> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mentionlab.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Metrics Glossary

> What every MentionLab metric actually measures, and how it is computed

## Overview

Most of these metrics are rates, and a rate is only as clear as its denominator. This page states the
denominator for every one of them, because several metrics that sound similar do not divide by the
same thing.

<Info>
  Metrics are grouped into: **Coverage**, **Mention**, **Source**, **Sentiment**, **Shopping**,
  **Fan-out** and **Social**.
</Info>

<Warning>
  Every metric respects the [filter bar](/guides/filters-and-comparisons). Filters that narrow the
  population of responses — **Sources**, **Shopping**, models, countries — also narrow the
  denominator. Filtering to "Sources" makes Source rate 100% by definition.
</Warning>

***

## Coverage metrics

<AccordionGroup>
  <Accordion title="Total responses" icon="database">
    **Type:** Number

    Every AI response collected in the selected period, after filters. This is the denominator for
    Mention rate, Citation rate, Source rate and Shopping Coverage.
  </Accordion>

  <Accordion title="Total queries" icon="message-question">
    **Type:** Number

    The number of **distinct queries that produced at least one response** in the period — not the
    number of queries configured in the project, and not queries × runs.

    <Note>
      A query that ran in three languages counts as three queries here, because each is a separate query
      row.
    </Note>
  </Accordion>

  <Accordion title="Source rate" icon="quote-left">
    **Type:** Percentage

    $\text{Source rate} = \frac{\text{Responses with at least one citation}}{\text{Total responses}} \times 100$

    How often the AI platforms bothered to cite anything at all.
  </Accordion>

  <Accordion title="Shopping rate / Shopping Coverage" icon="cart-shopping">
    **Type:** Percentage

    $\text{Shopping Coverage} = \frac{\text{Responses containing shopping results}}{\text{Total responses}} \times 100$

    The Overview card calls it **Shopping rate**; the Shopping page calls it **Shopping Coverage**. Same
    number.
  </Accordion>
</AccordionGroup>

***

## Mention metrics

<AccordionGroup>
  <Accordion title="Mention rate" icon="eye">
    **Type:** Percentage

    $\text{Mention rate} = \frac{\text{Responses mentioning the entity}}{\text{Total responses}} \times 100$

    An entity mentioned five times in one response counts **once**. The denominator is every response in
    scope, not only those that mention some brand.

    <Note>
      Scoped variants use a scoped denominator: on the Tags page the denominator is the responses carrying
      that tag; on the Platforms page it is that model's responses; on a query it is that query's
      responses.
    </Note>

    <Info>
      The REST API calls this field `visibilityPct`, and some cards are still titled "Visibility score".
      It is the same metric.
    </Info>
  </Accordion>

  <Accordion title="Avg. position" icon="ranking-star">
    **Type:** Number (rank — lower is better)

    The mean of the position at which the entity appears, averaged over mentions.

    | Position | Interpretation      |
    | -------- | ------------------- |
    | 1–2      | Top recommendation  |
    | 3–5      | Strong presence     |
    | 6–10     | Moderate visibility |
    | 10+      | Low prominence      |

    <Warning>
      When a model does not report a position, MentionLab stores `0` and that zero is included in the
      average — so an entity whose positions are frequently unreported will show an artificially low
      (apparently better) average. An entity with no mentions at all also renders as `0`, displayed as `-`.
      Read this metric alongside the mention count, never on its own.
    </Warning>
  </Accordion>

  <Accordion title="Number of mentions" icon="at">
    **Type:** Number

    The total number of times the entity's name (or an alias) appears. Unlike Mention rate, repeats
    within one response all count.

    <Warning>
      "Mentions" means two different things depending on the page. On the Overview and Competitors entity
      tables it is the raw occurrence count. On the **Sentiments** page, "Total Mentions Analyzed" and the
      "Mentions" column count **one per response per entity** — a presence count, not an occurrence count.
    </Warning>
  </Accordion>

  <Accordion title="Avg. mentions per result" icon="repeat">
    **Type:** Number

    $\text{Avg. mentions per result} = \frac{\text{Number of mentions}}{\text{Responses mentioning the entity}}$

    How prominently a brand is featured *when it is featured*. The denominator is responses where the
    entity was present, not all responses. Shown as `-` when the entity was never mentioned.
  </Accordion>

  <Accordion title="Share of Voice" icon="chart-pie">
    **Type:** Percentage

    Your brand's slice of all brand mentions. **Three surfaces compute it differently — the numbers will
    not match, and all three are correct for their context:**

    | Where                               | Numerator                       | Denominator                                     |
    | ----------------------------------- | ------------------------------- | ----------------------------------------------- |
    | Overview donut, Competitors, Tags   | Responses mentioning the entity | Sum of that count across all entities           |
    | Platforms rank table & detail cards | Raw mention count on that model | Raw mention count of all entities on that model |
    | Query detail                        | Raw mention count on that query | Raw mention count of all entities on that query |

    <Note>
      Because one response can mention several brands, the denominator is a sum of per-brand counts, not a
      count of responses. It still sums to 100% across brands.
    </Note>
  </Accordion>

  <Accordion title="Presence (response tags)" icon="tags">
    **Type:** Percentage

    $\text{Presence} = \frac{\text{Responses carrying the tag}}{\text{Total responses}} \times 100$

    Used by the Overview **Response Tag Visibility** card.

    <Note>
      The card is described as "percentage of queries covered by each response tag", but the denominator is
      **responses**.
    </Note>
  </Accordion>
</AccordionGroup>

***

## Source metrics

Sources have three different units on one row — responses, pages and citation rows. Which one a
metric uses decides what it means.

<AccordionGroup>
  <Accordion title="Citations" icon="quote-left">
    **Type:** Number

    The number of **distinct AI responses that cited this domain**. A response citing four pages from the
    same domain counts once.
  </Accordion>

  <Accordion title="Citation rate" icon="chart-line">
    **Type:** Percentage

    $\text{Citation rate} = \frac{\text{Responses citing this domain}}{\text{Total responses}} \times 100$

    A per-domain reach metric: how much of your query volume this one site touches. Rates across domains
    do **not** sum to 100%.

    <Warning>
      The **Platforms** page has a differently-defined metric with the same label. There, "Citation Rate"
      is the percentage of a model's responses that cite *anything* — a property of the model, not of a
      domain.
    </Warning>
  </Accordion>

  <Accordion title="Pages" icon="file-lines">
    **Type:** Number

    Distinct cited URLs from the domain. Shown in the domain detail sheet as **Total page citations**
    (a count of URLs, despite the word "citations").
  </Accordion>

  <Accordion title="Brand pages" icon="file-circle-check">
    **Type:** Number

    Distinct cited URLs from the domain on which your brand was found. Shown as **Entity page
    citations**. Always a subset of Pages.
  </Accordion>

  <Accordion title="Presence" icon="chart-area">
    **Type:** Percentage

    $\text{Presence} = \frac{\text{Brand pages}}{\text{Pages}} \times 100$

    Of this domain's cited pages, how many mention you.

    <Note>
      In the Sources grid this cell displays a ratio like `12/40` rather than a percentage. The colour band
      and the sort order both come from the percentage.
    </Note>
  </Accordion>

  <Accordion title="True reach" icon="bullseye">
    **Type:** Percentage

    $\text{True reach} = \frac{\text{Brand citation rows}}{\text{Total citation rows}} \times 100$

    Of every time this domain was cited, how often the cited content mentioned you.

    <Warning>
      True reach counts **citation rows**, while Presence counts **distinct pages**. A domain can show high
      Presence and low True reach at once — its brand-mentioning pages exist but rarely get cited.
    </Warning>

    <Info>
      Only meaningful at domain level, not for individual URLs.
    </Info>
  </Accordion>

  <Accordion title="Citation share" icon="chart-simple">
    **Type:** Percentage

    $\text{Citation share} = \frac{\text{Responses citing this domain}}{\text{Sum of that count across all domains}} \times 100$

    Sums to 100% across domains.

    <Note>
      The denominator is always the **whole project**. Filtering the grid by category or search does not
      rescale the remaining rows.
    </Note>
  </Accordion>

  <Accordion title="Entity citation share" icon="percent">
    **Type:** Percentage

    $\text{Entity citation share} = \frac{\text{Brand pages on this domain}}{\text{Brand pages across all domains}} \times 100$

    Your brand-mentioning cited pages, by domain. Note this is built on **pages**, not citations, despite
    the name.
  </Accordion>
</AccordionGroup>

***

## Sentiment metrics

<AccordionGroup>
  <Accordion title="Sentiment score" icon="face-smile">
    **Type:** Number (1–100)

    The mean of the per-mention sentiment scores the analysis model assigns, where 1 is most negative,
    50 neutral and 100 most positive.

    | Score  | Displayed label |
    | ------ | --------------- |
    | 60–100 | Positive        |
    | 40–59  | Neutral         |
    | 1–39   | Negative        |

    <Warning>
      The Sentiments page renders this score with a `%` sign. It is an index, not a share — a score of 62
      does not mean 62% of mentions were positive.
    </Warning>

    <Note>
      The thresholds that classify an *individual* mention as positive / neutral / negative are different
      (≤33 negative, ≤66 neutral, above that positive). So a brand with a 55 average score can still show a
      majority of individually-positive mentions.
    </Note>
  </Accordion>

  <Accordion title="Sentiment breakdown" icon="chart-pie">
    **Type:** Percentages

    The split of mentions across positive, neutral and negative:

    $\text{Category \%} = \frac{\text{Mentions in category}}{\text{Positive} + \text{Neutral} + \text{Negative}} \times 100$

    <Note>
      Mentions classified as *mixed*, and mentions with no score, are counted in **Total Mentions
      Analyzed** but in none of the three slices — so the three counts will not add up to that card.
    </Note>
  </Accordion>

  <Accordion title="Sentiment by entity" icon="users">
    **Type:** Comparison

    Per-entity sentiment score and breakdown, so you can compare how AI platforms describe you versus
    competitors. This table always lists every entity, even when a **View as** pin is active.
  </Accordion>
</AccordionGroup>

***

## Shopping metrics

<AccordionGroup>
  <Accordion title="Identified Brands / Products / Retailers" icon="tags">
    **Type:** Number

    Distinct brands, products and retailers detected in shopping results. Brands and products are counted
    **after merging**, so duplicates you merged collapse to one. Retailers are not merged.

    Shopping appearances that could not be resolved to a brand or product are excluded from these counts
    and from the All Products table — map them from **Project settings → Shopping Settings → Shopping
    Products**.
  </Accordion>

  <Accordion title="Visibility (shopping)" icon="eye">
    **Type:** Percentage

    $\text{Visibility} = \frac{\text{Shopping responses including this brand or product}}{\text{Responses containing any shopping result}} \times 100$

    The denominator is shopping responses only — not all responses.
  </Accordion>

  <Accordion title="SoV (shopping)" icon="chart-pie">
    **Type:** Percentage

    A brand's share of all shopping mentions.

    <Note>
      Unresolved ("Not matched") mentions are deliberately kept in the denominator, so the visible brand
      shares add up to less than 100%. The shortfall is the size of your mapping backlog.
    </Note>
  </Accordion>

  <Accordion title="Retailer Distribution" icon="store">
    **Type:** Percentages

    Each retailer's share of distinct product listings across all retailers. Merchants below 1% are
    grouped into **Other**.
  </Accordion>

  <Accordion title="Merchant citation metrics" icon="tag">
    **Type:** Percentages

    On the **All Merchants** table:

    | Metric                | Definition                                                                             |
    | --------------------- | -------------------------------------------------------------------------------------- |
    | **Citation Rate**     | Shopping responses featuring this merchant ÷ all responses containing shopping results |
    | **Citation Share**    | This merchant's product listings ÷ all merchants' product listings                     |
    | **Entity Cit. Share** | This merchant's brand-matched rows ÷ all merchants' brand-matched rows                 |
    | **True Reach**        | This merchant's product rows mentioning your brand ÷ all its product rows              |
  </Accordion>
</AccordionGroup>

***

## Fan-out metrics

<Warning>
  Every fan-out rate and average divides by **responses that produced at least one fan-out**, never by
  all responses. Responses where the model suggested nothing are outside the denominator entirely.
</Warning>

<AccordionGroup>
  <Accordion title="Total fan-outs" icon="arrows-split-up-and-left">
    **Type:** Number

    Every fan-out entry in scope. One response can produce several, so this exceeds the response count.
    Repeats of the same text within one response are collapsed at ingest.
  </Accordion>

  <Accordion title="Unique fan-outs" icon="fingerprint">
    **Type:** Number

    Distinct fan-out texts. Deduplication is an **exact text match** — `Best CRM 2026` and
    `best CRM 2026` count separately.
  </Accordion>

  <Accordion title="Avg per response" icon="calculator">
    **Type:** Number

    $\text{Avg per response} = \frac{\text{Total fan-outs}}{\text{Responses that produced at least one fan-out}}$

    Because of that denominator this value can never fall below 1.0, and adding models that emit no
    fan-outs will not lower it. The REST API calls this field `avgPerExecution`.
  </Accordion>

  <Accordion title="Fan-out occurrence rate" icon="percent">
    **Type:** Percentage

    $\text{Occurrence rate} = \frac{\text{Responses suggesting this fan-out}}{\text{Responses that produced at least one fan-out}} \times 100$

    How reliably a given follow-up gets suggested. A fan-out near 100% is a question the model treats as
    unavoidable in your category.
  </Accordion>
</AccordionGroup>

***

## Social metrics (YouTube)

<AccordionGroup>
  <Accordion title="Videos cited / Citations / Citations per video" icon="video">
    **Type:** Numbers

    **Videos cited** is the number of distinct videos cited. **Citations** is the number of distinct AI
    responses that cited any YouTube video. **Citations / video** divides one by the other.
  </Accordion>

  <Accordion title="Citation Share (YouTube)" icon="percent">
    **Type:** Percentage

    A video's, channel's or country's share of YouTube-video citations in scope.

    <Warning>
      This column **can sum to more than 100%** down a table. One response often cites several videos, from
      several channels, in several countries, and counts once toward each. Individual rows are still ≤100%.
    </Warning>

    <Note>
      The **YouTube Channel Share** donut deliberately uses a different denominator so its slices total
      100%. A channel's donut percentage will not match its Citation Share in the table.
    </Note>
  </Accordion>

  <Accordion title="Citation Rate (YouTube)" icon="chart-line">
    **Type:** Percentage

    How often this video, channel or country appears across **all** AI responses in scope — the same
    denominator as the rest of the product.
  </Accordion>

  <Accordion title="Channel countries" icon="earth-americas">
    **Type:** Number

    Distinct home countries of the cited channels.

    <Note>
      This count **excludes** channels with no country set, while the **By Country** table includes them as
      an "Unknown" row.
    </Note>
  </Accordion>
</AccordionGroup>