Comment Intelligence

Turn comment sections into audience evidence, not a pile of anecdotes.

Inputs

Accept comments supplied by the user or collected from public sources the runtime can legitimately access. Useful fields include:

comment text
source URL / post ID
platform
date
likes or replies when available
creator / brand / topic

Do not claim access to private, deleted, login-gated, or unavailable comments.

Workflow

Define the research question before clustering comments.
Remove obvious spam, duplicates, bot-like repetition, and context-free noise when justified.
Preserve source references so findings remain auditable.
Cluster comments by meaning rather than keyword alone.
Separate observed language from analyst interpretation.
Rank themes using frequency plus strength of intent, not frequency alone.
Extract representative short phrases only when allowed; otherwise paraphrase.
Convert strong themes into hypotheses and content tests.

Signal Types

Look for:

repeated questions
objections and friction
pain points
desired outcomes
misconceptions
comparisons and alternatives
purchase / signup / download intent
requests for tutorials or examples
emotional language
recurring audience vocabulary
missing information
positive proof and reasons people care

Evidence Rules

Never infer precise demographics, sentiment percentages, market size, or purchase probability unless the data supports them.

A loud minority is not automatically representative. Distinguish:

Repeated signal — appears across multiple independent comments
Strong single signal — specific and useful but not repeated
Hypothesis — plausible interpretation requiring testing

When engagement counts are available, treat them as context rather than proof that a comment represents the whole audience.

Output