Creation and evaluation of timelines for longitudinal user posts

Anthony Hills, Adam Tsakalidis, Federico Nanni, Ioannis Zachos, Maria Liakata


Abstract
There is increasing interest to work with user generated content in social media, especially textual posts over time. Currently there is no consistent way of segmenting user posts into timelines in a meaningful way that improves the quality and cost of manual annotation. Here we propose a set of methods for segmenting longitudinal user posts into timelines likely to contain interesting moments of change in a user’s behaviour, based on their online posting activity. We also propose a novel framework for evaluating timelines and show its applicability in the context of two different social media datasets. Finally, we present a discussion of the linguistic content of highly ranked timelines.
Anthology ID:
2023.eacl-main.274
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3791–3804
Language:
URL:
https://aclanthology.org/2023.eacl-main.274
DOI:
10.18653/v1/2023.eacl-main.274
Bibkey:
Cite (ACL):
Anthony Hills, Adam Tsakalidis, Federico Nanni, Ioannis Zachos, and Maria Liakata. 2023. Creation and evaluation of timelines for longitudinal user posts. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3791–3804, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Creation and evaluation of timelines for longitudinal user posts (Hills et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.274.pdf
Video:
 https://aclanthology.org/2023.eacl-main.274.mp4