# Open Text Analysis

Open-ended responses often contain the most valuable insights but also the most complexity. Artemis uses AI-powered semantic analysis to interpret, summarize, and structure qualitative feedback at scale.

Instead of manually reading hundreds or thousands of comments, users can request structured insights directly.

Artemis can:

* Summarize recurring themes
* Detect positive, negative, and mixed sentiment
* Cluster comments by meaning
* Highlight emerging concerns
* Extract representative quotes
* Group open texts results along with other survey question answers

### 🔎 Theme Discovery & Summaries

* “Summarize the main themes from the Comment Question.”
* “What are customers talking about the most based on the Comment Question?”
* “Provide a high-level overview of recent comments based on the Comment Question.”
* “Identify the top 5 recurring feedback themes from the Comment Question.”
* "Provide the main themes of the Comment Question and group them by the Country Question"

Outputs may include structured summaries, categorized themes, and concise narrative overviews.

### 😊 Sentiment Analysis

* “Analyze sentiment in recent comments based on the Comment Question.”
* “Show positive vs negative feedback distribution based on the Comment Question.”
* “Highlight the most critical comments based on the Comment Question.”
* “Identify strongly positive testimonials based on Testimonial Question.”

Artemis provides sentiment breakdowns and contextual interpretation, not just raw tagging.

### 🧩 Comment Clustering

* “Cluster comments by topic.”
* “Group similar feedback together.”
* “Identify patterns in service-related complaints.”
* “Segment comments into key discussion categories.”

This helps transform unstructured feedback into actionable insight groups.