Implementation Of The Random Forests Method On The Retweet Classification Model Based On Content

Abstract

Abstract
Twitter as one of the biggest social media on the internet has been used as the center of information exchangeon mainstream media. As this paper was written Covid-19 information sporadically propagated through twitter. To help spread validated information to the masses we need to understand which factors are relevant and support the information diffusion. In this paper author tried to find similarities between tweetsby using TF-IDF, author also applied content features from tweet’s meta-data to random forests classifier to predict which tweets users might retweet. The result of the shows that by using content features, machinelearning models can predict retweets from users. The proposed method of combining content features fromtwitter metadata and TF-IDF leads to a better model than the stand-alone features with 69.97% of accuracy.
Keywords: Retweet Prediction, TF-IDF, Random Forest