Text Analytics Applied to Indian Politics

Due to the advent of data explosion, there is an emerging need to collect, monitor, analyse, summarize, and visualize politically relevant information from social media and other online sources. In order to analyse such an open and unstructured domain, it is essential to employ generic and robust methods to procure, integrate, store, and analyse large amounts of text-based data from multiple sources and contexts. The Indian political system remains largely unanalysed, mainly owing to the unavailability of structured textual data openly accessible by the public. In this article, we present a cloud-based text analysis platform built to serve as a viable solution to the problem. The platform enables the procurement, integration, storage, and analysis of large text-based data sets from multiple sources and domains. We have applied this platform to analyse the Indian political ecosystem.