Text analysis is a fascinating field that attracts people from several, often distant, scientific fields. As of today, text analysis is executed through powerful scripts scattered in many packages and libraries of different programming languages, each of which contains only a subset of available linguistic features and requires high technical knowledge to be operated. As a result, it is difficult to obtain a unified result with all desired features. Hence, many scientists, particularly those who lack a computer science background, are excluded from using them.
The goal of the project is to build a desktop GUI that provides its users with an easy way to extract quantitative text profiles from multilingual texts. The text analysis will come from scripts that combine many existing NLP packages written in R. The tool is modular and open source, in order to be easily accessible and adaptable to specific scientific needs. This project, which is rooted in the Google Summer of Code program, attempts to boost and facilitate research in the field of NLP and beyond, as it will make text analysis accessible to people with little to none computer science knowledge, such as linguistics students and scholars.
To download the installer, visit this and download "xtralingua.Setup.0.2.0.exe" under assets. Since this project is still in a pre-release phase, Windows and antivirus software might not recognise it as a valid application.
To install the application double-click the installer. The app will initialize right away. During first execution, you will need to provide the R's bin directory and a folder where R's packages are to be downloaded (we suggest using a new folder). After that, the required dependencies are going to be downloaded. Total size is ~500MB, so be aware that this step may take a while.
- Panagiotis Papantonakis (PanagiotisP)
- George Mikros (gmikros)
- Sotiris Leventis (sotirisleventis)
- Fotis Fitsilis (fitsilisf)