@inproceedings{zhong-etal-2020-interpreting,
title = "Interpreting {T}witter User Geolocation",
author = "Zhong, Ting and
Wang, Tianliang and
Zhou, Fan and
Trajcevski, Goce and
Zhang, Kunpeng and
Yang, Yi",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.79/",
doi = "10.18653/v1/2020.acl-main.79",
pages = "853--859",
abstract = "Identifying user geolocation in online social networks is an essential task in many location-based applications. Existing methods rely on the similarity of text and network structure, however, they suffer from a lack of interpretability on the corresponding results, which is crucial for understanding model behavior. In this work, we adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting the locations of the testing users. This methodology helps with providing meaningful explanations on prediction results. Furthermore, it also initiates an attempt to uncover the so-called {\textquotedblleft}black-box{\textquotedblright} GNN-based models by investigating the effect of individual nodes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2020-interpreting">
<titleInfo>
<title>Interpreting Twitter User Geolocation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianliang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goce</namePart>
<namePart type="family">Trajcevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunpeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying user geolocation in online social networks is an essential task in many location-based applications. Existing methods rely on the similarity of text and network structure, however, they suffer from a lack of interpretability on the corresponding results, which is crucial for understanding model behavior. In this work, we adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting the locations of the testing users. This methodology helps with providing meaningful explanations on prediction results. Furthermore, it also initiates an attempt to uncover the so-called “black-box” GNN-based models by investigating the effect of individual nodes.</abstract>
<identifier type="citekey">zhong-etal-2020-interpreting</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.79</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.79/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>853</start>
<end>859</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interpreting Twitter User Geolocation
%A Zhong, Ting
%A Wang, Tianliang
%A Zhou, Fan
%A Trajcevski, Goce
%A Zhang, Kunpeng
%A Yang, Yi
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F zhong-etal-2020-interpreting
%X Identifying user geolocation in online social networks is an essential task in many location-based applications. Existing methods rely on the similarity of text and network structure, however, they suffer from a lack of interpretability on the corresponding results, which is crucial for understanding model behavior. In this work, we adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting the locations of the testing users. This methodology helps with providing meaningful explanations on prediction results. Furthermore, it also initiates an attempt to uncover the so-called “black-box” GNN-based models by investigating the effect of individual nodes.
%R 10.18653/v1/2020.acl-main.79
%U https://aclanthology.org/2020.acl-main.79/
%U https://doi.org/10.18653/v1/2020.acl-main.79
%P 853-859
Markdown (Informal)
[Interpreting Twitter User Geolocation](https://aclanthology.org/2020.acl-main.79/) (Zhong et al., ACL 2020)
ACL
- Ting Zhong, Tianliang Wang, Fan Zhou, Goce Trajcevski, Kunpeng Zhang, and Yi Yang. 2020. Interpreting Twitter User Geolocation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 853–859, Online. Association for Computational Linguistics.