[HTML][HTML] Predicting and analyzing the popularity of false rumors in Weibo

Y Mu, P Niu, K Bontcheva, N Aletras - Expert Systems with Applications, 2024 - Elsevier
Malicious online rumors with high popularity, if left undetected, can spread very quickly with
damaging societal implications. The development of reliable computational methods for …

Examining temporal bias in abusive language detection

M Jin, Y Mu, D Maynard, K Bontcheva - arXiv preprint arXiv:2309.14146, 2023 - arxiv.org
The use of abusive language online has become an increasingly pervasive problem that
damages both individuals and society, with effects ranging from psychological harm right …

Evolving domain adaptation of pretrained language models for text classification

YS Chuang, Y Wu, D Gupta, R Uppaal, A Kumar… - arXiv preprint arXiv …, 2023 - arxiv.org
Adapting pre-trained language models (PLMs) for time-series text classification amidst
evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance …

Examining the limitations of computational rumor detection models trained on static datasets

Y Mu, X Song, K Bontcheva, N Aletras - arXiv preprint arXiv:2309.11576, 2023 - arxiv.org
A crucial aspect of a rumor detection model is its ability to generalize, particularly its ability to
detect emerging, previously unknown rumors. Past research has indicated that content …

Explicit Stance Detection in the Political Domain: A New Concept and Associated Dataset

AR Caceres-Wright, N Udhayasankar, G Bunn… - … Conference on Social …, 2024 - Springer
Stance detection, defined as the task of classifying an individual's attitude towards a target
person or concept, offers the potential to understand political opinions at scale using social …

Analyse, détection et quantification de la controverse dans les médias sociaux par l'utilisation de modèle d'apprentissage profond sur des données structurelles et …

S Benslimane - 2023 - theses.hal.science
Ces dernières années, l'utilisation massive des réseaux sociaux et le nombre im-portant
d'utilisateurs impliqués a été une source incontournable pour les études etanalyses, sur …

Combating misinformation on social media by exploiting post and user-level information

Y Mu - 2023 - etheses.whiterose.ac.uk
Misinformation on social media has far-reaching negative impact on the public and society.
Given the large number of real-time posts on social media, traditional manual-based …