Used Recurrent Neural Network to extract the aspect of textual restaurant reviews
o Analyzed restaurant reviews from the SemEval 2014-Task 4 data set and created normalized vectors from words using the word2vec function from the gensim library.
o Implemented a Recurrent Neural Network with the word vector input for aspect extraction in TensorFlow to predict output aspect vectors.
Run:
-
Run the word2vec.ipynb file to create the word vectors and create the word2vec.csv
-
Run the AspectExtraction_Using_RNN.ipynb to train the RNN network and estimate the loss.