Give user interference more weight in message classification
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 1k
- Forks
- 348
- Avg merge
- 12h 28m
- Merged PRs (30d)
- 91
Description
Is your feature request related to a problem? Please describe.
As a user I sometimes change the importance state of incoming messages, when the automatic classification gets it wrong. Yet sometimes the system doesn't seem capable of improving its classification.
Describe the solution you'd like
Track when I, as a user, mark a message as important or not important, so that it has more weight in the classification than messages that were marked as important by the system.
Describe alternatives you've considered
N/a
Additional context
From an implementation PoV we might attach additional tags to a message that signal the special importance/unimportance. Then later we add new features into the machine learning algorithm that gives weight to how many messages of one sender were marked as important/unimportant.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named. Trace how message importance is stored and how classification uses system- versus user-marked importance, then determine where sender history is incorporated. Done means user changes to important or unimportant influence later classification more strongly than automatic labels.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript, machine-learning
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100