no code implementations • 25 Mar 2024 • Rabindra Lamsal, Maria Rodriguez Read, Shanika Karunasekera
Tasks such as semantic search and clustering on crisis-related social media texts enhance our comprehension of crisis discourse, aiding decision-making and targeted interventions.
no code implementations • 7 Dec 2023 • Fengze Sun, Jianzhong Qi, Yanchuan Chang, Xiaoliang Fan, Shanika Karunasekera, Egemen Tanin
Our model is powered by a dual-feature attentive fusion module named DAFusion, which fuses embeddings from different region features to learn higher-order correlations between the regions as well as between the different types of region features.
no code implementations • 11 Sep 2023 • Rabindra Lamsal, Maria Rodriguez Read, Shanika Karunasekera
Additionally, we investigate the impact of model initialization on convergence and evaluate the significance of domain-specific models in generating semantically meaningful sentence embeddings.
no code implementations • 18 May 2023 • Amila Silva, Ling Luo, Shanika Karunasekera, Christopher Leckie
Also, we propose a novel technique to construct news datasets minimizing the latent biases in existing news datasets.
1 code implementation • 29 Aug 2022 • Zainab Zaidi, Mengbin Ye, Fergus John Samon, Abdisalam Jama, Binduja Gopalakrishnan, Chenhao Gu, Shanika Karunasekera, Jamie Evans, Yoshihisa Kashima
While pro-vax tweets (37 million) far outnumbered anti-vax tweets (10 million), a majority of tweets from both stances (63% anti-vax and 53% pro-vax tweets) came from dual-stance users who posted both pro- and anti-vax tweets during the observation period.
no code implementations • 23 Jun 2021 • Yasmeen George, Shanika Karunasekera, Aaron Harwood, Kwan Hui Lim
First, to address the challenge related to the unknown spatial resolution of events, a quad-tree method is exploited in order to split the geographical space into multiscale regions based on the density of social media data.
no code implementations • 11 Feb 2021 • Amila Silva, Ling Luo, Shanika Karunasekera, Christopher Leckie
Hence, this work: (1) proposes a novel framework that jointly preserves domain-specific and cross-domain knowledge in news records to detect fake news from different domains; and (2) introduces an unsupervised technique to select a set of unlabelled informative news records for manual labelling, which can be ultimately used to train a fake news detection model that performs well for many domains while minimizing the labelling cost.
no code implementations • 23 Jul 2020 • Amila Silva, Shanika Karunasekera, Christopher Leckie, Ling Luo
To address this problem, we present METEOR, a novel MEmory and Time Efficient Online Representation learning technique, which: (1) learns compact representations for multi-modal data by sharing parameters within semantically meaningful groups and preserves the domain-agnostic semantics; (2) can be accelerated using parallel processes to accommodate different stream rates while capturing the temporal changes of the units; and (3) can be easily extended to capture implicit/explicit external knowledge related to multi-modal data streams.
2 code implementations • 7 Jul 2020 • Yi Han, Shanika Karunasekera, Christopher Leckie
(2) GNNs trained on a given dataset may perform poorly on new, unseen data, and direct incremental training cannot solve the problem---this issue has not been addressed in the previous work that applies GNNs for fake news detection.
no code implementations • 18 Jun 2020 • Amila Silva, Ling Luo, Shanika Karunasekera, Christopher Leckie
OMBA jointly learns representations for products and users such that they preserve the temporal dynamics of product-to-product and user-to-product associations.
no code implementations • 11 Feb 2020 • Yi Han, Shanika Karunasekera, Christopher Leckie
Events detected from social media streams often include early signs of accidents, crimes or disasters.
no code implementations • 23 Oct 2019 • Amila Silva, Shanika Karunasekera, Christopher Leckie, Ling Luo
Building spatiotemporal activity models for people's activities in urban spaces is important for understanding the ever-increasing complexity of urban dynamics.
no code implementations • 14 Mar 2016 • Seyed Morteza Mousavi, Aaron Harwood, Shanika Karunasekera, Mojtaba Maghrebi
To improve the quality of the extracted SVLs, instead of using NNQ, we label the visited locations as the IDs of the POIs which geometrically intersect with the GPS observations.