A Deep CNN-GRU Framework for Personalized News Recommendation

News Recommendation Systems designed significantly for readers interest and there are number social networking sites like Twitter, Facebook, LinkedIn are popular nowadays. Users of these sites look popular news updates in that site itself instead of going to individual news websites. Our research work, gives the predominant solution for this problem. In this proposed work, a novel deep convolutional neural network based Word2Vec embedding technique is used along with GRU for recommending the news which is interested to the readers specially in twitter. In twitter, journalists of Republic, Times Now and BBC News India are used to post the news updates in the form of tweets and these tweets are collected then CNN along with Word2Vector embedding is preferred for feature extraction. All the aggregated features are given as input to the Gated Recurrent Unit which finds the highly preferred news and classifies the news for each user using softmax function. The proposed model is compared with various feature extraction techniques and computational approaches. Among these state-of-the-art techniques our proposed CNN with word2vec embedding technique provides the promising results with the F -Measure of 93.60%.