Machine Learning & AI

Modern Data Platform

Call Center Sentiment Analysis: Client Relationships Redefined

As a worldwide supplier at the forefront of the building materials market, the competition is fierce. This major developer and producer of construction components employs nearly 20,000 people across the world and serves clients internationally as well. With the ubiquitous nature of their clientele, communication and relationship building has been challenging. The company enlisted BlueGranite and together we:

  • Established a centralized hub to log and monitor client statistics
  • Implemented a system to produce visual reports, facilitating communications with stakeholders
  • Streamlined account management protocol by automating audio to text transcription

According to BusinessWire, the global building materials market is projected to reach $187.48 billion in revenue by the year 2026. The massive market is trending upward, boasting an average of 5% growth each year since 2012. With so many players within the industry, suppliers do not have the luxury of room for error. 

Azure Speeds Manufacturer Toward Coveted 360-degree Customer View

Before partnering with BlueGranite, the organization was having a difficult time collecting and processing feedback from their clients. With hundreds of calls and emails a day, clients were offering up plenty of information, but the company had no method of analyzing and categorizing the nature of the calls and emails or the quality of their client relationships. Short of manually listening to and transcribing each call, or reading through every email, there was no way to centralize and gain performance insights from the vast quantities of data without making a significant change. Overall, they were missing out on meaningful client engagements, which is a crucial part of retention and growth.

The company knew that it had to take measures to improve client engagement efforts. By implementing a system to transcribe the feedback and compile it into a central hub, the supplier would be able to analyze the data and act accordingly. A big part of client satisfaction and refining your product is reacting to the client’s feedback; taking steps to streamline that process was crucial.

We teamed up with the company to design a customer sentiment analysis solution – paving the way for meaningful client engagement, greater fraud detection, higher satisfaction rates, and greater insight. We set out to create an integrated client view across three different channels – voice, email, and chat. To have this all information in a single repository gives organizations a powerful engagement tool.

Microsoft Azure Made it Simple

Utilizing Microsoft Azure simplified the process of gathering and compiling data into comprehensive reports. We were able to check the pulse of their clientele by reviewing email and phone call records and used a variety of Azure services to consolidate the data, transcribe audio, and extract the overall tone of the messages.

Pulling It All Together

To remain competitive, companies must be able to gather client feedback and complaints quickly, escalate them to the proper managers and respond expeditiously. After implementing the solution, the organization had almost instant insight into the challenges and successes of their clients across the globe.

Due to taking advantage of multiple Microsoft technologies, the manufacturer can now easily gauge if they have a happy customer, and, if not, take steps to make their experience better, all thanks to:

  • An automated way to transform audio to text
  • A centralized location to store those conversions, along with email text
  • A system to piece together all of the data
  • An analytics system to monitor sentiment
  • Power BI’s rich visuals to help stakeholders see the big picture

The client is now enjoying the benefits of greater client satisfaction and increased retention and account growth. The client’s ratings improve daily, allowing them to leverage their reputation to grow their client base.

Are you having a hard time connecting with your clientele? Contact BlueGranite today to discuss how we can help facilitate engagement and improve your services today.


  • We used Azure Functions to monitor Azure Blob Storage for new audio files. A new file triggered a speech-to-text transcription from Azure Media Services. The Azure Function also converted the raw TTML output from Media Services into a tab-delimited text file.

  • We employed Azure Data Factory V2 to orchestrate the movement of raw call and email text data through Azure Data Lake Store, Azure Data Lake Analytics, Azure Machine Learning, and Azure SQL Database.

  • We used Azure Data Lake Analytics to obtain sentiment and key phrases from the text, transform the data, and saved the final form to Data Lake Store. We built  custom topic and clustering models in Azure Machine Learning to further enrich and categorize the data.

  • We used Azure SQL Database as a final data mart and Power BI to visualize the data.