@inproceedings{ansari-etal-2021-data,
title = "Data Augmentation for Mental Health Classification on Social Media",
author = "Ansari, Gunjan and
Garg, Muskan and
Saxena, Chandni",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.19",
pages = "152--161",
abstract = "The mental disorder of online users is determined using social media posts. The major challenge in this domain is to avail the ethical clearance for using the user-generated text on social media platforms. Academic researchers identified the problem of insufficient and unlabeled data for mental health classification. To handle this issue, we have studied the effect of data augmentation techniques on domain-specific user-generated text for mental health classification. Among the existing well-established data augmentation techniques, we have identified Easy Data Augmentation (EDA), conditional BERT, and Back-Translation (BT) as the potential techniques for generating additional text to improve the performance of classifiers. Further, three different classifiers- Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are employed for analyzing the impact of data augmentation on two publicly available social media datasets. The experimental results show significant improvements in classifiers{'} performance when trained on the augmented data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ansari-etal-2021-data">
<titleInfo>
<title>Data Augmentation for Mental Health Classification on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gunjan</namePart>
<namePart type="family">Ansari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muskan</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandni</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The mental disorder of online users is determined using social media posts. The major challenge in this domain is to avail the ethical clearance for using the user-generated text on social media platforms. Academic researchers identified the problem of insufficient and unlabeled data for mental health classification. To handle this issue, we have studied the effect of data augmentation techniques on domain-specific user-generated text for mental health classification. Among the existing well-established data augmentation techniques, we have identified Easy Data Augmentation (EDA), conditional BERT, and Back-Translation (BT) as the potential techniques for generating additional text to improve the performance of classifiers. Further, three different classifiers- Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are employed for analyzing the impact of data augmentation on two publicly available social media datasets. The experimental results show significant improvements in classifiers’ performance when trained on the augmented data.</abstract>
<identifier type="citekey">ansari-etal-2021-data</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.19</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>152</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Mental Health Classification on Social Media
%A Ansari, Gunjan
%A Garg, Muskan
%A Saxena, Chandni
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F ansari-etal-2021-data
%X The mental disorder of online users is determined using social media posts. The major challenge in this domain is to avail the ethical clearance for using the user-generated text on social media platforms. Academic researchers identified the problem of insufficient and unlabeled data for mental health classification. To handle this issue, we have studied the effect of data augmentation techniques on domain-specific user-generated text for mental health classification. Among the existing well-established data augmentation techniques, we have identified Easy Data Augmentation (EDA), conditional BERT, and Back-Translation (BT) as the potential techniques for generating additional text to improve the performance of classifiers. Further, three different classifiers- Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR) are employed for analyzing the impact of data augmentation on two publicly available social media datasets. The experimental results show significant improvements in classifiers’ performance when trained on the augmented data.
%U https://aclanthology.org/2021.icon-main.19
%P 152-161
Markdown (Informal)
[Data Augmentation for Mental Health Classification on Social Media](https://aclanthology.org/2021.icon-main.19) (Ansari et al., ICON 2021)
ACL