Project Description

Our project will be a language processing tool that allows users to easily analyze online or uploaded text using common text processing algorithms for topic modelling, sentiment, and comparative word frequency analyses. We hope to make it available both as a web application and browser extension. The web framework will be done through Angular for the frontend and Django for the backend. The tool will be available for anyone to use for free, but will primarily be developed for digital humanities researchers. The primary goal is to make already created text-processing libraries available to researchers (and curious readers) who would otherwise not be able to use it. The tool will likely highlight or underline text words that the algorithm defines as critical to the meaning of the text (eg: in a term frequency analysis, the terms that show up the most; in a sentiment analysis, the words that are strongly associated with particular sentiments, in a topic modelling analysis, the words that provide the strongest information about the content of the text, etc.), and will provide more information if the user clicks on the underlined or highlighted text.