Where can I find a list of Hebrew stop words?
I doubt that there is one openly available, but as a simple approximation, you could create a list of very frequent tokens in a reasonably large corpus. Then, depending on your need, you can use the list as such, or filter it manually, or do some trial-and-error with your algorithm to see how it works. Here’s a list of the 100 most common tokens from a pretty large news corpus I have. Note that for my purposes, I counted various punctuation characters as tokens. The number “1” represents all the numeric tokens, hence its high position in the list. You would probably be aware of that stop list is a problematic concept in Hebrew due to the morphology & orthography – some of the useful ones are just attached to the words.
