Practical NLP for Finding Wifi in Hostels

racketracer.com

119 points·racketracer··10 comments

Based on the title I was sure this was going to be about how to phrase requests for WiFi access in places you aren't staying.

"You want to tell me where the wifi is you are feeling good for me."

That in itself is another Twitter bot. Find all hotels 100 feet away and send them mentions via Twitter

It's worth mentioning www.hotelwifitest.com as a (probably?) more accurate way of determining wifi speed and price...

That can't tell you if the range is crappy, or if it cuts out often.

Ah. I was thinking it was the other kind of NLP : "These are not the access points you are looking for"...

I like this version better.

As an aside - have you read about the supposed NLP used by Obama in his speech cadence and delivery? I think its quite fascinating... just google Obama NLP

> Overall there’s too much information that can’t really get stuffed into 140 characters which is quite a sham

You could have a "verbose" mode (e.g. put -v at the end of the tweet) which abbreviates everything to one or two characters and omits the best review phrase.

This is interesting.

Yelp has also started doing something along these lines selecting quotes from reviews in which a word that occurs frequently has been found.

I would suspect that instead of word frequency, they likely use TF-IDF (or even better, BM25[1]) or LDA [2] to identify relevant keywords to highlight.

1. https://en.wikipedia.org/wiki/Okapi_BM25

2. https://en.wikipedia.org/wiki/Latent_Dirichlet_allocation

Reply on news.ycombinator.com