the-algorithm
the-algorithm copied to clipboard
Source code for the X Recommendation Algorithm
Will this remain a snapshot without any updates or will this become the actual thing the company is working on & using in production? If this will be the real...
The current implementation allows for coordinated hurting of account reputation without recourse. The most general behavior is that global penalties are prone to be gamed (all of them). In other...
**Is your feature request related to a problem? Please describe.** The dataset used for the filters could introduce bias **Describe the solution you'd like** The datasets should also be open...
issue: 1. the recommended tweets are sometimes 6-7 days old with outdated content 2. tweets are shown repetitively even after seen by the user several times 3. includes tweets already...
_**tl;dr: fewer algorithms for home feed generation, more algorithms for content & author discovery across the core features Topics, Trends, Lists and Search**_ _Introduction_ X platforms (including Twitter, a **text**-focused...
Many code-related PRs to this repo address formatting and linting issues. Without a commonly agreed-upon set of tools PRs with code quality fixes might override each other. This is of...
src/scala/com/twitter/interaction_graph/bqe/training/labeled_candidates.sql In this case, the rows with negative labels are ignored so the labels being trained are {0,1}. Why don't we include the negative label and use {-1,0,1}?
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Go to '...' 2. Click on '....' 3. Scroll...
#Description This is not the issue. As I look at the document and architecture, Twitter leverages lots of user-tweet engagement features but I do not see how Twitter handles Tweet...
Hi There This is more like a clarification question about how the project is structured with bazel and current dependencies that are potentially missing I am trying to build the...