Re:Sentiment analysis on Twitter using word2vec and keras
by b_ttercup on Sunday July 16, 2017 @05:30PM
(#14784206)
Glove is great. Simpler and faster with a very small trade off for quality. Word2vec has an advantage in that you can produce document vectors with only a small change in the network infrastructure. Tf-idf weighted word vector averages will probably be the best you can do using glove.
Re:Sentiment analysis on Twitter using word2vec and keras
by v1n337 on Sunday July 16, 2017 @07:19PM
(#14784622)
The GloVe project just happens to have pre-trained models on their official page.
Word2vec do have a Google News corpus model on their official page, but there are many more trained word2vec models in the literature.
Re:Sentiment analysis on Twitter using word2vec and keras
by ahmedbesbes on Sunday July 16, 2017 @05:06PM
(#14784117)
thank you for the feedback, I'll definitely give it a shot.
Haven't had the opportunity to measure the difference in quality, and I've mostly used word2vec until now (with vectors I've trained myself after lemmatization and PoS-tagging of a corpus), but the fact that GloVe provides you different trained models from twitter, Wikipedia and so on is pretty nice