The client wanted to improve patient experience by analysing comments in the patient feedback forms
Objective
Analyze patient sentiments from free text comments in the patient feedback forms
Abzooba’s Solution:
Machine learning techniques are being used to automatically categorise opinions as either positive, neutral or negative and relate them to separate business aspects
The contexts are captured by a word embedding layer: word2vec
The output is then fed into an LSTM model, a type of Recurrent Neural Network, to classify texts into desired categories
SoftMax based attitude detection algorithm are used to identify the user sentiments efficiently
Business Benefits:
Providing accurate assessment of patient opinions about different aspects of the hospitals
