Wix, a leading SaaS website building platform for creating, managing and growing a global, digital presence for over 263 million users worldwide, was an early adopter of the innovation and technology that enables businesses to build a powerful digital presence on the internet. The Wix customer care representatives are responsible primarily for guiding Wix customers in building and setting up their online businesses.
Wix customer care support of Wix users takes the form of conversations, which sometimes can become quite long, naturally. Traditional sentiment analysis models fail to support conversation datasets, especially long ones. Another shortcoming of traditional sentiment analysis is a lack of support for highly subjective subjects, such as if something is said to be beautiful. Wix customer care set a goal to understand and anticipate its customers’ sentiment toward Wix’s products and sentiment for the actual support services. Traditional ways of achieving this understanding are through surveys, which only about 20% of users complete, and the survey results can be highly biased. Conducting these surveys also takes time, which delays the representatives’ primary responsibility of helping customers build websites.
Wix enlisted the expertise of the IBM® CTO Office, IBM Research®, IBM Expert Labs and IBM Client Engineering to address a critical challenge: comprehensively understanding the sentiment of every Wix customer interaction with Wix support, quickly and accurately. Collaboratively, IBM and Wix researched and developed a machine learning model with the IBM watsonx.ai™ AI studio. Then watsonx.ai enabled the teams to collaborate on a shared development environment using notebooks, share data by Wix, train and test the system quickly and, eventually, integrate the system with GPUs to ensure swift inference directly from the notebooks, streamlining the entire process.
The test was a success. The developed product was deployed into production, and Wix’s customer care management now actively uses it to continuously monitor users’ sentiment toward Wix products and Wix support services. While adhering to strict data protection regulations, the model is now active on about 50% of Wix support interactions, soon to expand to 100%. It is used to create an important KPI that measures the quality of Wix support and is gaining trust of customer care in the AI model analysis.
Being able to monitor users’ sentiment in real time enables Wix customer care management to optimize its representatives’ operations as well as fine-tune Wix products according to users’ feedback. The implementation of this project was so successful that this model’s sentiment prediction has now become one of Wix’s main KPIs that it tracks and uses to guide its entire organization accordingly.
Founded in 2006, Wix (link resides outside of ibm.com) is a leading SaaS website building platform that offers a complete solution from enterprise-grade infrastructure and business features to advanced SEO and marketing tools—enabling anyone to create and grow online.
Legal
© Copyright IBM Corporation 2024. IBM Corporation, New Orchard Road, Armonk, NY 10504.
Produced in the United States of America, April 2024.
IBM, the IBM logo, ibm.com, watsonx, watsonx.ai, and watsonx.governance are trademarks or registered trademarks of International Business Machines Corporation, in the United States and/or other countries. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on A current list of IBM trademarks is available on https://www.ibm.com/legal/copyright-trademark.
This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates.
All client examples cited or described are presented as illustrations of the manner in which some clients have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Generally expected results cannot be provided as each client’s results will depend entirely on the client’s systems and services ordered. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.
The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the client is in compliance with any law or regulation.