MeVer team tackling Corona virus and Conspiracies using Ensemble Classification

This paper presents the approach developed by the Media Verification (MeVer) team to tackle the task of Corona Virus and Conspiracies Multimedia Analysis Task at the MediaEval 2021 Challenge. We utilized ensemble learning and propose a two-stage classification approach that aims to overcome the challenge of the imbalanced and relatively small training dataset. We deal with the problem as binary classification in the first stage and in the second stage we predict the multi-labels. We experimented with fine-tuning pre-trained Bidirectional Encoder Representations from Transformers (BERT) and achieved a score of 0.294 in terms of the Matthews Correlation Coefficient (MCC), which is the official evaluation metric of the task. Additionally, leveraging on the proposed two-stage classification approach, we extracted a set of feature representations (BoW, TfIDF, embeddings) and classify them using traditional machine learning algorithms (Support Vector Machines, Logistic Regression) achieving in the best run a score of 0.292 of MCC. Copyright 2021 for this paper by its authors.

MeVer NetworkX: Network Analysis and Visualization for Tracing Disinformation

The proliferation of online news, especially during the “infodemic” that emerged along with the COVID-19 pandemic, has rapidly increased the risk of and, more importantly, the volume of online misinformation. Online Social Networks (OSNs), such as Facebook, Twitter, and YouTube, serve as fertile ground for disseminating misinformation, making the need for tools for analyzing the social web and gaining insights into communities that drive misinformation online vital. We introduce the MeVer NetworkX analysis and visualization tool, which helps users delve into social media conversations, helps users gain insights about how information propagates, and provides intuition about communities formed via interactions. The contributions of our tool lie in easy navigation through a multitude of features that provide helpful insights about the account behaviors and information propagation, provide the support of Twitter, Facebook, and Telegram graphs, and provide the modularity to integrate more platforms. The tool also provides features that highlight suspicious accounts in a graph that a user should investigate further. We collected four Twitter datasets related to COVID-19 disinformation to present the tool’s functionalities and evaluate its effectiveness. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

MeVer team tackling corona virus and 5G conspiracy using ensemble classification based on BERT

This paper presents the approach developed by the Media Verification (MeVer) team to tackle the task of FakeNews: Coronavirus and 5G conspiracy at the MediaEval 2020 Challenge. We build a twostage classification approach based on ensemble learning of multiple classification networks. Due to the imbalanced and relatively small dataset, our ensemble method leads to improved performance compared to a single classification model. We fine-tune pre-trained Bidirectional Encoder Representations from Transformers (BERT), one of the most popular transformer models, on the problem of Coronavirus and 5G conspiracy detection. Our approach achieved a score of 0.413 in terms of the Matthews Correlation Coefficient (MCC), which is the official evaluation metric of the task. © 2020 Copyright 2020 for this paper by its authors. All Rights Reserved.