Détection de mésusages de médicaments dans les réseaux sociaux

Abstract : Detection of drug misuse in social media. Misuses happen when patients do not follow the prescriptions and do actions which lead to potentially harmful situations. Although such situations are dangerous, patients usually do not report the misuse of drugs to their physicians. Hence, it is necessary to study other sources of information to discover what is happening in reality. We propose to study online health fora. The purpose of our work is to explore online health fora with supervised classification methods in order to identify messages that contain drug misuses. Our method permits to detect misuses with up to 0.810 F-mesure. This method can help the detection of messages with misuses and building corpus with drug misuses, which can be used by experts to further study the types of misuses committed by patients.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://halshs.archives-ouvertes.fr/halshs-01968335
Contributor : Natalia Grabar <>
Submitted on : Wednesday, January 2, 2019 - 3:16:30 PM
Last modification on : Thursday, February 7, 2019 - 3:37:41 PM
Long-term archiving on : Wednesday, April 3, 2019 - 3:16:30 PM

File

bigeard-TALN2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : halshs-01968335, version 1

Collections

Citation

Elise Bigeard, Natalia Grabar, Frantz Thiessard. Détection de mésusages de médicaments dans les réseaux sociaux. TALN, May 2018, Rennes, France. ⟨halshs-01968335⟩

Share

Metrics

Record views

72

Files downloads

82