Speaker's blog: How text analytics is changing the employee survey

by Andrew Marritt

​The use of text analytics in HR will be discussed in detail by our speaker Andrew Marritt, who is the founder of OrganizationView, a Swiss-based people analytics practice, at the HR Analytics online conference.

In my last post, I discussed the process by which employee engagement increases and decreases and therefore what are the most effective interventions leaders can use to make a long-term difference. In this post, I explore the related question - what do we need to change?

As People Analysts, OrganizationView have conducted a lot of surveys over the last six years. One thing we’ve come to appreciate is how important employees’ open text comments are to driving action from management. The issue has usually been how to deal with tens of thousands of comments, provided in multiple languages. This was one of the driving forces behind our decision to develop Workometry, our employee feedback platform.

Europe HR

HR Analytics

Visit event website
Before the advent of reliable text analytics, analysing these comments at scale was time and cost prohibitive. The way that employee surveys have developed has largely been influenced by this constraint. However, just as statistics has been changed by the availability of large, easily available computing power and cheaper acquisition costs for data, we predict that our understanding of employees will be changed by the availability of text analytics.

With text, there are two main tasks that we want to do: we want to categorise the text into one or more topics and we might want to score the text on some sort of scale, for example, by level of sentiment.

When categorizing, we want to go further than just words. We look at two dimensions - the topic (e.g., ‘career development’) and the context (e.g., ‘shortage’). This has to be more than just keyword as we’ll want to link together the multiple synonyms - it’s the meaning not the words that they’ve chosen which is important.

Doing this adds metadata to our text. We can then apply various statistical techniques to the metadata. Typically, we identify in the region of 40–60 different topics for any text question. We can think of this as equivalent to adding another 40–60 scale questions to a survey. Therefore, we can ask the short surveys that are needed to maintain response rates when you’re doing them frequently whilst capturing very rich data. We use an unsupervised learning approach meaning that the topics are suggested by the data, not precoded based on generic results.One of the reasons that we do analysis is to draw attention to the parts of the information that managers need to focus on. We’re currently doing that by combining two techniques.Read the complete blog post and much more from Andrew Marritt here.

Interested in this topic?

More articles


An interview with Hamdah Said Al Shamsi, Acting General Manager, Public Authority for Social Insurance (PASI)

Hamdah Said Al Shamsi has wide experience in the field of finance and management along with more than 25 years of leadership experience with the Public Authority for Social Insurance (PASI) where she held various roles and with the United States Agency for International Development (USAID). She is also a contributing editor to several major magazines and newspapers in Oman. Mrs Al Shamsi has authored four books. Ms Shamsi is also a speaker and an active member of Toastmasters International in Oman.


Bottling Success: An Interview with Dalila Safir

Ms Dalila Safir possesses more than 15 years of experience in HR and Communication. Throughout her career, she has held different roles in the HR function, in multinationals organization, including Alcan (Aluminium and Packaging), where she spent 10 years. She holds a Master and Post Master Degree in HR & Communication from University Paris IV Sorbonne and a Master in NLP Coaching from Mindbrige. She also teaches HR Marketing and HR Management at the University of La Sorbonne Abu Dhabi.Ms Safir is currently the HR Director for Aujan Coca-Cola Beverages Company where she has implemented a novel HR strategy structured around 3 main pillars Alignment-Capability-Engagement to support the Group vision to become a world class bottling operation.


The Rules of Employee Engagement

Take a look at the infographic talking about "The Rules of Employee Engagement"