**Dataset Information:** Training Data consist of the following information about many different tweets, and is stored in Tabular data. Following are features describing the tweet:

1. Identity: a number assigned to each tweet
2. Text: Main body of the tweet.
3. Header: title/Header of a tweet
4. Type_of_tweet : [ 1 if is from source tweet, 0 is from branch tweet of source tweet ]
5. Screen_and_username Displayed name of the account holder, who tweeted.
6. Num_followers: number of followers of the account holder.
7. Num_friends: number of friends of the account holder.
8. Num_retweets: number of retweets of the tweet involved.
9. tweet_language: the language of tweet involved.
10. Rumour_identification: [1 if it is rumour, 0 if not a rumour] (Needed to be predicted for Test_Data.csv)