I am working on a dataset of amazon alexa reviews and wish to cluster them in positive and negative clusters. I am using Word2Vec for vectorization so wanted to know the difference between Text Embedding and Word Embedding. Also, which one of them will be useful for my clustering of reviews (Please consider that I want to predict the cluster of any reviews that I enter.) Thanks in advance!
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
4
A Text embedding is a vector representation of a text. A trivial way to construct a text embedding is to average the word embeddings of each word in the text.
However using this method, you will lose contextual information.
-
$\begingroup$ oh okay! But if i have to predict cluster for a new review(text) then won't I be needing text embedding? Or can i do the same using word embedding too? $\endgroup$ Nov 20, 2020 at 19:02
-
$\begingroup$ for your use-case text-embeddding (doc2Vec) is most likely the easiest first step $\endgroup$ Nov 20, 2020 at 20:31
-
-
$\begingroup$ @chikitin no, you can take the average of each word embedding in a text to construct a basic text embedding. The embedding would not take word order into account but would create some averaged topics of words $\endgroup$ May 17 at 19:46