Yandex ‘leak’ reveals 1,922 search ranking factors

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by inerte on Monday January 30, 2023 @11:06AM (#34581576)

Everything in there makes sense imho except the Yellow Image Count. Anyone knows why that would be a factor?

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by encoderer on Monday January 30, 2023 @11:12AM (#34581687)

No, but can you explain the distance to Ankara one?

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by inerte on Monday January 30, 2023 @11:23AM (#34581925)

well now you're making me doubt myself, that's a weird one too. My first guess was "they need to know how far one request is from another, and Ankara is a good as any city"

So say suppose you're in New Orleans and I am in San Jose, now we can compare our distance, because geographical distance usually equates to cultural differences and perceptions of quality.

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by sam_lowry_ on Monday January 30, 2023 @11:31AM (#34582106)

They have a Turkish version, so I guess this props up Turkish results to requests from Turkey (granted, Ankara is not exactly in the middle of the country ;-)

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by stilldyl on Monday January 30, 2023 @05:02PM (#34587071)

Ankara is the nearest city to Kırşehir, considered by some to be the geographical centre of the world (as viewed on a typical flat map).

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by RugnirViking on Tuesday January 31, 2023 @04:20AM (#34593058)

there was exactly one other similar one (Distance to Madagan) which is a random russian town. So I think it might be deciding which of their datacenters should serve the request?

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by ogurechny on Tuesday January 31, 2023 @07:22PM (#34604425)

It is a bit funny to see people trying to guess the meaning of something which is a common knowledge elsewhere. Puts a perspective on all the talk about “modern, global, connected, automatically translated world”.

For a decade and a half, Yandex has had a codename for each big revision of search ranking algorithms and release of new search features. Most were city names, and Magadan was one of them. So “distance” is probably a distance to some rating introduced in that release. Whether it is a positive or negative factor (cutting obvious over-optimized sites), I have no idea.

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by f311a on Monday January 30, 2023 @04:02PM (#34586333)

I’m pretty sure yellow is a slang for a category of images. It could be ad images.

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by inerte on Monday January 30, 2023 @09:55PM (#34590268)

Could be! Perhaps as in Yellow Pages?

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by ogurechny on Tuesday January 31, 2023 @07:10PM (#34604306)

https://en.wikipedia.org/wiki/Yellow_journalism

In other words, clickbait images from clickbait ad networks.

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by drusepth on Monday January 30, 2023 @09:57PM (#34590284)

It's been a long time since I've read it, but I vaguely remember a write-up many years ago (before we used ML for NSFW detection) about how either yellow images would often produce false positives in popular detection algos, and/or about how the yellow-ness of an image could be used as a lower-tech proxy for basic NSFW detection (seemingly because of its proximity to some common skin tones).

I don't know if either of these are relevant here, but it's possible a weight on Yellow Images could be related to NSFW images.

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by drusepth on Monday January 30, 2023 @10:02PM (#34590318)

Upon closer inspection, they have a lot of weights regarding "yellowness" [0], and several of them say "based on Toloka", which is an antifraud service that assigns colors to violation levels [1].

So my suspicion above is probably wrong, and "yellow" images probably refer to a Toloka score/color for whatever domain the images are hosted on.

[0] https://yandex-explorer.herokuapp.com/search?q=yellow&o=all

[1] https://join.toloka.ai/blog/project-limits/

[ Parent | on HN ]

Re:Yandex ‘leak’ reveals 1,922 search ranking factors by patrakov on Tuesday January 31, 2023 @01:45AM (#34592027)

Wrong Toloka. Yandex has its own Toloka which is a crowdsourcing platform for repetitive tasks that inherently require a human in the loop. In other words, this factor comes from real human assessors hired via Toloka.

[ Parent | on HN ]