/nlp-project

Text mining and analysis on health discussions on Suomi24 online forum

Primary LanguagePythonApache License 2.0Apache-2.0

Suomi24: Mining Health Discussions

Text mining and analysis on health discussions on suomi24.

About the project

This project concerns a rough exploration of the Finnish Suomi24 dataset in order to map the discussions related to health, answering the questions: What are the main health issues that much interest citizens? What are their key worries, inspirations? How such worries, inspirations are manifested in the forum?

Requirements

  • virtualenv
  • python3
  • java
  • download stanford named entity taggger and unzip it in stanford folder: stanford-ner-2018-10-16

Getting Started

Clone the Repository As usual, you get started by cloning the project to your local machine:

git clone git@github.com:moamenibrahim/nlp_project.git
cd nlp_project/

Create a virtual enviroment in the current project folder using python3

virtualenv -p python3 venv
source venv/bin/activate
pip install -r requirements.txt
./init.sh

Authors