word2vec-spam-filter
AI
spam classification
SHOW HN2017
104points
21comments
#439of 2,242 in 2017
Top 20%of 2017 by points
How HN took it
DebatedReal support and real criticism
2 positive, 2 neutral or asking, 0 mixed, 2 critical, out of 6 comments about the project. Thread score -0.07.
Idea: 2 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Interesting, fun project idea
From 1 comment
Sounds like a fun project. However, I doubt if word vectors buy you anything more than, say, old good Nilsimsa from 2001 (https://en.wikipedia.org/wiki/Nilsimsa_Hash). Side note:…
mci on HN
Word vectors can catch paraphrased spam
From 2 comments
word2vec has the advantage that you could potentially identify spam messages that are paraphrases rather than exact copies of the ones in the training set.
laretluval on HNIt seems DCC isn't using word vectors at all? Using word vectors you can know that viagra and v14gr4 is the same word, because it is used in the same way in messages. That in…
EmilStenstrom on HN
Objections
Nilsimsa hashing may do as well without word vectors
From 2 comments
Sounds like a fun project. However, I doubt if word vectors buy you anything more than, say, old good Nilsimsa from 2001 (https://en.wikipedia.org/wiki/Nilsimsa_Hash). Side note:…
mci on HN1. Pedantically: it's GloVe, not word2vec. 2. Nilsimsa or any locality-sensitive hash detect changed messages, too, be the changes synonyms or not. 3. I don't think OP's GloVe…
mci on HN
Bulk sending is a weak spam signal on its own
From 1 comment
That, and the fact that a message is sent in bulk isn't actually a very strong indicator that the message is spam, at least in the email world. As one input to a filtering…
massaman_yams on HN
Requests
Train vectors on own spam dataset
From 1 comment
We don't have words like v1agra. As I mentioned in the README, we took vectors pretrained on wikipedia. One of the possible improvements can be to train the vectors on our own…
doody_parizada on HN
Questions
Does it use word2vec or GloVe?
From 2 comments
I was hoping to learn about word2vec by reading the sourcecode but am I right when I say this has nothing to do with word2vec?
chrbarrol on HNLooks like it uses GloVe and not word2vec. They're both algorithms for generating word vectors but they are different.
drwl on HN
Alternatives named
Nilsimsa hash
From 1 comment
Sounds like a fun project. However, I doubt if word vectors buy you anything more than, say, old good Nilsimsa from 2001 (https://en.wikipedia.org/wiki/Nilsimsa_Hash). Side note:…
mci on HN
DCC
From 1 comment
This sounds like an early version of DCC: https://www.rhyolite.com/dcc/ At first glance, I don't see anything that DCC didn't do, what did I miss?
Arnt on HN
ConceptNet Numberbatch
From 1 comment
Maybe look into ConceptNet Numberbatch: https://github.com/commonsense/conceptnet-numberbatch/blob/master/README.md
physicsyogi on HN