1 code implementation • 11 May 2022 • Rabab Alkhalifa, Elena Kochkina, Arkaitz Zubiaga
Therefore an ability to predict a model's ability to persist over time can help design models that can be effectively used over a longer period of time.
no code implementations • 1 Sep 2021 • Rabab Alkhalifa, Arkaitz Zubiaga
Social media platforms provide a goldmine for mining public opinion on issues of wide societal interest and impact.
no code implementations • 31 Aug 2021 • Wenjie Yin, Rabab Alkhalifa, Arkaitz Zubiaga
There is however a gap in the longitudinal study of how sentiment evolved in social media over the years.
1 code implementation • 27 Aug 2021 • Rabab Alkhalifa, Elena Kochkina, Arkaitz Zubiaga
We propose a novel approach to mitigate this performance drop, which is based on temporal adaptation of the word embeddings used for training the stance classifier.
no code implementations • 5 Nov 2020 • Rabab Alkhalifa, Adam Tsakalidis, Arkaitz Zubiaga, Maria Liakata
In this paper, we present the results and main findings of our system for the DIACR-ITA 2020 Task.
no code implementations • 2 Nov 2020 • Rabab Alkhalifa, Arkaitz Zubiaga
This paper presents our submission to the SardiStance 2020 shared task, describing the architecture used for Task A and Task B.
no code implementations • 30 Aug 2020 • Rabab Alkhalifa, Theodore Yoong, Elena Kochkina, Arkaitz Zubiaga, Maria Liakata
The purpose of this task is to determine the check-worthiness of tweets about COVID-19 to identify and prioritise tweets that need fact-checking.