@inproceedings{kocaman-etal-2022-john,
title = "{J}ohn{\_}{S}now{\_}{L}abs@{SMM}4{H}`22: Social Media Mining for Health ({\#}{SMM}4{H}) with Spark {NLP}",
author = "Kocaman, Veysel and
Celik, Cabir and
Gurbaz, Damla and
Pirge, Gursev and
Polat, Bunyamin and
Saglamlar, Halil and
Sarikaya, Meryem Vildan and
Turer, Gokhan and
Talby, David",
editor = "Gonzalez-Hernandez, Graciela and
Weissenbacher, Davy",
booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.smm4h-1.13/",
pages = "44--47",
abstract = "Social media has become a major source of information for healthcare professionals but due to the growing volume of data in unstructured format, analyzing these resources accurately has become a challenge. In this study, we trained health related NER and classification models on different datasets published within the Social Media Mining for Health Applications ({\#}SMM4H 2022) workshop. Transformer based Bert for Token Classification and Bert for Sequence Classification algorithms as well as vanilla NER and text classification algorithms from Spark NLP library were utilized during this study without changing the underlying DL architecture. The trained models are available within a production-grade code base as part of the Spark NLP library; can scale up for training and inference in any Spark cluster; has GPU support and libraries for popular programming languages such as Python, R, Scala and Java."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocaman-etal-2022-john">
<titleInfo>
<title>John_Snow_Labs@SMM4H‘22: Social Media Mining for Health (#SMM4H) with Spark NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veysel</namePart>
<namePart type="family">Kocaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cabir</namePart>
<namePart type="family">Celik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damla</namePart>
<namePart type="family">Gurbaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gursev</namePart>
<namePart type="family">Pirge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bunyamin</namePart>
<namePart type="family">Polat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Halil</namePart>
<namePart type="family">Saglamlar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="given">Vildan</namePart>
<namePart type="family">Sarikaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Turer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Talby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Seventh Workshop on 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">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media has become a major source of information for healthcare professionals but due to the growing volume of data in unstructured format, analyzing these resources accurately has become a challenge. In this study, we trained health related NER and classification models on different datasets published within the Social Media Mining for Health Applications (#SMM4H 2022) workshop. Transformer based Bert for Token Classification and Bert for Sequence Classification algorithms as well as vanilla NER and text classification algorithms from Spark NLP library were utilized during this study without changing the underlying DL architecture. The trained models are available within a production-grade code base as part of the Spark NLP library; can scale up for training and inference in any Spark cluster; has GPU support and libraries for popular programming languages such as Python, R, Scala and Java.</abstract>
<identifier type="citekey">kocaman-etal-2022-john</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.13/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>44</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T John_Snow_Labs@SMM4H‘22: Social Media Mining for Health (#SMM4H) with Spark NLP
%A Kocaman, Veysel
%A Celik, Cabir
%A Gurbaz, Damla
%A Pirge, Gursev
%A Polat, Bunyamin
%A Saglamlar, Halil
%A Sarikaya, Meryem Vildan
%A Turer, Gokhan
%A Talby, David
%Y Gonzalez-Hernandez, Graciela
%Y Weissenbacher, Davy
%S Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F kocaman-etal-2022-john
%X Social media has become a major source of information for healthcare professionals but due to the growing volume of data in unstructured format, analyzing these resources accurately has become a challenge. In this study, we trained health related NER and classification models on different datasets published within the Social Media Mining for Health Applications (#SMM4H 2022) workshop. Transformer based Bert for Token Classification and Bert for Sequence Classification algorithms as well as vanilla NER and text classification algorithms from Spark NLP library were utilized during this study without changing the underlying DL architecture. The trained models are available within a production-grade code base as part of the Spark NLP library; can scale up for training and inference in any Spark cluster; has GPU support and libraries for popular programming languages such as Python, R, Scala and Java.
%U https://aclanthology.org/2022.smm4h-1.13/
%P 44-47
Markdown (Informal)
[John_Snow_Labs@SMM4H’22: Social Media Mining for Health (#SMM4H) with Spark NLP](https://aclanthology.org/2022.smm4h-1.13/) (Kocaman et al., SMM4H 2022)
ACL
- Veysel Kocaman, Cabir Celik, Damla Gurbaz, Gursev Pirge, Bunyamin Polat, Halil Saglamlar, Meryem Vildan Sarikaya, Gokhan Turer, and David Talby. 2022. John_Snow_Labs@SMM4H’22: Social Media Mining for Health (#SMM4H) with Spark NLP. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 44–47, Gyeongju, Republic of Korea. Association for Computational Linguistics.