@inproceedings{sanchez-villegas-aletras-2021-point,
title = "Point-of-Interest Type Prediction using Text and Images",
author = "S{\'a}nchez Villegas, Danae and
Aletras, Nikolaos",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.614",
doi = "10.18653/v1/2021.emnlp-main.614",
pages = "7785--7797",
abstract = "Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared. Inferring a POI{'}s type is useful for studies in computational social science including sociolinguistics, geosemiotics, and cultural geography, and has applications in geosocial networking technologies such as recommendation and visualization systems. Prior efforts in POI type prediction focus solely on text, without taking visual information into account. However in reality, the variety of modalities, as well as their semiotic relationships with one another, shape communication and interactions in social media. This paper presents a study on POI type prediction using multimodal information from text and images available at posting time. For that purpose, we enrich a currently available data set for POI type prediction with the images that accompany the text messages. Our proposed method extracts relevant information from each modality to effectively capture interactions between text and image achieving a macro F1 of 47.21 across 8 categories significantly outperforming the state-of-the-art method for POI type prediction based on text-only methods. Finally, we provide a detailed analysis to shed light on cross-modal interactions and the limitations of our best performing model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-villegas-aletras-2021-point">
<titleInfo>
<title>Point-of-Interest Type Prediction using Text and Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danae</namePart>
<namePart type="family">Sánchez Villegas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared. Inferring a POI’s type is useful for studies in computational social science including sociolinguistics, geosemiotics, and cultural geography, and has applications in geosocial networking technologies such as recommendation and visualization systems. Prior efforts in POI type prediction focus solely on text, without taking visual information into account. However in reality, the variety of modalities, as well as their semiotic relationships with one another, shape communication and interactions in social media. This paper presents a study on POI type prediction using multimodal information from text and images available at posting time. For that purpose, we enrich a currently available data set for POI type prediction with the images that accompany the text messages. Our proposed method extracts relevant information from each modality to effectively capture interactions between text and image achieving a macro F1 of 47.21 across 8 categories significantly outperforming the state-of-the-art method for POI type prediction based on text-only methods. Finally, we provide a detailed analysis to shed light on cross-modal interactions and the limitations of our best performing model.</abstract>
<identifier type="citekey">sanchez-villegas-aletras-2021-point</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.614</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.614</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>7785</start>
<end>7797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Point-of-Interest Type Prediction using Text and Images
%A Sánchez Villegas, Danae
%A Aletras, Nikolaos
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F sanchez-villegas-aletras-2021-point
%X Point-of-interest (POI) type prediction is the task of inferring the type of a place from where a social media post was shared. Inferring a POI’s type is useful for studies in computational social science including sociolinguistics, geosemiotics, and cultural geography, and has applications in geosocial networking technologies such as recommendation and visualization systems. Prior efforts in POI type prediction focus solely on text, without taking visual information into account. However in reality, the variety of modalities, as well as their semiotic relationships with one another, shape communication and interactions in social media. This paper presents a study on POI type prediction using multimodal information from text and images available at posting time. For that purpose, we enrich a currently available data set for POI type prediction with the images that accompany the text messages. Our proposed method extracts relevant information from each modality to effectively capture interactions between text and image achieving a macro F1 of 47.21 across 8 categories significantly outperforming the state-of-the-art method for POI type prediction based on text-only methods. Finally, we provide a detailed analysis to shed light on cross-modal interactions and the limitations of our best performing model.
%R 10.18653/v1/2021.emnlp-main.614
%U https://aclanthology.org/2021.emnlp-main.614
%U https://doi.org/10.18653/v1/2021.emnlp-main.614
%P 7785-7797
Markdown (Informal)
[Point-of-Interest Type Prediction using Text and Images](https://aclanthology.org/2021.emnlp-main.614) (Sánchez Villegas & Aletras, EMNLP 2021)
ACL
- Danae Sánchez Villegas and Nikolaos Aletras. 2021. Point-of-Interest Type Prediction using Text and Images. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7785–7797, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.