# YouTube Comment Insights (`seemuapps/youtube-comment-insights`) Actor Analyze YouTube video comments into per-video audience insights. Sentiment breakdown, top keywords, requested topics, questions, and complaints. - **URL**: https://apify.com/seemuapps/youtube-comment-insights.md - **Developed by:** [Andrew](https://apify.com/seemuapps) (community) - **Categories:** Videos, Social media, AI - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $80.00 / 1,000 video comments analyzeds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## YouTube Comment Insights Turn any YouTube video's comments into a single, ready-to-read audience report — sentiment breakdown, most-requested topics, top questions, recurring complaints, and the comments that resonated most. You get the insight layer, not a raw comment dump. ### What you get For every video you submit, one summary record containing: - **Sentiment breakdown** — positive, negative, and neutral percentages plus a single sentiment score, computed with a transparent positive/negative word lexicon - **Top keywords** — the 15 most frequently discussed content words across the comments, each with a count - **Most-requested topics** — comments where viewers ask the creator to do, make, or cover something, with examples and a total request count - **Top questions** — the highest-liked questions your audience is asking - **Recurring complaints** — comments flagged for common gripes (clickbait, too long, boring, audio issues, and more) with examples and a count - **Most-liked comments** — the top 10 comments by like count, with author and likes - **Video context** — title, channel, view count, reported comment count, and how many comments were analyzed - Export to JSON, CSV, or Google Sheets directly from the Apify console ### Use cases - **Content planning** — see exactly which topics your audience is asking for next - **Audience research** — measure how viewers feel about a video at a glance - **Competitor analysis** — analyze a rival channel's videos to find unmet audience demand - **Community management** — surface the most-liked questions and complaints worth a reply - **Creator vetting** — gauge real audience reception before a sponsorship or collaboration ### How it works Comments are scored with deterministic keyword and sentiment heuristics — a hand-built lexicon of positive and negative words plus pattern matching for requests, questions, and complaints. Results are fully reproducible: the same comments always produce the same report. ### How to use 1. Paste one or more YouTube video URLs or 11-character video IDs into **Video URLs or IDs** (watch links, `youtu.be` links, and Shorts links all work) 2. Set **Max Comments Per Video** (default 200; up to 1000) — more comments means richer insights 3. Choose **Comment Order** — **Relevance** for top/most-engaged comments, or **Newest** for the latest 4. Run the actor — one insight record per video appears in the **Dataset** tab If a video has comments turned off, its row is returned with a `comments_disabled` status so the rest of your batch still completes. ### Output format One dataset record per video: ```json { "videoId": "0e3GPea1Tyg", "videoUrl": "https://www.youtube.com/watch?v=0e3GPea1Tyg", "videoTitle": "Example video title", "channelTitle": "Example Channel", "viewCount": 12000000, "commentCountReported": 48000, "commentsAnalyzed": 200, "totalCommentLikes": 35210, "sentimentPositivePct": 61.5, "sentimentNegativePct": 12.0, "sentimentNeutralPct": 26.5, "sentimentScore": 0.5, "topKeywords": [{ "keyword": "editing", "count": 18 }], "topRequests": { "count": 14, "examples": [{ "text": "Please do a video on...", "author": "viewer", "likeCount": 320 }] }, "topQuestions": [{ "text": "How did you make this?", "author": "viewer", "likeCount": 88 }], "complaints": { "count": 6, "examples": [{ "text": "This was too long", "author": "viewer", "likeCount": 12 }] }, "mostLikedComments": [{ "text": "Best video yet!", "author": "viewer", "likeCount": 1500 }], "status": "success", "error": null } ```` ### Related YouTube actors Part of a complete YouTube toolkit — explore the rest of the suite: - [YouTube Channel Videos Scraper](https://apify.com/seemuapps/youtube-channel-videos-scraper) — List every video on a channel with metadata - [YouTube Video Metadata Scraper](https://apify.com/seemuapps/youtube-video-metadata-scraper) — Bulk video metadata — views, tags, chapters, more - [YouTube Transcript Scraper](https://apify.com/seemuapps/youtube-transcript-scraper) — Full transcripts and timestamped captions - [YouTube Channel Growth Analyzer](https://apify.com/seemuapps/youtube-channel-growth-analyzer) — Growth metrics, cadence, and best posting time - [YouTube Similar Channels Finder](https://apify.com/seemuapps/youtube-similar-channels-finder) — Find similar and competitor channels - [YouTube Sponsorship & Brand Deal Tracker](https://apify.com/seemuapps/youtube-sponsorship-tracker) — Extract sponsors, brand deals, and promo codes - [YouTube Creator Contact Finder](https://apify.com/seemuapps/youtube-creator-contact-finder) — Find a creator's email and social links - [YouTube Email Scraper](https://apify.com/seemuapps/youtube-email-scraper) — Bulk-extract contact emails from channels - [YouTube Thumbnail Downloader](https://apify.com/seemuapps/youtube-thumbnail-downloader) — Download video thumbnails in every size - [YouTube Video Downloader](https://apify.com/seemuapps/youtube-video-downloader) — Download videos as MP4 up to 1440p - [YouTube to MP3 Converter](https://apify.com/seemuapps/youtube-to-mp3) — Convert videos to MP3 audio (128–320 kbps) - [YouTube MCP Server](https://apify.com/seemuapps/youtube-mcp) — All YouTube tools for AI agents via MCP # Actor input Schema ## `videoUrls` (type: `array`): List of YouTube video watch URLs or bare 11-character video IDs. Supports youtu.be/ID, watch?v=ID, and shorts/ID formats. ## `maxCommentsPerVideo` (type: `integer`): How many top-level comments to analyze per video (20–1000). Higher values give richer insights but use more quota and time. ## `commentOrder` (type: `string`): Order in which comments are fetched: Relevance (top/most engaged comments) or Newest (most recent first). ## Actor input object example ```json { "videoUrls": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "maxCommentsPerVideo": 200, "commentOrder": "relevance" } ``` # Actor output Schema ## `results` (type: `string`): One record per video: videoId, videoUrl, videoTitle, channelTitle, viewCount, commentCountReported, commentsAnalyzed, sentimentPositivePct, sentimentNegativePct, sentimentNeutralPct, sentimentScore, topKeywords\[], topRequests\[], topQuestions\[], complaints\[], mostLikedComments\[], status (success|error|comments\_disabled), error. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "videoUrls": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ] }; // Run the Actor and wait for it to finish const run = await client.actor("seemuapps/youtube-comment-insights").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "videoUrls": ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"] } # Run the Actor and wait for it to finish run = client.actor("seemuapps/youtube-comment-insights").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "videoUrls": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ] }' | apify call seemuapps/youtube-comment-insights --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=seemuapps/youtube-comment-insights", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "YouTube Comment Insights", "description": "Analyze YouTube video comments into per-video audience insights. Sentiment breakdown, top keywords, requested topics, questions, and complaints.", "version": "1.0", "x-build-id": "MgUySdz2HsFREnR8x" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/seemuapps~youtube-comment-insights/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-seemuapps-youtube-comment-insights", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/seemuapps~youtube-comment-insights/runs": { "post": { "operationId": "runs-sync-seemuapps-youtube-comment-insights", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/seemuapps~youtube-comment-insights/run-sync": { "post": { "operationId": "run-sync-seemuapps-youtube-comment-insights", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Video URLs or IDs", "type": "array", "description": "List of YouTube video watch URLs or bare 11-character video IDs. Supports youtu.be/ID, watch?v=ID, and shorts/ID formats.", "items": { "type": "string" } }, "maxCommentsPerVideo": { "title": "Max Comments Per Video", "minimum": 20, "maximum": 1000, "type": "integer", "description": "How many top-level comments to analyze per video (20–1000). Higher values give richer insights but use more quota and time.", "default": 200 }, "commentOrder": { "title": "Comment Order", "enum": [ "relevance", "time" ], "type": "string", "description": "Order in which comments are fetched: Relevance (top/most engaged comments) or Newest (most recent first).", "default": "relevance" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```