Skip to content
English
  • There are no suggestions because the search field is empty.

Comment Analysis

Comment Insights - part of Comment Analysis - proactively surfaces the most relevant insights based on an aggregate analysis of the qualitative feedback your employees have shared in the last 90 days. To access Comment Insights, navigate to the Milestone page, then open the Comment Analysis tab.

If your organization uses Point in Time surveys, you may also see Comment Insights for any closed Point in Time survey, calculated after the survey has closed.

Filters can be applied to Comment Insights to drill down into specific locations or roles where these insights may be more resonant, but the insights themselves will not change.

Defining an Insight

A Comment Insight is a pattern or trend identified through analysis of comments submitted by employees. Insights are generated leveraging proprietary AI analysis, semantic similarity and clustering algorithms to review all open-text comments in a user’s scope. Each day, WorkStep analyzes milestone survey responses and any newly closed Point in Time surveys to render this analysis. This analysis identifies granular trends and patterns that would otherwise go undetected.

In order for an Insight to qualify, there must be at least three unique employees who have shared relevant feedback related to the insight. 

Understanding the Comment Insights Table

The Comment Insights table refreshes daily and includes the Comment Insight, the weekly volume of relevant comments, the number of employees who have shared feedback related to the insight and sentiment. 

  • Comments by Week measures the total volume of comments related to that comment insight over the last 90 days.
  • Employees measure the number of unique employees who have shared related feedback in the last 90 days.
  • Sentiment provides an aggregate view of the sentiment for that comment insight. WorkStep uses Google’s natural language processor (NLP) to determine the sentiment of each open text comment and does not calculate sentiment for comments that are 1 word or less. 

At the top of the table, you'll also see a chart which displays the total number of comments displayed and the number of comment insights generated from those comments. Not every comment will have a related comment insight.

Default sorting of the chart is in order of Comments by Week. Users may also filter the Comment Insights table using any of their available filters. Filtering the table will not generate new or different Comment Insights, but will adjust comment volume, employees and sentiment according to the filters applied.

Individual Comment Insight Analysis

To explore an individual insights, click into an individual Comment Insight to see a summary of the comment insight, a chart of weekly comment volume, and sentiment. To the right of those charts, all of the relevant comments related to that comment insight will be visible. Each comment also includes an opportunity to share whether or not that comment is relevant to the comment insight to help inform future analyses.

What’s the difference between Comment Insights, Alert Categories and Opportunity Themes?

  • Opportunity Theme: A comment’s theme is based on the content of the survey question which elicited a comment response. For example, a comment under the “Safety” theme is categorized as such based on the question the survey participant was responding to. 
  • Alert Category: Alert categories are assigned to individual comments based on the feedback shared by the employee and whether or not that feedback meets the criteria for certain alert categories.
  • Comment Insights: Unlike themes and alert categories, Comment Insights consider comments in aggregate. A Comment Insight may include individual comments that have themes or alert categories. Additionally, Comment Insights evolve based on the content of comments overtime, while alert categories and themes are static and never change.
  • Topics: A topic groups together comments with a common subject matter, regardless of the specific language used. For example, the safety topic could include a comment that references hazardous conditions in the warehouse, even though the word “safety” is never used in the comment.

    Topics provide users with a comprehensive understanding of employee feedback on a specific issue. A comment can belong to more than one topic, or to none if there’s nothing relevant.