> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://api.docs.siftsy.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://api.docs.siftsy.com/_mcp/server.

# Get an analysis

GET https://api.siftsy.app/analyst/v1/analyses/{analysisId}

Requires `analyses:read`, or `analyses:run` for an `an_…` analysis
created by the same key (so a run-only key can poll the `Location`
it was given). For analyses created with `POST /analyses`
(`an_…` ids) this is the poll endpoint: `status` is `queued`,
`running`, `ready`, or `failed`; `scope`, `content`, and
`commentAnalysis` are populated once `ready`. Non-terminal responses
include `Retry-After` and `meta.pollAfterMs`.

For persisted campaign reports (`kind: report`) the payload includes
the stored `report`. Comment bodies are never included; sample them
at `GET /analyses/{analysisId}/comments` (`comments.path`).

Rate class `analysis_read` (60 / minute, 2,000 / day per key). Poll
at `meta.pollAfterMs`; polling faster only spends this budget.

Reference: https://api.docs.siftsy.com/api-reference/siftsy-analyst-api/get-analysis

## Authentication

- `Authorization` header (bearer token, required) — Bearer authentication of the form `Bearer <token>`, where token is your auth token.
- `X-Api-Key` header (required) — API Key authentication via header

## Servers

- `https://api.siftsy.app/analyst/v1` (Production, default)
- `http://localhost:3000/analyst/v1` (Local development)

## Request

### Path parameters

- `analysisId` (string, required)

## Response

### 200

Analysis detail, including `comments.path`

- `data` (Analysis, optional) — An analysis created with `POST /analyses`. `scope`, `content`, and `commentAnalysis` are `null` until `status` is `ready`. `content` is creator-side (what was posted); `commentAnalysis` is audience-side (how the matched comments landed). A sample of comments behind the analysis lives at `comments.url` (absolute) / `comments.path`; flat tables at `export.url` / `export.path`. A `kind: comparison` analysis has `sides` (the definition) and `comparison` (the result) instead of `scope` / `content` / `commentAnalysis`.
- `meta` (EnvelopeAnalysisMeta, optional)

## Errors

### 404 Not Found Error

Resource not found

- `any`

## Types

### Analysis

An analysis created with `POST /analyses`. `scope`, `content`, and `commentAnalysis` are `null` until `status` is `ready`. `content` is creator-side (what was posted); `commentAnalysis` is audience-side (how the matched comments landed). A sample of comments behind the analysis lives at `comments.url` (absolute) / `comments.path`; flat tables at `export.url` / `export.path`. A `kind: comparison` analysis has `sides` (the definition) and `comparison` (the result) instead of `scope` / `content` / `commentAnalysis`.

- `id` (string, optional)
- `url` (string, optional, nullable) — Absolute URL of this analysis on the host you called. Poll it as-is.
- `kind` (enum, optional)
  - Allowed values: `snapshot`, `search`, `comparison`
- `sides` (list of AnalysisSidesItems, optional) — Comparisons only. The resolved sides, in `compare` order.
- `comparison` (AnalysisComparison, optional, nullable) — Comparisons only, once `ready`.
- `answer` (AnalysisAnswer, optional, nullable) — Echo of `answer` (`{ question }`; `question` is `null` for an overview).
- `timeline` (AnalysisTimelineOptions, optional) — Options for `include: ["timeline"]`. Sending `timeline` without that include is a `400`.
- `export` (AnalysisExport, optional)
- `status` (enum, optional)
  - Allowed values: `queued`, `running`, `ready`, `failed`
- `createdAt` (string, optional)
- `updatedAt` (string, optional, nullable)
- `completedAt` (string, optional, nullable)
- `expiresAt` (string, optional, nullable)
- `selection` (AnalysisSelection, optional) — Which content the analysis covers. Provide exactly one of `postIds` or `posts`; `collectionId` may stand alone or be combined with `posts` filters to narrow within the collection. Resolves to at most 1,000 posts (newest first).
- `filters` (any, optional, nullable) — Echo of the normalized `filters`, or `null`.
- `search` (any, optional, nullable) — Echo of `search` (`query`, `mode`, optional `minRelevance`), or `null`.
- `include` (list of string, optional)
- `postCount` (integer, optional)
- `postIds` (list of string, optional) — Resolved post ids, newest first.
- `selectionTruncated` (boolean, optional) — True when the selection matched more than 1,000 posts.
- `progress` (AnalysisProgress, optional, nullable) — Present while `queued` / `running`.
- `pollAfterMs` (integer, optional, nullable)
- `error` (AnalysisError, optional, nullable) — Present when `status` is `failed`.
- `scope` (AnalysisScope, optional, nullable) — How much of the selection the analysis describes.
- `content` (AnalysisContent, optional, nullable) — Creator-side summary of the selected posts.
- `commentAnalysis` (AnalysisCommentAnalysis, optional) — Audience-side aggregate over the matched comments — the same vibe-check math as the dashboard. `notableComments` lists `{postId, commentId}` pairs. `briefSummary`, `topics`, and `outliers` are reserved (currently `null` / empty); a written finding is `answer`.
- `comments` (AnalysisComments, optional)
- `computedAt` (string, optional, nullable)

### EnvelopeAnalysisMeta

- `status` (enum, optional)
  - Allowed values: `queued`, `running`, `ready`, `failed`
- `pollAfterMs` (integer, optional) — Present while `status` is `queued` or `running`

### AnalysisSidesItems

- `side` (integer, optional) — 1-based; pass as `?side=` on the comments route
- `label` (string, optional)
- `selection` (AnalysisSelection, optional) — Which content the analysis covers. Provide exactly one of `postIds` or `posts`; `collectionId` may stand alone or be combined with `posts` filters to narrow within the collection. Resolves to at most 1,000 posts (newest first).
- `postCount` (integer, optional)
- `selectionTruncated` (boolean, optional)

### AnalysisComparison

Comparisons only, once `ready`.

- `sides` (list of map from string to any, optional) — One entry per side with `label`, `scope`, `content` (up to 25 post cards), and `commentAnalysis` — the same shapes as a single analysis.
- `deltas` (list of AnalysisComparisonDeltasItems, optional) — Each side after the first against side 1: score points (`scores`), 0–1 share differences (`shareOfComments`, `shareOfContent`), and mix-bar percentage points (`mix`).

### AnalysisAnswer

Present when `answer` was requested. `text` is markdown with citation markers (`[1]`, `[2, 5]`) numbered in reading order; each number is a `citations[].n`. Claims commenters make are attributed, never stated as fact. Links, images, and URLs are removed from `text`. When the writer fails, `text` is `null` and `error` explains; the analysis numbers are still ready. Citations carry comment text and usernames only for keys with `comments:read`. Other keys get `{ n, postId, commentId, postLink }` and `citationsRedacted: true`; they still read `text`, a summary that paraphrases the comments (at most a short quoted fragment).

- `question` (string, optional, nullable)
- `text` (string, optional, nullable)
- `citations` (list of AnalysisAnswerCitationsItems, optional)
- `citationsRedacted` (boolean, optional) — Present (true) when the key lacks `comments:read` and citations are cut to ids.
- `sampleSize` (integer, optional)
- `generatedAt` (string, optional)
- `error` (AnalysisAnswerError, optional)

### AnalysisTimelineOptions

Options for `include: ["timeline"]`. Sending `timeline` without that include is a `400`.

- `granularity` (enum, optional, default: day) — Weeks start Monday. Very long day series come back weekly.
  - Allowed values: `day`, `week`, `month`
- `basis` (enum, optional, default: comment) — `comment` places each comment on the day it was written; `post` on the day its post was published.
  - Allowed values: `comment`, `post`
- `timeZone` (string, optional, default: UTC) — IANA zone for the period boundaries, e.g. `America/New_York`.

### AnalysisExport

- `path` (string, optional) — Relative to the API base URL. Add `?table=` and `&format=csv`.
- `url` (string, optional, nullable)

### AnalysisSelection

Which content the analysis covers. Provide exactly one of `postIds` or `posts`; `collectionId` may stand alone or be combined with `posts` filters to narrow within the collection. Resolves to at most 1,000 posts (newest first).

- `collectionId` (string, optional) — Only posts in this collection (and its sub-collections).
- `postIds` (list of string, optional) — Explicit post ids. Cannot be combined with `collectionId` or `posts`.
- `posts` (map from string to any, optional) — The same filters accepted by `GET /posts`: `link`, `account`, `tag`, `platform`, `posted_since`, `posted_until`, `updated_since`, `min_score` / `max_score`, the bucket percentage ranges (`min_positive_percent`, …), and `status` (`complete` by default).

### AnalysisProgress

Present while `queued` / `running`.

- `phase` (string, optional)
- `percent` (double, optional)

### AnalysisError

Present when `status` is `failed`.

- `message` (string, optional)

### AnalysisScope

How much of the selection the analysis describes.

- `postCount` (integer, optional)
- `postIds` (list of string, optional)
- `totalComments` (integer, optional) — Visible comments across the selection before `filters` / `search`.
- `matchedComments` (integer, optional) — Comments that matched `filters` / `search` — the ones the numbers below describe.
- `matchedPosts` (integer, optional)
- `shareOfComments` (double, optional, nullable) — matchedComments / totalComments (0–1).
- `shareOfContent` (double, optional, nullable) — matchedPosts / postCount (0–1).

### AnalysisContent

Creator-side summary of the selected posts.

- `postCount` (integer, optional)
- `posts` (list of map from string to any, optional) — Up to 100 post cards (newest first) with `matchedComments`.
- `postsTruncated` (boolean, optional)
- `topics` (list of AnalysisContentTopicsItems, optional) — Creator topics across the selection, deduped, with `postCount`.
- `messages` (list of AnalysisContentMessagesItems, optional)
- `scores` (AnalysisContentScores, optional)
- `mix` (AnalysisContentMix, optional)

### AnalysisCommentAnalysis

Audience-side aggregate over the matched comments — the same vibe-check math as the dashboard. `notableComments` lists `{postId, commentId}` pairs. `briefSummary`, `topics`, and `outliers` are reserved (currently `null` / empty); a written finding is `answer`.

- `briefSummary` (string, optional, nullable) — Audience brief when materialized on the post
- `scores` (PostScores, optional) — Scores resolved for the team's selected score version (1-10 scale). `content` / `topic` are populated for score version 2+ teams.
- `mix` (AnalysisCommentAnalysisMix, optional)
- `topics` (list of CommentTheme, optional) — Emergent comment themes when stored on the post
- `notableCommentIds` (list of string, optional)
- `outliers` (list of AnalysisCommentAnalysisOutliersItems, optional)
- `wordCloud` (any, optional, nullable)
- `emojiCloud` (any, optional, nullable)
- `totalComments` (double, optional, nullable)
- `completeness` (enum, optional)
  - Allowed values: `full`, `scores_and_content`, `scores_only`, `content_only`, `unavailable`
- `notableComments` (list of AnalysisCommentAnalysisNotableCommentsItems, optional)
- `timeline` (AnalysisTimeline, optional) — Present with `include: ["timeline"]`. Scores over Time with the dashboard chart's bucketing, over the matched comments. Each point's `scores` are the mean 1–10 score of that period's comments and `mix` its five-bucket shares. `lowConfidence` marks periods with fewer than `minComments` comments. `coverage.status` is `insufficient` when too few comments carry a usable timestamp.
- `languages` (AnalysisLanguages, optional) — Present with `include: ["languages"]`. A comment in two languages counts in both, so shares can add up to more than 1. Up to 25 languages, most common first.
- `answer` (AnalysisAnswer, optional) — Present when `answer` was requested. `text` is markdown with citation markers (`[1]`, `[2, 5]`) numbered in reading order; each number is a `citations[].n`. Claims commenters make are attributed, never stated as fact. Links, images, and URLs are removed from `text`. When the writer fails, `text` is `null` and `error` explains; the analysis numbers are still ready. Citations carry comment text and usernames only for keys with `comments:read`. Other keys get `{ n, postId, commentId, postLink }` and `citationsRedacted: true`; they still read `text`, a summary that paraphrases the comments (at most a short quoted fragment).

### AnalysisComments

- `path` (string, optional) — Relative to the API base URL (`…/analyst/v1`).
- `url` (string, optional, nullable) — Absolute URL for `path` on the host you called. Follow it as-is.

### AnalysisComparisonDeltasItems

- `label` (string, optional)
- `vs` (string, optional)
- `scores` (map from string to double, optional)
- `shareOfComments` (double, optional, nullable)
- `shareOfContent` (double, optional, nullable)
- `mix` (map from string to any, optional)

### AnalysisAnswerCitationsItems

- `n` (integer, optional)
- `postId` (string, optional, nullable)
- `commentId` (string, optional, nullable)
- `username` (string, optional, nullable)
- `likes` (double, optional, nullable)
- `text` (string, optional, nullable)
- `platform` (string, optional, nullable)
- `postLink` (string, optional, nullable)
- `postAccount` (string, optional, nullable)

### AnalysisAnswerError

- `message` (string, optional)

### AnalysisContentTopicsItems

- `title` (string, optional)
- `description` (string, optional, nullable)
- `postCount` (integer, optional)

### AnalysisContentMessagesItems

- `topic` (string, optional)
- `stance` (string, optional, nullable)
- `postCount` (integer, optional)

### AnalysisContentScores

- `content` (double, optional, nullable)
- `topic` (double, optional, nullable)

### AnalysisContentMix

- `content` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.
- `topic` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.

### PostScores

Scores resolved for the team's selected score version (1-10 scale). `content` / `topic` are populated for score version 2+ teams.

- `scoreVersion` (double, optional)
- `siftsyScore` (double, optional, nullable)
- `sentiment` (double, optional, nullable)
- `relevance` (double, optional, nullable)
- `consensus` (double, optional, nullable)
- `content` (double, optional, nullable)
- `topic` (double, optional, nullable)

### AnalysisCommentAnalysisMix

- `sentiment` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.
- `content` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.
- `topic` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.
- `relevance` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.
- `consensus` (ScoreBuckets, optional) — Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.

### CommentTheme

- `label` (string, optional)
- `shareOfComments` (double, optional, nullable)
- `shareOfContent` (double, optional, nullable)
- `commentCount` (double, optional, nullable)
- `postCount` (double, optional, nullable)
- `scores` (PostScores, optional) — Scores resolved for the team's selected score version (1-10 scale). `content` / `topic` are populated for score version 2+ teams.
- `brief` (CommentThemeBrief, optional)
- `sampleCommentIds` (list of string, optional)

### AnalysisCommentAnalysisOutliersItems

### AnalysisCommentAnalysisNotableCommentsItems

- `postId` (string, optional)
- `commentId` (string, optional)

### AnalysisTimeline

Present with `include: ["timeline"]`. Scores over Time with the dashboard chart's bucketing, over the matched comments. Each point's `scores` are the mean 1–10 score of that period's comments and `mix` its five-bucket shares. `lowConfidence` marks periods with fewer than `minComments` comments. `coverage.status` is `insufficient` when too few comments carry a usable timestamp.

- `basis` (enum, optional)
  - Allowed values: `comment`, `post`
- `granularity` (enum, optional)
  - Allowed values: `day`, `week`, `month`
- `monthsFromWeeks` (boolean, optional) — Present (true) on very long series, where months are built from weeks and each week counts in the month of its Monday.
- `timeZone` (string, optional)
- `coverage` (AnalysisTimelineCoverage, optional)
- `minComments` (integer, optional)
- `points` (list of AnalysisTimelinePointsItems, optional)

### AnalysisLanguages

Present with `include: ["languages"]`. A comment in two languages counts in both, so shares can add up to more than 1. Up to 25 languages, most common first.

- `totalComments` (integer, optional)
- `detectedComments` (integer, optional)
- `undetectedComments` (integer, optional)
- `languages` (list of AnalysisLanguagesLanguagesItems, optional)
- `languagesTruncated` (boolean, optional)

### ScoreBuckets

Five-bucket percentage breakdown. Dashboard labels per dimension — Sentiment: Positive / Lean positive / Neutral / Lean negative / Negative. Content: Supportive (positive) / Receptive (leanPositive) / Split (neutral) / Skeptical (leanNegative) / Opposed (negative). Topic: Enthusiastic (positive) / Favorable (leanPositive) / Mixed (neutral) / Critical (leanNegative) / Hostile (negative). Relevance: On-topic (positive) / Relevant (leanPositive) / General (leanNegative) / Off-topic (negative). Consensus: Agreeing (positive) / Discussing (leanPositive) / Debating (leanNegative) / Fighting (negative). neutralPercent is typically unused for relevance and consensus.

- `positivePercent` (double, optional, nullable)
- `leanPositivePercent` (double, optional, nullable)
- `neutralPercent` (double, optional, nullable)
- `leanNegativePercent` (double, optional, nullable)
- `negativePercent` (double, optional, nullable)

### CommentThemeBrief

- `heading` (string, optional, nullable)
- `description` (string, optional, nullable)

### AnalysisTimelineCoverage

- `total` (integer, optional)
- `timed` (integer, optional)
- `approximate` (integer, optional)
- `untimed` (integer, optional)
- `status` (enum, optional)
  - Allowed values: `complete`, `partial`, `insufficient`, `none`

### AnalysisTimelinePointsItems

- `period` (string, optional) — Period start, `YYYY-MM-DD`
- `comments` (integer, optional)
- `lowConfidence` (boolean, optional)
- `scores` (AnalysisTimelinePointsItemsScores, optional)
- `mix` (map from string to ScoreBuckets, optional)

### AnalysisLanguagesLanguagesItems

- `language` (string, optional)
- `comments` (integer, optional)
- `shareOfComments` (double, optional, nullable)

### AnalysisTimelinePointsItemsScores

- `sentiment` (double, optional, nullable)
- `content` (double, optional, nullable)
- `topic` (double, optional, nullable)
- `relevance` (double, optional, nullable)
- `consensus` (double, optional, nullable)

## Examples

**Response**

```json
{
  "data": {
    "id": "an_5f2c9a1e0b6d4d0f9c1a2b3c4d5e6f70",
    "kind": "snapshot",
    "status": "ready",
    "createdAt": "2026-09-10T15:04:05.000Z",
    "updatedAt": "2026-09-10T15:04:05.400Z",
    "completedAt": "2026-09-10T15:04:05.400Z",
    "expiresAt": "2026-09-17T15:04:05.000Z",
    "selection": {
      "collectionId": "col_launch",
      "type": "collection",
      "status": "complete"
    },
    "filters": null,
    "search": null,
    "include": [
      "wordCloud"
    ],
    "postCount": 12,
    "postIds": [
      "p_301",
      "p_298",
      "p_290"
    ],
    "selectionTruncated": false,
    "scope": {
      "postCount": 12,
      "postIds": [
        "p_301",
        "p_298",
        "p_290"
      ],
      "totalComments": 4820,
      "matchedComments": 611,
      "matchedPosts": 11,
      "shareOfComments": 0.1268,
      "shareOfContent": 0.9167
    },
    "content": {
      "postCount": 12,
      "posts": [
        {
          "id": "p_301",
          "platform": "tiktok",
          "link": "https://www.tiktok.com/@acme/video/7311",
          "creator": {
            "username": "acme"
          },
          "postedAt": "2026-09-02T17:00:00.000Z",
          "matchedComments": 97
        }
      ],
      "postsTruncated": false,
      "topics": [
        {
          "title": "Product launch",
          "description": null,
          "postCount": 12
        }
      ],
      "messages": [
        {
          "topic": "Product launch",
          "stance": "The new line ships faster",
          "postCount": 8
        }
      ],
      "scores": {
        "content": 7.1,
        "topic": 6.4
      },
      "mix": {
        "content": {
          "positivePercent": 41,
          "leanPositivePercent": 22,
          "neutralPercent": 18,
          "leanNegativePercent": 11,
          "negativePercent": 8
        },
        "topic": {
          "positivePercent": 35,
          "leanPositivePercent": 27,
          "neutralPercent": 20,
          "leanNegativePercent": 10,
          "negativePercent": 8
        }
      }
    },
    "commentAnalysis": {
      "briefSummary": null,
      "scores": {
        "scoreVersion": 3,
        "siftsyScore": 3.4,
        "sentiment": 2.3,
        "relevance": 7.8,
        "consensus": 6.9,
        "content": 2.1,
        "topic": 2.6
      },
      "mix": {
        "sentiment": {
          "positivePercent": 0,
          "leanPositivePercent": 0,
          "neutralPercent": 0,
          "leanNegativePercent": 38,
          "negativePercent": 62
        },
        "content": {
          "positivePercent": 0,
          "leanPositivePercent": 2,
          "neutralPercent": 5,
          "leanNegativePercent": 40,
          "negativePercent": 53
        },
        "topic": {
          "positivePercent": 1,
          "leanPositivePercent": 3,
          "neutralPercent": 6,
          "leanNegativePercent": 41,
          "negativePercent": 49
        },
        "relevance": {
          "positivePercent": 58,
          "leanPositivePercent": 24,
          "neutralPercent": 9,
          "leanNegativePercent": 6,
          "negativePercent": 3
        },
        "consensus": {
          "positivePercent": 44,
          "leanPositivePercent": 31,
          "neutralPercent": 12,
          "leanNegativePercent": 9,
          "negativePercent": 4
        }
      },
      "topics": [],
      "outliers": [],
      "wordCloud": [
        {
          "text": "shipping",
          "value": 84,
          "type": "word",
          "avgSentiment": 2.1,
          "sentimentCategory": "negative",
          "mentionPercentage": 13.7
        },
        {
          "text": "never arrived",
          "value": 51,
          "type": "phrase",
          "avgSentiment": 1.8,
          "sentimentCategory": "negative",
          "mentionPercentage": 5.6
        }
      ],
      "emojiCloud": null,
      "totalComments": 611,
      "completeness": "scores_and_content",
      "notableComments": [
        {
          "postId": "p_301",
          "commentId": "c_77f1"
        },
        {
          "postId": "p_298",
          "commentId": "c_1a09"
        }
      ]
    },
    "comments": {
      "path": "/analyses/an_5f2c9a1e0b6d4d0f9c1a2b3c4d5e6f70/comments"
    },
    "computedAt": "2026-09-10T15:04:05.400Z"
  },
  "meta": {
    "status": "queued",
    "pollAfterMs": 1
  }
}
```

**SDK Code**

```python
import requests

url = "https://api.siftsy.app/analyst/v1/analyses/analysisId"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.siftsy.app/analyst/v1/analyses/analysisId';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.siftsy.app/analyst/v1/analyses/analysisId"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.siftsy.app/analyst/v1/analyses/analysisId")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.siftsy.app/analyst/v1/analyses/analysisId")
  .header("Authorization", "Bearer <token>")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.siftsy.app/analyst/v1/analyses/analysisId', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.siftsy.app/analyst/v1/analyses/analysisId");
var request = new RestRequest(Method.GET);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Authorization": "Bearer <token>"]

let request = NSMutableURLRequest(url: NSURL(string: "https://api.siftsy.app/analyst/v1/analyses/analysisId")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"
request.allHTTPHeaderFields = headers

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```