This paper presents an unsupervised approach using recurrent neural networks and anomaly detection to identify depressed users in online forums. By analyzing linguistic styles and network-based features from the ReachOut.com platform, the study achieves an F1-measure of 0.64 in detecting depression, outperforming baseline methods. The combination of psycho-linguistic and network features proves effective in identifying users facing depression, offering a valuable tool for supporting mental health interventions.
-
Shrestha, Anu, Edoardo Serra, and Francesca Spezzano. "Multi-modal social and psycho-linguistic embedding via recurrent neural networks to identify depressed users in online forums." Network Modeling Analysis in Health Informatics and Bioinformatics 9 (2020): 1-11.
-
Members
- JoelR
- N700
- Adriano Faria
- Live Games
- Como
- DawPi
- IC Essentials
- opentype
- Square Wheels
- Voyage
- A Zayed
- Brian
- COSMIN
- Nathan Explosion
- Auto Evoke
- YalcinA
- master963
- VAHID
- Chris Anderson
- Myr
- bernhara
- ReyDev
- send2yoni
- terabyte
- Dilip
- ZLTRGO
- adik
- eivindsimensen
- envy
- onlyME
- V0RT3X
- GazzaGarratt
- Analog
- Paul Kaiser
- Paul
- TracyIsland
- Andy Y
- Omar Barbeytia carretero
- JoeyM
- Ryancoolround
- rainx
- YourSharona
- Kentraiyle Robinson
- MichaelR
- Edward Ellas
- IPS THEME
- aXenDev
- PrettyPixels
- Denis Dyack
- Labis
- DursunKaptan
- MissB
- TheLlamaman
- aLEX49566
- Codepixel
- alsl sndnxnx
- burnyourfeelings
- isvans
- Marius
- Matt
- Thomas Taschler
- Surpac
- JoshB
- Ioannis D
- abobader
- Richard Arch
- bdmusic 24
- Majster87
- TomCat
- Pmw
- Torgeir Rui
- Kammer et
- Nicolas PC
- XwReK
- Claudia999
- Kirill Gromov
- Synergy
- bing11
- Marcin Martyniak
- ArashDev
- ali hagi
- StevenM
- NewVicious
- lukash
- Andhrafriends Admin
- Daffy
- hyprem
- GuitarGathering
- Tripp
- Askancy
- MLK
- Jelly Belly
- eveneme eveneme
- Nomad
- Morphe
- lordi
- shahed
- John Horton
- PayMap
- Serval