What HR Needs to Know About Sentiment Analysis

What HR Needs to Know About Sentiment Analysis

In the brave new world of employee monitoring technology, one of the most fascinating developments is the refinement of sentiment analysis, which promises to give employers timely and accurate data about how their employees are feeling. The Atlantic’s Kaveh Waddell gives an overview of where this technology came from and where it is going:

The field—known as sentiment analysis—got its start in market research. As online reviews started to gather steam in the mid-2000s, companies who wanted to understand how their products—or their competitors’ offerings—were being received began to use algorithms to aggregate reviews, says Bing Liu, a professor of computer science at the University of Illinois, Chicago, who has written extensively about the history of sentiment analysis. The algorithmic approach could reveal broader insights than a focus groups or surveys, the thinking went. …

More recently, the corporate world has turned these same tools inward. Large companies like Accenture, Intel, IBM, and Twitter have started using the software to understand how their own employees feel about their jobs, and identify problems that might escape a harried supervisor during annual-review time. …

Sentiment analysis is far from a polished technology. “The computer’s understanding of natural language is still bad,” says Liu. “Accuracy is not very easy.” A research project that tested basic analysis tools on a trove of emails sent between developers of an open-source server software suite only had a maximum accuracy rate of 30 percent. (Interestingly, when two people tried to determine the emotions expressed in 50 emails, they could only agree on three-quarters of them, says Tourani Parastou, the main author of the research paper at Polytechnique Montréal.)

Indeed, we’re seeing a boom in start-ups and corporate analytics teams offering real-time sentiment tracking tools as part of the digital transformation of HR. Employee engagement teams, for example, are moving away from large, annual or semi-annual engagement surveys that are arduous and backward looking. Tools ranging from pulse surveys and mood trackers, to social network analysis and health monitoring, now provide a wide variety of new, on-the-go sources of data for companies to better gauge employee engagement. HR is transforming into a data and tech-savvy function, but better data is not enough for HR practitioners to fully adopt these innovations.

First, in our survey and conversations with hundreds of heads of Engagement, the number one challenge they have identified is not about the quality of data they have, but rather about putting engagement problems on the agenda and getting leaders to do something about them. One member even said to us that data was only helpful if it served as a catalyst for action; the quality of data and analysis was secondary. That being said, the best innovations are those that don’t just provide great insights, but also help users chart the way forward. (CEB Corporate Leadership Council members can read all the findings from our survey of engagement leaders here.)

Second, while natural language processors and newer technologies like facial scanners may be getting better at accurately identifying employees’ feelings from their word choices or expressions, the science connecting this data to the issues HR cares about (e.g., long-term employee engagement, intent to stay) remains murky at best. I might be frustrated at times with the work I do, but that’s because I am engaged with work that is challenging me, not because I want to flip my table and leave the office. That is why companies like IBM are doing right by employees and clients by having analysts examine the trends first before submitting their findings. CEB’s analytical tools, likewise, are developed from the efforts of hundreds of I/O psychologists and researchers investigating the relationship between specific employee perceptions and behaviors.

The state of sentiment analysis is truly making tremendous progress, but however quickly these technologies advance, only those with concrete applications and sound science will appeal to potential users.