Comment Analysis

Comment Insights has replaced "Trending Topics" in WorkStep.

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.

Comment Insights Table

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.

Full Text Search:

Looking for comments related to a particular term? Input one or many keywords into the search bar to search comments over the last 180 days.

💡Tip: When searching multiple keywords at once, separate the words by a space.

You'll be able to apply filters to narrow results either before you begin searching or after results have been returned. Note that all searches will be “OR” searches and the current version does not support exact searches or “AND” searches. An “AND” search would only populate results that include every word included in that search, while an “OR” search will populate results that include any of the words included in the search. For comments in languages other than English, the platform will search the translation of the comment.

Sentiment Analysis

As part of both Comment Insights and the results of full text search, we’ll provide an aggregate view of the sentiment of the Comment Insight or the search term(s). 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.

Sentiment is bucketed into 3 groups: negative, positive or neutral. If the NLP has low confidence in the sentiment bucket we will consider it neutral sentiment. If a sentiment cannot be determined, it will be considered “null” and will not be included in the sentiment graph or counts.

Calculations

The frequency graph is calculated by the individual comments and begins on Sunday of each week. As an example, if an employee mentioned “schedule” 4 times in a single survey and a user searched for “schedule,” we would count that 4 times in the frequency chart for those full text search results.

Attribute charts will respect the confidentiality threshold of three or more respondents. This means that if there is a comment that comes from a Forklift Operator, for example, and that’s the only Forklift Operator in those search results, we will not show a bar for that role on the by role attribute charts.

The sentiment graph hover-over will show the count of individual comments that make up each bucket. Because some comments that are part of the search could have a “null” sentiment, the counts may not always match up to the total comment count.

Comments will display in order from most to least recent and will contain the same chips as on the comments tab - respecting anonymity threshold. You'll be able to export the comments in the same format and including the same fields as the comment export from the comments page by clicking on the download icon in the top right corner of the comment panel.

Term Expansion

Using the same logic and technology used to determine the Topics for Trending Topics by Bright™, we’ll suggest topics for users to add to their search based on their initial search. You can select multiple topics to expand your search, and can continue to add keywords as well.