Editorial
When we think of how generative AI can improve employee engagement, one of the first things that comes to mind is using generative AI to help craft targeted content that employees are more likely to read and engage with. But employee engagement is far more than having compelling content. AI is not human and lacks the human nuances that build employee engagement.
We subscribe to definitions like this one from Gallup:
Employee engagement is the strength of the mental and emotional connection employees feel toward the organization that they work for, their team and their work.
On a day-to-day basis, employee engagement can be assessed and measured at scale through the online conversations had on internal social networking sites. These sites typically host online communities that can, and do, facilitate mental and emotional connections with work colleagues, and ultimately, the organization at large.
Not All Online Communities Are Equal
We have been benchmarking online communities within Viva Engage (formerly Yammer) for nearly a decade. Over that time, we have seen a gradual deterioration in what we call “true communities of practices,” where deeper knowledge sharing and learning occurs within particular work practice contexts. Communities of practice are where subject matter experts can connect and progress their “best practices” to even greater heights. They are also where less expert staff can learn from domain experts as well as each other. In other words, develop the mental and emotional connections associated with employee engagement.
Instead, the majority of online communities facilitate information sharing where only a few contribute and many more read. Some examples include transactional question and answer facilities, non-human centered status or news updates, management broadcasts, etc. Information-centered communities are largely transactional, creating little, if any, human connections to the contributor or anyone else; therefore contributing little to true employee engagement.
Related Podcast: Why Communities Are the Organizational Model of the Future
Generative AI Can Supersede Information-Sharing Communities
Researchers studied the impact the introduction of ChatGPT had on the usage of transactional information sharing community sites versus more human relationship centered communities. They published their findings in Nature, “The consequences of generative AI for online knowledge communities.”
Stack Overflow is a hugely popular site for software developers to have their technical questions answered by fellow site users. Reddit is an acknowledged online community space which prioritizes human connections. The researchers selected the area of Reddit where the topics overlapped with those of Stack Overflow.
The introduction of ChatGPT had a dramatic effect on the use of the Stack Overflow Q&A platform and virtually no effect on the human-centered Reddit site. If we project these findings onto the use of online communities in social networking platforms like Viva Engage, we could expect a significant drop in activity on communities used specifically for transactional information sharing. Those would likely reduce or even disappear, leaving the human-centered ones to thrive.
This is a good thing. In effect, generative AI could remove much of the noise we see in online community spaces, leaving those that are more aligned to deep knowledge sharing and learning free to achieve the genuine employee engagement organizations desire.
Related Article: We're More Disconnected at Work. We Need Communities Over AI for Wellbeing
Can Generative AI Help Build New Connections?
To test this proposition we used ChatGPT4o to read an image of a social network graph:
We then asked it some questions about creating new connections.
Question: I am new to this group. Who should I meet who could introduce me to the most group members?
ChatGPT: Based on the network diagram you provided, the best person to meet for introductions to the most group members would be Edward. Edward is directly connected to six other members (Adam, Jane, Fred, Betty, Carl and Diane). By meeting Edward, you will have the opportunity to be introduced to the most members of the group quickly.
Question: So Edward has the most direct connections. But is Edward also the person who is best positioned to reach everyone in the group, either directly or indirectly?
ChatGPT: It appears that Fred and Edward are both well-positioned, but Fred has a unique advantage in that he is directly connected to both Edward and Gail, which are the key nodes for further connections. Therefore, Fred might be better positioned overall to reach everyone in the group, either directly or indirectly, considering the shortest paths.
While imperfect, this test shows that ChatGPT4o has a good grasp of social network analysis theory and is able to offer practical advice on building connections.
Related Article: Microsoft's Copilot in Viva Engage and the Trouble With AI Overreliance
Webinar
Sep
25
CMS Briefing: A Live Look at What’s Next in AI-Driven Platforms
Learn how leading organizations are using AI‑driven tools to publish faster, personalize smarter and stay secure.
Register
Webinar
On demand
Ready or Not: How Data-First Organizations Are Unlocking Agentforce Potential
Learn how to cut through the noise, activate Agentforce and build a Salesforce AI strategy that actually delivers.
Watch Now
Webinar
On demand
AI in Customer Service: Faster Resolutions, Happier Customers
Don’t let rising demand burn out your team. See how to build a smarter, more resilient support org.
Watch Now
Webinar
On demand
From Hype to High-Impact CX Strategies That Actually Scale
Turn buzzworthy AI and outsourcing trends into measurable CX wins with fresh 2025 data.
Watch Now
Webinar
On demand
Insights to Action Rethinking the Contact Center for Real Business Impact
Join our exclusive webinar to hear CX executives share their innovative strategies for transforming service delivery.
Watch Now
Webinar
On demand
Accelerating Healthcare Ops with AI
Sign up to see how your peers are putting AI to work — and making it stick.
Watch Now
Implications Going Forward
Use of generative AI internally within organizations is still in its infancy. We will soon undertake our 10th Viva Engage benchmarking study, so will look to see if the effect shown above is reflected in the results.
In the longer term, we anticipate that generative AI will help staff write more engaging and targeted content. It will also improve information access for staff, obviating the need for many information sharing communities. Finally, presented with connection data, it will be able to aid individuals build better networks at work.
Collectively, despite its lack of humanness, generative AI on balance, will be a positive influence on employee engagement.
Learn how you can join our contributor community.
