@inproceedings{liza-2020-sentence,
title = "Sentence Classification with Imbalanced Data for Health Applications",
author = "Liza, Farhana Ferdousi",
editor = "Gonzalez-Hernandez, Graciela and
Klein, Ari Z. and
Flores, Ivan and
Weissenbacher, Davy and
Magge, Arjun and
O'Connor, Karen and
Sarker, Abeed and
Minard, Anne-Lyse and
Tutubalina, Elena and
Miftahutdinov, Zulfat and
Alimova, Ilseyar",
booktitle = "Proceedings of the Fifth Social Media Mining for Health Applications Workshop {\&} Shared Task",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.smm4h-1.25/",
pages = "138--145",
abstract = "Identifying and extracting reports of medications, their abuse or adverse effects from social media is a challenging task. In social media, relevant reports are very infrequent, causes imbalanced class distribution for machine learning algorithms. Learning algorithms typically designed to optimize the overall accuracy without considering the relative distribution of each class. Thus, imbalanced class distribution is problematic as learning algorithms have low predictive accuracy for the infrequent class. Moreover, social media represents natural linguistic variation in creative language expressions. In this paper, we have used a combination of data balancing and neural language representation techniques to address the challenges. Specifically, we participated the shared tasks 1, 2 (all languages), 4, and 3 (only the span detection, no normalization was attempted) in Social Media Mining for Health applications (SMM4H) 2020 (Klein et al., 2020). The results show that with the proposed methodology recall scores are better than the precision scores for the shared tasks. The recall score is also better compared to the mean score of the total submissions. However, the F1-score is worse than the mean score except for task 2 (French)."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liza-2020-sentence">
<titleInfo>
<title>Sentence Classification with Imbalanced Data for Health Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farhana</namePart>
<namePart type="given">Ferdousi</namePart>
<namePart type="family">Liza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Magge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulfat</namePart>
<namePart type="family">Miftahutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying and extracting reports of medications, their abuse or adverse effects from social media is a challenging task. In social media, relevant reports are very infrequent, causes imbalanced class distribution for machine learning algorithms. Learning algorithms typically designed to optimize the overall accuracy without considering the relative distribution of each class. Thus, imbalanced class distribution is problematic as learning algorithms have low predictive accuracy for the infrequent class. Moreover, social media represents natural linguistic variation in creative language expressions. In this paper, we have used a combination of data balancing and neural language representation techniques to address the challenges. Specifically, we participated the shared tasks 1, 2 (all languages), 4, and 3 (only the span detection, no normalization was attempted) in Social Media Mining for Health applications (SMM4H) 2020 (Klein et al., 2020). The results show that with the proposed methodology recall scores are better than the precision scores for the shared tasks. The recall score is also better compared to the mean score of the total submissions. However, the F1-score is worse than the mean score except for task 2 (French).</abstract>
<identifier type="citekey">liza-2020-sentence</identifier>
<location>
<url>https://aclanthology.org/2020.smm4h-1.25/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>138</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence Classification with Imbalanced Data for Health Applications
%A Liza, Farhana Ferdousi
%Y Gonzalez-Hernandez, Graciela
%Y Klein, Ari Z.
%Y Flores, Ivan
%Y Weissenbacher, Davy
%Y Magge, Arjun
%Y O’Connor, Karen
%Y Sarker, Abeed
%Y Minard, Anne-Lyse
%Y Tutubalina, Elena
%Y Miftahutdinov, Zulfat
%Y Alimova, Ilseyar
%S Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F liza-2020-sentence
%X Identifying and extracting reports of medications, their abuse or adverse effects from social media is a challenging task. In social media, relevant reports are very infrequent, causes imbalanced class distribution for machine learning algorithms. Learning algorithms typically designed to optimize the overall accuracy without considering the relative distribution of each class. Thus, imbalanced class distribution is problematic as learning algorithms have low predictive accuracy for the infrequent class. Moreover, social media represents natural linguistic variation in creative language expressions. In this paper, we have used a combination of data balancing and neural language representation techniques to address the challenges. Specifically, we participated the shared tasks 1, 2 (all languages), 4, and 3 (only the span detection, no normalization was attempted) in Social Media Mining for Health applications (SMM4H) 2020 (Klein et al., 2020). The results show that with the proposed methodology recall scores are better than the precision scores for the shared tasks. The recall score is also better compared to the mean score of the total submissions. However, the F1-score is worse than the mean score except for task 2 (French).
%U https://aclanthology.org/2020.smm4h-1.25/
%P 138-145
Markdown (Informal)
[Sentence Classification with Imbalanced Data for Health Applications](https://aclanthology.org/2020.smm4h-1.25/) (Liza, SMM4H 2020)
ACL