On-Device Wellbeing Journal with Private Sentiment Trends
A private journal that analyses mood trends entirely on the device, with the encrypted data never leaving the phone. The engineering claim is the privacy architecture, and the most important design work is knowing what the app must refuse to do.
Intermediate
A small team, or one strong student willing to learn something new.1 semester, 2 students
5 to ship
3 optional extrasSuggested stack
What you should ship
- Encrypted local storage with a key derived from the user's passphrase or device biometrics
- On device sentiment and emotion classification with no network calls, demonstrably verified
- Trend visualisation over weeks with optional tagging of activities and sleep
- Explicit crisis handling: defined phrases surface local support resources and the app makes no clinical claim
- Privacy verification: network traffic capture during a full session proving no data leaves the device
If you have time left
- Correlation between logged activities and mood, presented as association rather than cause
- Encrypted export and restore controlled entirely by the user
- Model quality compared against a cloud model to quantify the cost of staying local
The problem
Mood tracking applications routinely upload the most sensitive text a person writes to a server, and their privacy policies are frequently worse than users assume. There is no technical need for this.
What you build
An encrypted local store, a quantised sentiment model running on device, trend visualisation, and a demonstration that nothing is transmitted.
The claim you must actually prove
Do not merely assert privacy. Capture the app's network traffic during a full session and include the evidence in your report. A verified claim is worth far more than a stated one, and the verification method is a contribution in itself.
The trade off to measure
On device models are smaller and less accurate than server models. Quantify that gap and argue about whether the privacy gain is worth it. That is a genuine engineering judgement and exactly what a final year project should demonstrate.
The ethical boundary, which is not optional
This is a journal, not a mental health intervention. It must not diagnose, score anyone against a clinical scale, or imply treatment. It must handle expressions of crisis by surfacing real local support resources immediately, and this behaviour must be designed deliberately, tested, and described in the report. If your institution has an ethics process, this project goes through it.
Scope warning
No social features, no sharing, no cloud backup by default. The privacy architecture is the project and every network feature undermines it.
Ideas and guidance, not finished projects
These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.
Not sure this one fits you?
I help students pick an idea that matches their skills and their deadline, then scope it down until it is finishable. Guidance only, never done for you.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.