Deep NLP Project:- Sentiment Analysis of Alexa Reviews using LSTM
About the Data
Amazon Alexa is a cloud-based voice service developed by Amazon that allows customers to interact with technology. There are currently over 40 million Alexa users around the world.This dataset consists of a nearly 3000 Amazon customer reviews (input text), star ratings, date of review, variant and feedback of various amazon Alexa products like Alexa Echo, Echo dots, Alexa Firesticks etc. for learning how to train Machine for sentiment analysis.
What you can do with this Data ?
You can use this data to analyze Amazon’s Alexa product ; discover insights into consumer reviews and assist with machine learning models.You can also train your machine models for sentiment analysis and analyze customer reviews how many positive reviews ? and how many negative reviews ?
Dataset Information:
- Dataset contain 3150 Alexa Reviews with Customer Rating.
- In dataset reviews are given rating between 0 to 5.
- Reviews with
Rating > 3 are consider as Positive SentimentandRating <3 are consider as Negative Sentiment
Word Cloud
- Word Cloud is a visualization technique for text data wherein each word is picturized with its importance in the context or its frequency.
- The more commonly the term appears within the text being analysed, the larger the word appears in the image generated.
- The enlarged texts are the most number of words used there and small texts are the less number of words used.
Word Cloud of Positive Sentiment
Word Cloud of Negative Sentiment
Deep NLP Model Building
-
Batch Size = 32
-
Epochs = 40
-
loss = 'categorical_crossentropy
-
optimizer = 'adam'
-
Traning Accuracy : 98.30%