/Tweet_collusive-or-genuine

This project was the part of IIIT Delhi assignment submission.

Primary LanguagePythonApache License 2.0Apache-2.0

Twitter data sets to analayze whether the tweet is collusive or genuine

Online media platforms have enabled users to connect with individuals, organizations, and share their thoughts. Apart from social connectivity, these platforms also help in getting information about different topics of interest, promoting our opinions/interests, etc. Those who are involved in business/politics, in order to top their game, it is mandatory for them to increase their reputation in online media. Since the natural way of gaining social growth is cumbersome, unfair ways to boost the reputation come into the light and we refer to this phenomenon as collusion in online media. For example, individuals/organizations that need a wider reach in the audience, approach blackmarket services to boost their social growth in an artificial way. Blackmarket services provide online media services ranging from online social networks to various other platforms such as rating platforms, video-sharing platforms, and even recruitment platforms thereby creating an inadequate social space. In this project we have used the the tools of machine learning and data science and to predict whether a tweet is collusive or genuine.
This uses a model developed in python using nltk library of NLP.

How to run the code

  1. Run the python file (.py file) in Jupyter Notebook
  2. There are no dependencies