Popularity Prediction of Online Petitions using a Multimodal DeepRegression Model

Kotaro Kitayama, Shivashankar Subramanian, Timothy Baldwin


Abstract
Online petitions offer a mechanism for peopleto initiate a request for change and gather sup-port from others to demonstrate support for thecause. In this work, we model the task of peti-tion popularity using both text and image rep-resentations across four different languages,and including petition metadata. We evaluateour proposed approach using a dataset of 75kpetitions from Avaaz.org, and find strong com-plementarity between text and images.
Anthology ID:
2020.alta-1.14
Volume:
Proceedings of the 18th Annual Workshop of the Australasian Language Technology Association
Month:
December
Year:
2020
Address:
Virtual Workshop
Editors:
Maria Kim, Daniel Beck, Meladel Mistica
Venue:
ALTA
SIG:
Publisher:
Australasian Language Technology Association
Note:
Pages:
110–114
Language:
URL:
https://aclanthology.org/2020.alta-1.14
DOI:
Bibkey:
Cite (ACL):
Kotaro Kitayama, Shivashankar Subramanian, and Timothy Baldwin. 2020. Popularity Prediction of Online Petitions using a Multimodal DeepRegression Model. In Proceedings of the 18th Annual Workshop of the Australasian Language Technology Association, pages 110–114, Virtual Workshop. Australasian Language Technology Association.
Cite (Informal):
Popularity Prediction of Online Petitions using a Multimodal DeepRegression Model (Kitayama et al., ALTA 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.alta-1.14.pdf