@inproceedings{wu-etal-2024-pasum,
title = "{PASUM}: A Pre-training Architecture for Social Media User Modeling Based on Text Graph",
author = "Wu, Kun and
Mou, Xinyi and
Xue, Lanqing and
Ying, Zhenzhe and
Wang, Weiqiang and
Zhang, Qi and
Huang, Xuanjing and
Wei, Zhongyu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1107",
pages = "12644--12656",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-pasum">
<titleInfo>
<title>PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Mou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lanqing</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenzhe</namePart>
<namePart type="family">Ying</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiqiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">wu-etal-2024-pasum</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1107</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12644</start>
<end>12656</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph
%A Wu, Kun
%A Mou, Xinyi
%A Xue, Lanqing
%A Ying, Zhenzhe
%A Wang, Weiqiang
%A Zhang, Qi
%A Huang, Xuanjing
%A Wei, Zhongyu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F wu-etal-2024-pasum
%X 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.
%U https://aclanthology.org/2024.lrec-main.1107
%P 12644-12656
Markdown (Informal)
[PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph](https://aclanthology.org/2024.lrec-main.1107) (Wu et al., LREC-COLING 2024)
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.