Define the credibility of any post offering a job or internship entered by analysing posts on Online Social Media. Concepts of Data Collection and Storage, Data Filtration and Classification and Data Analysis and Clustering were used throughout the project.
- Data was extracted from Facebook using Facebook API in the form of textural posts
- Filtered and classified using the Naive Bayes Classifier and the NLTK python library into useful and spam posts.
- Finally important and valuable results from data collected were analysed and represented using word clouds and bar graphs.
- New posts entered will be classified into spam or non-spam i.e. ham.
- Anshita Gupta
- Chhavi Gupta
- Raunak Jain
This project is licensed under the terms of the MIT license.