Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras

Ioanna Kyriazidou, Georgios Drakopoulos, Andreas Kanavos, Christos Makris, Phivos Mylonas


Digital influence and trust are central research topics in social media analysis with a plethora of applications ranging from social login to geolocation services and community structure discovery. In the evolving and diverse microblogging sphere of Twitter verified accounts reinforce digital influence through trust. These typically correspond either to an organization or to a person of high social status or to netizens who have been consistently proven to be highly influential. This conference paper presents a framework for estimating the probability that the next mention of any account will be to a verified account, an important metric of digital influence. At the heart of this framework lies a convolutional neural network (CNN) implemented in keras over TensorFlow. The training features are extracted from a dataset of tweets regarding the presentation of the Literature Nobel prize to Bob Dylan collected with the Twitter Streaming API and stored in MongoDB. In order to demonstrate the performance of the CNN, the results obtained by applying logistic regression to the same training features are shown in the form of statistical metrics computed from the corresponding contingency matrices, which are obtained using the pandas Python library.


Paper Citation