Sentiment insights show how positive or negative someone feels during their Weekly10 check-in. We make it easy to understand how your people feel without running intrusive surveys.
Weekly10 provides an anonymous aggregated view of sentiment across your organisation. It also allows you to group and filter these insights down to department and team level to compare trends, without compromising on individual privacy.
Our sentiment analysis uses artificial intelligence and machine learning to understand how your people are feeling during their check-in. It reads the context rather than content to accurately convert those insights into data you can rely on to make informed business decisions.
See the impact of company and world events
Sentiment is relative rather than an absolute measure. That’s because the culture of different organisations leads to different preferences in communication style and often, we see large differences in ‘baseline sentiment’ between organisations that you may not expect from other engagement scores.
Sentiment analysis is useful for showing changes over time. You can quickly understand how your people are reacting towards internal or world events, enabling you to intervene and ask questions before issues escalate.
Take appropriate action, not reflex responses
Ongoing trend data helps you to isolate and understand peaks and troughs in context. This means you can implement appropriate interventions, not knee-jerk reactions. Our sentiment analysis can group your business by teams, departments or even locations helping you to find your weak points and act decisively.
Making qualitative data measurable
Weekly10 has a built-in natural language processing (NLP) engine. It uses machine learning to understand the sentiment of feedback and conversations that form part of the Weekly10 employee check-in.
We use one of the largest natural language datasets in the world to ensure maximum accuracy. An independent study in 2019 showed that across a dataset of 15,000 text paragraphs the datasets we use had an overall accuracy of 77% when compared with a human manually assessing the text.
As well as detecting the sentiment of the text within a check-in, Weekly10 also looks at the sentiment of the question being asked. This provides a weighted sentiment which is more reflective of the actual feedback provided.
How sentiment is measured
Sentiment is a measure of how positive or negative someone is when they provide feedback. In Weekly10 we provide this sentiment as a measure between 0 and 1.
Typically a score below 0.3 is on average considered negative and above 0.7 very positive. Between 0.3 and 0.7 we would term the level of sentiment to be neutral or mixed.
There's no good or bad level of sentiment, more that it should be treated as a relative rather than absolute measure. This is because the culture of different organisations leads to different preferences in communication style and often, we see large differences in ‘baseline sentiment’ between organisations that you may not expect from other engagement scores.