loading
Papers

Research.Publish.Connect.

Paper

Authors: Ioanna Kyriazidou 1 ; Georgios Drakopoulos 2 ; Andreas Kanavos 1 ; Christos Makris 1 and Phivos Mylonas 2

Affiliations: 1 CEID, University of Patras, Patras, Hellas and Greece ; 2 Department of Informatics, Ionian University, Kerkyra, Hellas and Greece

ISBN: 978-989-758-386-5

Keyword(s): Social Analytics, Digital Influence, Digital Trust, Verified Account, Document Databases, MongoDB, Convolutional Network, Logistic Regression, Keras, Pandas, TensorFlow.

Related Ontology Subjects/Areas/Topics: Social Media Analytics ; Society, e-Business and e-Government ; Web Information Systems and Technologies

Abstract: 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 t he 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. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.232.51.247

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kyriazidou, I.; Drakopoulos, G.; Kanavos, A.; Makris, C. and Mylonas, P. (2019). Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras.In Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-386-5, pages 25-33. DOI: 10.5220/0007810200250033

@conference{webist19,
author={Ioanna Kyriazidou. and Georgios Drakopoulos. and Andreas Kanavos. and Christos Makris. and Phivos Mylonas.},
title={Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras},
booktitle={Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2019},
pages={25-33},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007810200250033},
isbn={978-989-758-386-5},
}

TY - CONF

JO - Proceedings of the 15th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with Keras
SN - 978-989-758-386-5
AU - Kyriazidou, I.
AU - Drakopoulos, G.
AU - Kanavos, A.
AU - Makris, C.
AU - Mylonas, P.
PY - 2019
SP - 25
EP - 33
DO - 10.5220/0007810200250033

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.