Sochiatrist is our project to help researchers investigate signals of mental health from naturally-occurring social messaging data, online and on mobile devices. We are interested in studying the effects of private messaging (direct messages or group chat) more than public posts on social media. For example, we'd like to know the effect of 1:1 messages between friends on a person's feeling of social support. What factors influence this and how consistent is this between individuals? How do the timing of messages or the replies from different individuals play a role?
One tool we have developed for understanding this is the Sochiatrist Social Data Extractor [1] for gathering this data retroactively from consenting individuals. This tool extracts messages from common messaging platforms, allowing the anonymizing of content, relationship tagging, date filtering, and removal of sender content (messages sent to the user), resulting in output saved in a common format. The studies are usually done in coordination with our research collaborators using clinical techniques and corroborated with other biomarker data, e.g. [2]. We have investigated the use of automated techniques and human review on understanding the emotional affect of the individuals while they are messaging [1].
As a group we are also interested in developing new ways of person-to-person social support without privacy risks or negative effects of social platforms, and understanding the effects of isolation during the pandemic on messaging behaviors and mental health [3].
[1] Sochiatrist: Signals of Affect in Messaging Data
Talie Massachi, Grant Fong, Varun Mathur, Sachin Pendse, Gabriela Hoefer, Jessica Fu, Chong Wang, Nikita Ramoji, Nicole Nugent, Megan Ranney, Daniel Dickstein, Michael Armey, Ellie Pavlick, Jeff Huang.
CSCW 2020. [PDF] [Video]
[2] Days with and without self-injurious thoughts and behaviors: Impact of childhood maltreatment on adolescent online social networking
Lauren R. Grocott, Anneliese Mair, Janine N. Galione, Michael F. Armey, Jeff Huang, Nicole R. Nugent.
Journal of Adolescence, 94, 2022. [DOI]
[3] Bridging the Social Distance: Offline to Online Social Support during the COVID-19 Pandemic
Gabriela Hoefer, Talie Massachi, Neil G Xu, Nicole R. Nugent, Jeff Huang.
CSCW 2022. [PDF]
The Sochiatrist Social Data Extractor is compatible with several social messaging platforms
Consent and login information from the user is needed to extract this data
iMessages and Text Messages
Facebook (Messages and Timeline Posts)
Twitter (Messages and Direct Messages)
Instagram (Direct Messages and Posts)
Snapchat (Metadata only)
WhatsApp (coming soon)
The Sochiatrist Social Data Extractor is intended to use on Macs. A more limited remotely-accessible online version is being planned.
Step 1: Download Sochiatrist
Contact us at sochiatrist@lists.cs.brown.edu
to download Sochiatrist. You should only need to download the app once as it has an auto-updater. Once you receive the zip file, open Finder and double-click the file to unzip it.
Step 2: Move Sochiatrist to Applications
For MacOS to recognize Sochiatrist as an application, we have to move it to the Applications folder.
Within the unzipped zip file, there should be an app named Sochiatrist Data Extractor. Copy it.
Within Finder, navigate to your Applications directory using the shortcut
Cmd+Shift+A
and
paste it there.
Replace any previous versions to overwrite previous releases.
Step 3: Enable Full Disk Access
If running MacOS Mojave, you need to allow Sochiatrist access to all your data.
Open Spotlight using Cmd+Space
, type in "privacy" and hit enter. Navigate to the
"Privacy" pane.
Scroll down to the "Full Disk Access" setting, click the lock to make changes, and click the plus to add Sochiatrist to the list of allowed apps.
Step 4: Run the Application
You can now click and run Sochiatrist like any other native Mac application.
Open Spotlight using Cmd+Space
, type "Sochiatrist" and hit enter.
Pin it to your dock for quick access!
The first time you run it it may take some time to start up as it has to install local
dependencies.
If the app is blocked because it is from an unidentified developer:
Open Spotlight using Cmd+Space
, type in "security", and hit enter.
Under the "General" pane, there should be an option to "Open Anyways". Click this to run the application without trouble in the future.
Step 5: Troubleshooting
Sometimes, portions of our dependency management system may still fail. If the main process crashes, run the following code in the terminal and restart:
brew install libmagic && brew install ffmpeg && brew install gdbm && brew link
--overwrite gdbm
After completing the data extraction process, you can expect to find all messages in a CSV entitled anonymized_[name of participant].csv. The data will look like this.
As you can see above, all numbers are replaced with a pound sign/hashtag, all names are replaced with hashed representations of the name (e.g., 7ac988b056981), and all conversation participants are also anonymized in the fourth column.
This research is supported by NIH grants R21 HD088739-01, R01 MH108641-01A1, R01 MH110379-01A1, R01 MH105379-02S1, R01 HD095932-01A1, R01 MH124832-01, R01 HD104187-01, and Army Research Office grant 71881-NS-YIP.
The overarching research is in collaboration with teams at universities and hospitals in Rhode Island and Boston, led by Nicole Nugent, Megan Ranney, Daniel Dickstein, Christie Rizzo, Michael Armey, and Melanie Bozzay.