Predicting Information Diffusion on Twitter a Deep Learning Neural Network Model Using Custom Weighted Word Features

Abstract : Researchers have been experimenting with various drivers of the diffusion rate like sentiment analysis which only considers the presence of certain words in a tweet. We theorize that the diffusion of particular content on Twitter can be driven by a sequence of nouns, adjectives, adverbs forming a sentence. We exhibit that the proposed approach is coherent with the intrinsic disposition of tweets to a common choice of words while constructing a sentence to express an opinion or sentiment. Through this paper, we propose a Custom Weighted Word Embedding (CWWE) to study the degree of diffusion of content (retweet on Twitter). Our framework first extracts the words, create a matrix of these words using the sequences in the tweet text. To this sequence matrix we further multiply custom weights basis the presence index in a sentence wherein higher weights are given if the impactful class of tokens/words like nouns, adjectives are used at the beginning of the sentence than at last. We then try to predict the possibility of diffusion of information using Long-Short Term Memory Deep Neural Network architecture, which in turn is further optimized on the accuracy and training execution time by a Convolutional Neural Network architecture. The results of the proposed CWWE are compared to a pre-trained glove word embedding. For experimentation, we created a corpus of size 230,000 tweets posted by more than 45,000 users in 6 months. Research experimentations reveal that using the proposed framework of Custom Weighted Word Embedding (CWWE) from the tweet there is a significant improvement in the overall accuracy of Deep Learning framework model in predicting information diffusion through tweets.