Discussion on "How we autodetect spam using Google's Vertex AI"

Sandeep Panda · 2021-12-02T10:39:51.215Z

One of the downsides of our recent growth was an increase in spam. Since we all hate spam, and it was diluting the quality of content, we started cleaning up manually. But soon we realised that it wouldn't scale, and we ended up wasting an hour or so...

What is the cost that incurs on integrating vertex ai? I used their calculator and even the most basic machine, running entire week for 23 hours everyday, it went to $41. Or how does it work? Do you need to run it all the time or run it periodically?

Amazing Work !!!

Love the solution and the technical detail

It is not just an "announcement post"

This is absolutely a great post with technical details on how to recognize, approach a problem and then solve it. Kudos to you!! 👌🏻

Oh wow this was really interesting to learn. Spam is such a nuisance.

Holy cow this is amazing 🔥

I like how discord bot was also integrated to keep an eye for false classification

This is really amazing! I think especially the fact of using an automated ML approach in combination with manual checkups (discord bot) is really useful.

Great job 👍🏽

Are you still using only the displayName for predicting or the content as well?

Thanks! As of now, we are simply considering title. This has reduced spam content by ~95%. I think we'll go deeper and check the content as well after observing the current setup for a while.

Discussion

How we autodetect spam using Google's Vertex AI

Responses(6)

Recent in Forum

Search Hashnode

How we autodetect spam using Google's Vertex AI

Responses(6)

Recent in Forum