual analysis of political discourses in India. It aims at developing a range of semi-automated management tools in Python/R. They are designed at structuring large quantities of text for further statistical analysis (e.g. topic modelling, cooccurrences, sentiment analysis). Additionally, it contributes to the building and categorising of a unique dataset of Prime Ministerial discourses since independence.