Physicians Review Sentiment Analysis | NLP Application Development Services

Overview

Our client is a US-based start-up specializing in online reputation management for Health care providers like hospitals and private practices. The Client wanted a solution built using NLP and Machine Learning pipeline to analyze feedback from patients regarding their doctor’s visits. From the patient review, we extract entities, score them on the sentiment and rank the entities based on common positive and negative attributes. The result of the analysis is visualized in a dashboard.

Our Solution

  • Trained a machine learning sentiment classifier to score entities as positive, negative and neutral from historic data.
  • Built a custom NLP pipeline to identify and extract hidden entities in the review text and extract the sentences associated with the entities.
  • The text related to the hidden entities is scored using the trained classifier.
  • Trained a model to detect and extract the most common positive and negative attributes that has the highest correlation with review sentiment.
  • The entities are ranked across these common positive and negatives attributes.

Architecture Diagram

Tech Stack

Related capabilities

Free Consulting