Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jun 10;21(6):e12554.
doi: 10.2196/12554.

Early Detection of Depression: Social Network Analysis and Random Forest Techniques

Fidel Cacheda  1   2 , Diego Fernandez #  1   2 , Francisco J Novoa  1   2 , Victor Carneiro  1   2
Affiliations

Early Detection of Depression: Social Network Analysis and Random Forest Techniques

Fidel Cacheda et al. J Med Internet Res. .

Abstract

Background: Major depressive disorder (MDD) or depression is among the most prevalent psychiatric disorders, affecting more than 300 million people globally. Early detection is critical for rapid intervention, which can potentially reduce the escalation of the disorder.

Objective: This study used data from social media networks to explore various methods of early detection of MDDs based on machine learning. We performed a thorough analysis of the dataset to characterize the subjects' behavior based on different aspects of their writings: textual spreading, time gap, and time span.

Methods: We proposed 2 different approaches based on machine learning singleton and dual. The former uses 1 random forest (RF) classifier with 2 threshold functions, whereas the latter uses 2 independent RF classifiers, one to detect depressed subjects and another to identify nondepressed individuals. In both cases, features are defined from textual, semantic, and writing similarities.

Results: The evaluation follows a time-aware approach that rewards early detections and penalizes late detections. The results show how a dual model performs significantly better than the singleton model and is able to improve current state-of-the-art detection models by more than 10%.

Conclusions: Given the results, we consider that this study can help in the development of new solutions to deal with the early detection of depression on social networks.

Keywords: artificial intelligence; depression; machine learning; major depressive disorder; social media.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
Relative percentage for number of words used on title (a), text (b), and both fields (c) for depressed and nondepressed individuals.
Figure 2
Figure 2
Average time gaps distribution between writings for depressed and nondepressed subjects.
Figure 3
Figure 3
Time span bar plots according to the day of the week (a) and hour of the day (b) for depressed and nondepressed subjects.
Figure 4
Figure 4
Textual similarity measures. IDF: inverse document frequency; BM25: Okapi Best Matching 25.
Figure 5
Figure 5
Latent semantic space.
Figure 6
Figure 6
Early risk detection error metric. ERDE: early risk detection error.
See this image and copyright information in PMC

References

    1. Kessler RC, Aguilar-Gaxiola S, Alonso J, Chatterji S, Lee S, Ormel J, Ustün TB, Wang PS. The global burden of mental disorders: an update from the WHO World Mental Health (WMH) surveys. Epidemiol Psichiatr Soc. 2009;18(1):23–33. http://europepmc.org/abstract/MED/19378696 - PMC - PubMed
    1. Le HN, Boyd RC. Prevention of major depression: early detection and early intervention in the general population. Clin Neuropsychiatry. 2006;3(1):6–22. https://www.researchgate.net/publication/228343300_Prevention_of_major_d...
    1. World Health Organization. 2013. Comprehensive mental health action plan 2013-2020 https://www.who.int/mental_health/action_plan_2013/en/
    1. Mathers CD, Loncar D. Projections of global mortality and burden of disease from 2002 to 2030. PLoS Medicine. 2006 Nov;3(11):e442. doi: 10.1371/journal.pmed.0030442. http://dx.plos.org/10.1371/journal.pmed.0030442 06-PLME-RA-0071R2 - DOI - DOI - PMC - PubMed
    1. Muñoz RF, Mrazek PJ, Haggerty RJ. Institute of Medicine report on prevention of mental disorders. Summary and commentary. Am Psychol. 1996 Nov;51(11):1116–22. - PubMed

Publication types