@inproceedings{ding-etal-2017-multi,
title = "Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction",
author = "Ding, Tao and
Bickel, Warren K. and
Pan, Shimei",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1241",
doi = "10.18653/v1/D17-1241",
pages = "2275--2284",
abstract = "In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems. Since a substance use ground truth is difficult to obtain on a large scale, to maximize system performance, we explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. We also demonstrate the benefit of using multi-view unsupervised feature learning to combine heterogeneous user information such as Facebook {``}likes{''} and {``}status updates{''} to enhance system performance. Based on our evaluation, our best models achieved 86{\%} AUC for predicting tobacco use, 81{\%} for alcohol use and 84{\%} for illicit drug use, all of which significantly outperformed existing methods. Our investigation has also uncovered interesting relations between a user{'}s social media behavior (e.g., word usage) and substance use.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2017-multi">
<titleInfo>
<title>Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Warren</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Bickel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimei</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems. Since a substance use ground truth is difficult to obtain on a large scale, to maximize system performance, we explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. We also demonstrate the benefit of using multi-view unsupervised feature learning to combine heterogeneous user information such as Facebook “likes” and “status updates” to enhance system performance. Based on our evaluation, our best models achieved 86% AUC for predicting tobacco use, 81% for alcohol use and 84% for illicit drug use, all of which significantly outperformed existing methods. Our investigation has also uncovered interesting relations between a user’s social media behavior (e.g., word usage) and substance use.</abstract>
<identifier type="citekey">ding-etal-2017-multi</identifier>
<identifier type="doi">10.18653/v1/D17-1241</identifier>
<location>
<url>https://aclanthology.org/D17-1241</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>2275</start>
<end>2284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction
%A Ding, Tao
%A Bickel, Warren K.
%A Pan, Shimei
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F ding-etal-2017-multi
%X In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems. Since a substance use ground truth is difficult to obtain on a large scale, to maximize system performance, we explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. We also demonstrate the benefit of using multi-view unsupervised feature learning to combine heterogeneous user information such as Facebook “likes” and “status updates” to enhance system performance. Based on our evaluation, our best models achieved 86% AUC for predicting tobacco use, 81% for alcohol use and 84% for illicit drug use, all of which significantly outperformed existing methods. Our investigation has also uncovered interesting relations between a user’s social media behavior (e.g., word usage) and substance use.
%R 10.18653/v1/D17-1241
%U https://aclanthology.org/D17-1241
%U https://doi.org/10.18653/v1/D17-1241
%P 2275-2284
Markdown (Informal)
[Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction](https://aclanthology.org/D17-1241) (Ding et al., EMNLP 2017)
ACL