PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph

Kun Wu, Xinyi Mou, Lanqing Xue, Zhenzhe Ying, Weiqiang Wang, Qi Zhang, Xuanjing Huang, Zhongyu Wei


Abstract
Modeling social media users is the core of social governance in the digital society. Existing works have incorporated different digital traces to better learn the representations of social media users, including text information encoded by pre-trained language models and social network information encoded by graph models. However, limited by overloaded text information and hard-to-collect social network information, they cannot utilize global text information and cannot be generalized without social relationships. In this paper, we propose a Pre-training Architecture for Social Media User Modeling based on Text Graph(PASUM). We aggregate all microblogs to represent social media users based on the text graph model and learn the mapping from microblogs to user representation. We further design inter-user and intra-user contrastive learning tasks to inject general structural information into the mapping. In different scenarios, we can represent users based on text, even without social network information. Experimental results on various downstream tasks demonstrate the effectiveness and superiority of our framework.
Anthology ID:
2024.lrec-main.1107
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
12644–12656
Language:
URL:
https://aclanthology.org/2024.lrec-main.1107
DOI:
Bibkey:
Cite (ACL):
Kun Wu, Xinyi Mou, Lanqing Xue, Zhenzhe Ying, Weiqiang Wang, Qi Zhang, Xuanjing Huang, and Zhongyu Wei. 2024. PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12644–12656, Torino, Italia. ELRA and ICCL.
Cite (Informal):
PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph (Wu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1107.pdf