zlacker

[parent] [thread] 1 comments
1. julien+(OP)[view] [source] 2023-05-03 07:43:35
You could deduplicate based on vector similarity within a few days (7 days for big stories as their news cycle is longer, 24 or 48 hours for smaller stories). Idea: The number of stories within a cluster weighted by credibility of the source could be another element of the rating.
replies(1): >>yakhin+l2
2. yakhin+l2[view] [source] 2023-05-03 08:07:54
>>julien+(OP)
Wow, thank you! I'm just a frontend dev and know almost nothing about this. Will research vector similarity, sounds like the solution I need.
[go to top]