LITL at SMM4H: An Old-school Feature-based Classifier for Identifying Adverse Effects in Tweets

Ludovic Tanguy, Lydia-Mai Ho-Dac, Cécile Fabre, Roxane Bois, Touati Mohamed Yacine Haddad, Claire Ibarboure, Marie Joyau, François Le moal, Jade Moiilic, Laura Roudaut, Mathilde Simounet, Irena Stankovic, Mickaela Vandewaetere


Abstract
This paper describes our participation to the SMM4H shared task 2. We designed a rule-based classifier that estimates whether a tweet mentions an adverse effect associated to a medication. Our system addresses English and French, and is based on a number of specific word lists and features. These cues were mostly obtained through an extensive corpus analysis of the provided training data. Different weighting schemes were tested (manually tuned or based on a logistic regression), the best one achieving a F1 score of 0.31 for English and 0.15 for French.
Anthology ID:
2020.smm4h-1.24
Volume:
Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venues:
COLING | SMM4H
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
134–137
Language:
URL:
https://aclanthology.org/2020.smm4h-1.24
DOI:
Bibkey:
Cite (ACL):
Ludovic Tanguy, Lydia-Mai Ho-Dac, Cécile Fabre, Roxane Bois, Touati Mohamed Yacine Haddad, Claire Ibarboure, Marie Joyau, François Le moal, Jade Moiilic, Laura Roudaut, Mathilde Simounet, Irena Stankovic, and Mickaela Vandewaetere. 2020. LITL at SMM4H: An Old-school Feature-based Classifier for Identifying Adverse Effects in Tweets. In Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task, pages 134–137, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
LITL at SMM4H: An Old-school Feature-based Classifier for Identifying Adverse Effects in Tweets (Tanguy et al., SMM4H 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.smm4h-1.24.pdf
Data
SMM4H