Predicting Depression: a comparative study of machine learning approaches based on language usage.

Fuente: Redalyc
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Luciana Mariñelarena-Dondena
Format: Artículo científico
Sprache:en
Veröffentlicht: Centro de Estudios Académicos en Neuropsicología 2017
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1876450765768228864
author Luciana Mariñelarena-Dondena
author_facet Luciana Mariñelarena-Dondena
contents Predicting Depression: a comparative study of machine learning approaches based on language usage. Luciana Mariñelarena-Dondena Edgardo Ferretti Manolis Maragoudakis Maximiliano Sapino Marcelo Luis Errecalde Psicología Depression Deep Learning Machine Learning SMOTE (Synthetic Minority Oversampling TEchnique) Depression is a major public health concern and a leading cause of disability. Globally, more than 332 million people of all ages suffer from depression. Several studies in the literature show that people language usage is indicative of their psychological states. That is why, there is growing interest in the application of natural language processing techniques for predicting depression. In this work, we present a comparative study of different machine learning methods and alternative ways of representing documents to automatically detect social media users who have reported to had been diagnosed with depression. The obtained results have demonstrated that a Deep Learning approach had the superior classification performance, when combined with a Synthetic Minority Oversampling Technique to deal with the problem of class imbalances in the dataset used in our experiments. The F1 score achieved was 82.93% with an accuracy of more than 94%. 2017 artículo científico 0718-4123 https://www.redalyc.org/articulo.oa?id=439656187002 https://doi.org/10.7714/CNPS/11.3.201 en http://www.redalyc.org/revista.oa?id=4396 Cuadernos de Neuropsicología / Panamerican Journal of Neuropsychology application/pdf Centro de Estudios Académicos en Neuropsicología Cuadernos de Neuropsicología / Panamerican Journal of Neuropsychology (Chile) Num.3 Vol.11
format Artículo científico
id redalyc_439656187002
institution Redalyc
language en
publishDate 2017
publisher Centro de Estudios Académicos en Neuropsicología
spellingShingle Predicting Depression: a comparative study of machine learning approaches based on language usage.
Luciana Mariñelarena-Dondena
Psicología
Depression
Deep Learning
Machine Learning
SMOTE (Synthetic Minority Oversampling TEchnique)
Predicting Depression: a comparative study of machine learning approaches based on language usage. Luciana Mariñelarena-Dondena Edgardo Ferretti Manolis Maragoudakis Maximiliano Sapino Marcelo Luis Errecalde Psicología Depression Deep Learning Machine Learning SMOTE (Synthetic Minority Oversampling TEchnique) Depression is a major public health concern and a leading cause of disability. Globally, more than 332 million people of all ages suffer from depression. Several studies in the literature show that people language usage is indicative of their psychological states. That is why, there is growing interest in the application of natural language processing techniques for predicting depression. In this work, we present a comparative study of different machine learning methods and alternative ways of representing documents to automatically detect social media users who have reported to had been diagnosed with depression. The obtained results have demonstrated that a Deep Learning approach had the superior classification performance, when combined with a Synthetic Minority Oversampling Technique to deal with the problem of class imbalances in the dataset used in our experiments. The F1 score achieved was 82.93% with an accuracy of more than 94%. 2017 artículo científico 0718-4123 https://www.redalyc.org/articulo.oa?id=439656187002 https://doi.org/10.7714/CNPS/11.3.201 en http://www.redalyc.org/revista.oa?id=4396 Cuadernos de Neuropsicología / Panamerican Journal of Neuropsychology application/pdf Centro de Estudios Académicos en Neuropsicología Cuadernos de Neuropsicología / Panamerican Journal of Neuropsychology (Chile) Num.3 Vol.11
title Predicting Depression: a comparative study of machine learning approaches based on language usage.
topic Psicología
Depression
Deep Learning
Machine Learning
SMOTE (Synthetic Minority Oversampling TEchnique)
url https://www.redalyc.org/articulo.oa?id=439656187002
https://doi.org/10.7714/CNPS/11.3.201