Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination

Imane Guellil; Jinge Wu; Honghan Wu; Tony Sun; Beatrice Alex

Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination

Imane Guellil, Jinge Wu, Honghan Wu, Tony Sun, Beatrice Alex

School of Literatures, Languages and Cultures

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

This paper reports on the performance of Edin-burgh_UCL_Health's models in the Social Media Mining for Health (SMM4H) 2022 shared tasks. Our team participated in the tasks related to the Identification of Adverse Drug Events (ADEs), the classification of change in medication (change-med) and the classification of selfreport of vaccination (self-vaccine). Our best performing models are based on DeepADEM-iner (with respective F1= 0.64, 0.62 and 0.39 for ADE identification), on a GloVe model trained on Twitter (with F1=0.11 for the changemed) and finally on a stack embedding including a layer of Glove embedding and two layers of Flair embedding (with F1= 0.77 for selfreport)

Original language	English
Title of host publication	Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
Subtitle of host publication	The 29th International Conference on Computational Linguistics
Publisher	ACL Anthology
Pages	148-152
Publication status	Published - 11 Oct 2022

Publication series

Name
Number	18
Volume	29
ISSN (Print)	2951-2093

Access to Document

GuellilEtalACL2022EdinburghUCLHealthFinal published version, 139 KBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/2022.smm4h-1.40/Licence: Creative Commons: Attribution (CC-BY)

Cite this

Guellil, I., Wu, J., Wu, H., Sun, T., & Alex, B. (2022). Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task: The 29th International Conference on Computational Linguistics (pp. 148-152). ACL Anthology. https://aclanthology.org/2022.smm4h-1.40/

Guellil, Imane ; Wu, Jinge ; Wu, Honghan et al. / Edinburgh_UCL_Health@ SMM4H'22 : From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination. Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task: The 29th International Conference on Computational Linguistics. ACL Anthology, 2022. pp. 148-152

@inproceedings{70f6709bca2241e08adee02c93784d0a,

title = "Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination",

abstract = "This paper reports on the performance of Edin-burgh_UCL_Health's models in the Social Media Mining for Health (SMM4H) 2022 shared tasks. Our team participated in the tasks related to the Identification of Adverse Drug Events (ADEs), the classification of change in medication (change-med) and the classification of selfreport of vaccination (self-vaccine). Our best performing models are based on DeepADEM-iner (with respective F1= 0.64, 0.62 and 0.39 for ADE identification), on a GloVe model trained on Twitter (with F1=0.11 for the changemed) and finally on a stack embedding including a layer of Glove embedding and two layers of Flair embedding (with F1= 0.77 for selfreport)",

author = "Imane Guellil and Jinge Wu and Honghan Wu and Tony Sun and Beatrice Alex",

year = "2022",

month = oct,

day = "11",

language = "English",

publisher = "ACL Anthology",

number = "18",

pages = "148--152",

booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task",

}

Guellil, I, Wu, J, Wu, H, Sun, T & Alex, B 2022, Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination. in Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task: The 29th International Conference on Computational Linguistics. ACL Anthology, pp. 148-152. <https://aclanthology.org/2022.smm4h-1.40/>

Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination. / Guellil, Imane; Wu, Jinge; Wu, Honghan et al.
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task: The 29th International Conference on Computational Linguistics. ACL Anthology, 2022. p. 148-152.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Edinburgh_UCL_Health@ SMM4H'22

T2 - From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination

AU - Guellil, Imane

AU - Wu, Jinge

AU - Wu, Honghan

AU - Sun, Tony

AU - Alex, Beatrice

PY - 2022/10/11

Y1 - 2022/10/11

N2 - This paper reports on the performance of Edin-burgh_UCL_Health's models in the Social Media Mining for Health (SMM4H) 2022 shared tasks. Our team participated in the tasks related to the Identification of Adverse Drug Events (ADEs), the classification of change in medication (change-med) and the classification of selfreport of vaccination (self-vaccine). Our best performing models are based on DeepADEM-iner (with respective F1= 0.64, 0.62 and 0.39 for ADE identification), on a GloVe model trained on Twitter (with F1=0.11 for the changemed) and finally on a stack embedding including a layer of Glove embedding and two layers of Flair embedding (with F1= 0.77 for selfreport)

AB - This paper reports on the performance of Edin-burgh_UCL_Health's models in the Social Media Mining for Health (SMM4H) 2022 shared tasks. Our team participated in the tasks related to the Identification of Adverse Drug Events (ADEs), the classification of change in medication (change-med) and the classification of selfreport of vaccination (self-vaccine). Our best performing models are based on DeepADEM-iner (with respective F1= 0.64, 0.62 and 0.39 for ADE identification), on a GloVe model trained on Twitter (with F1=0.11 for the changemed) and finally on a stack embedding including a layer of Glove embedding and two layers of Flair embedding (with F1= 0.77 for selfreport)

M3 - Conference contribution

SP - 148

EP - 152

BT - Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task

PB - ACL Anthology

ER -

Guellil I, Wu J, Wu H, Sun T, Alex B. Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task: The 29th International Conference on Computational Linguistics. ACL Anthology. 2022. p. 148-152

Edinburgh_UCL_Health@ SMM4H'22: From Glove to Flair for handling imbalanced healthcare corpora related to Adverse Drug Events, Change in medication and self-reporting vaccination

Abstract / Description of output

Publication series

Access to Document

Fingerprint

Cite this