|
|
|
|
|
|
by kettlecorn
33 days ago
|
|
|
I have wondered if a pseudo-social / pseudo-technical solution of some sort of trust graph could help. Like you would say who you think is credible and human. An algorithm would evaluate trust on your behalf and it would look to the people you trust, and then who they trust, and so on and assign scores to people. Distrust, or even other observations, could percolate in a similar way. Then on social networks, or some sort of small-web, new users would need to find other people to vouch for them to establish trust. When viewing websites or social media posts the trust score of users could be shown alongside content, and used to filter feeds / visibility. A troll or bot could rather rapidly get picked up by a network of distrust so they could be filtered out quickly. The algorithms and details of such a thing are fuzzy to me, and I think a lot of care and thought would be needed to try to ensure it doesn't collapse under subtle flaws with time. |
|
|
1. Most websites that aren't dead had huge influx of new users at some point of their history. Recommendation system cannot handle that - it becomes a bottleneck, and people move to a competitor that doesn't have this problem.
2. Suppose you have a community and you say that each new user needs to be at least 99% compatible with what the community already stands for. Congratulations, your community will decay exponentially with each new user bringing the quality down just a tiny bit until it's gone.
The solutions that actually work tend to be UI-oriented. For example, 4chan has an outdated interface not because admins don't know to do modern UI, but rather because outdated UI filters off normies.
The biggest challenge is the balance between new users, who tend to bring the quality down, and old users, who are boring and have nothing to say beyond what has already been said.