prepare_w2v_embeddings: prepare_w2v_embeddings

In alex-gottlieb/deepIdeology: Scale Ideological Slant of Twitter Posts

Description

This function trains a word2vec model to create custom word embeddings from the training data set.

Usage

prepare_w2v_embeddings(texts, embedding_dim, tokenizer)

Arguments

texts	Character vector of raw text from training data.
embedding_dim	Dimensionality of word embeddings. Options are 25, 50, 100, 200.
tokenizer	Pre-fit keras text tokenizer.

Details

For a good introduction to word2vec model see Distributed Representations of Words and Phrases and their Compositionality (Mikolov et al., 2013)

Note

Embeddings are saved as Rdata to a folder called embeddings with the file format "tweet_wv2_{embedding_dim}.rda"

alex-gottlieb/deepIdeology documentation built on Nov. 1, 2019, 9:09 p.m.