Siftsy Docs
Extracting Key Insights

How to interpret sentiment scores

Use this guide to understand how Siftsy categorizes comment sentiment and what the sentiment breakdown tells you about your audience.

To view sentiment scores, you need to create an analysis first. See How to start analyzing comments


Sentiment categories

Siftsy classifies each comment as positive, negative, or neutral based on its language, tone, and context. These classifications feed into the overall sentiment distribution shown in your analysis.

Positive comments express approval, excitement, agreement, or satisfaction. Examples include praise, thanks, expressions of love or enjoyment, and constructive support.

Negative comments express criticism, disappointment, disagreement, or frustration. Examples include complaints, product issues, objections, and hostile language.

Neutral comments are informational or ambiguous. They neither praise nor criticize — often questions, simple reactions, or factual statements.


Reading the sentiment breakdown

Your analysis shows a sentiment distribution — a breakdown of what percentage of comments fall into each category. This helps you quickly assess:

  • Whether the audience is overall positive, negative, or mixed

  • How polarized the conversation is (high percentages on both ends suggest division)

  • Whether neutral comments dominate (often a sign of informational or low-engagement content)

A balanced sentiment distribution with a slight positive lean is typical for healthy, engaged audiences. Heavy negative skew may indicate controversy, backlash, or product issues worth investigating.


Sentiment vs. the Siftsy Score

Sentiment is one component of the Siftsy Score, but it's not the whole picture. The score also considers relevance (how on-topic comments are) and consensus (how aligned commenters are).

Two posts with identical sentiment distributions can have different Siftsy Scores if one has more engaged, on-topic discussion and the other has more noise or spam.


Filtering by sentiment

You can filter comments by sentiment to dive deeper into specific reactions:

  1. Open an analysis

  2. At the top, click the Explore card

  3. Type "/" to open shortcuts

  4. Select Sentiment and choose positive, negative, or neutral

  5. Click Search to generate a filtered analysis

Filtered analyses show insights specific to that sentiment group — useful for understanding what positive praise has in common, or what themes drive negative feedback.

You can combine sentiment filters with keywords, usernames, or topics for highly targeted insights.


What's next

Learn how to explore specific topics within your analysis in How to explore and search the comments, or understand the overall score in How to understand comment insights.

Was this helpful?