Given the title of a fake news article A and the title of a coming news article B, program classifies B into one of the three categories:
- agreed : B talks about the same fake news as A.
- disagreed : B refutes the fake news in A.
- unrelated : B is unrelated to A.
Basic preprocessing steps are required before using the data:
- Convert to Lowercase
- Remove punctuations
- Remove single character if any
- Remove stop words
- Convert numbers to words
- Lemmatization to get root words
Feature extraction approaches:
- Bag of words
- Similarity between text
- TF-IDF
Data modeling approaches:
- Naive Bayes
- Multinomial Logistic Regression
- Multi Layer Perceptron Classifier
Refer the report for further implementation details, approach, data preprocessing, feature extraction, data modeling and evaluation:
View Report
