Sentiment Analytics

About the Customer & Challenges Faced:

Press Ganey is a leading provider of patient experience measurement & performance analytics. They conduct a variety of patient experience surveys in hospitals and collect feedback to analyze every dimension of the patient experience. Healthcare providers are then provided a rating (on a five-point scale), based on the feedback. While it may be relatively easy to analyze the structured ratings provided in the feedback, additional effort is required for the analysis of unstructured comments. Reading all the comments in every section of each feedback form is humanly impossible.

Our client, a healthcare provider based in Pennsylvania, wanted to investigate patient sentiments and relate them to various business aspects.

Solution and Approach:

  • A large healthcare provider catering to patients in Philadelphia, Pennsylvania, and New Jersey wanted to improve the patient experience by analyzing patient sentiment extracted from free-text comments in their patient feedback forms.
  • framework provides out-of-the-box development platforms. The project was started seamlessly with the relevant environments which were then created automatically. Development images configured based on pre-defined templates were installed on-premises or in a development VM within the infrastructure. This enabled authentication using LDAP, seamless project setup using Bitbucket, Jenkins and Docker (ensuring build and deployment without software compatibility issues).  ​
  • The framework made available by leverages the latest ML and DL tools while preparing models and includes Pachyderm-based data versioning, deployment using a Kubernetes orchestration system, Kubeflow and Spark-based ML and DL build and deployment, Istio-based service mesh enabled microservice architecture, and ELK based monitoring capability; contributing to reduction in latency time.​
  •’s MLOps framework allows establishing high-end Alluxio and Presto-based efficient data connectivity and collecting data from diverse sources. The context from the patient feedback forms was captured by a word embedding layer (word2vec) and added as exploratory variables by using libraries.
  • By using data versioning and connectivity libraries, data versions were easily controlled, stored in xpresso Data Model (XDM)-enabled data store. This enabled easy retrieval and storage of datasets/ files into internal XDM. The attributes obtained were used for categorization (employing Pachyderm-based data versioning) and then performing univariate, bi-variate and Bag of Words analysis — for both structured and unstructured datasets through xpresso Exploratory Data Analysis (Data and Statistical Analysis). Different datasets and their different versions were easily controlled and stored in xpresso Data Model (XDM)-enabled data store that enabled easy retrieval and storage of datasets/files into internal XDM. This was achieved by using two excellent features of ​
  1. Data Connectivity Marketplace libraries​
  2. Data Versioning​
  • The output was then fed into the LSTM model, a type of Recurrent Neural Network, to classify texts into desired categories. ​
  • The solution provided an accurate assessment of patient opinions about different performance aspects of the hospitals and helped our client to identify key pain points for patients through various stages of their healthcare journey. The client is witnessing a considerable increase in the positive sentiments along with an increase in the performance ratings, which is translating into an increased footfall and revenue.​


  • By using, one can leverage high-end data connectivity, efficient data versioning, perform exploratory data analysis and generate inferences using an intuitive process and through an industry-standardized manner.
  • The unique, containerized platform-centric approach offered by can be used to employ required infrastructure, deploy rapidly to multiple high-availability environments while aligning with best-in-class DevSecOps practices.
  • also brings in-depth QA-QC testing and logging frameworks, synchronous and asynchronous monitoring, and performance tracking ability.
  • also has SSO (single-sign-on) for various in-built tools and subsystems that make the platform access seamless throughout.​
  • In a nutshell, all the above features in a single plate under the same hood make an unbeatable AI Ops framework.

Have Any Questions?

Need more information about the platform?