TikTok Comments Analyzer (AI)

Turn the comments under TikTok videos into a report a creator, brand or TikTok Shop seller can act on: how viewers feel (weighted by likes, so the comments people agree with count more), the questions they keep asking as a ready FAQ, which questions the creator has not answered yet, what viewers want next, who wants to buy, what they complain about, what needs attention right now, and reply drafts that fit TikTok's 150 characters. Every quote is copied word for word from a real comment.

No setup and no AI account needed. Run it with no input to get a free demo report on sample comments.

Open the full sample report: 40 fictional comments on two videos of a demo cooking creator in four languages, with the FAQ, requests, buying intent, themes, creator engagement, a daily trend, a video comparison and reply drafts.

What you get

💬 Audience mood by likes	Positive, neutral, mixed and negative shares, weighted by likes: one complaint with 2,000 likes counts for more than ten with none
🚨 Needs attention now	Harassment, threats, self-harm, product safety, legal threats and scams, with the reason and a link to the video
❓ Top questions as a ready FAQ	The questions viewers ask most, merged across languages, with counts, likes and quotes
⏳ Unanswered questions	Which questions the creator liked, pinned or replied to, and the most liked ones still waiting
💡 Requests and content ideas	"Part 2?", "do this with chicken", "restock the big jar": what viewers ask for next
🛒 Buying intent	Comments that ask for the link or price, say they added to cart or ordered on TikTok Shop
👍👎 Praise and complaint themes	Top themes with counts, likes, share of comments and up to 3 verbatim quotes each
🧹 Spam share	How much of the thread is "follow for follow", "check my bio" and crypto offers; spam is left out of the mood and themes
✍️ Reply drafts	Short, friendly drafts in the commenter's language for the most liked questions and complaints the creator hasn't answered, within TikTok's 150 characters, with placeholders like [price] or [link] instead of invented facts
📈 Comments by day	Comment volume and the share of negative comments per day (per week for long threads)
📊 Video comparison	Side-by-side table when you analyze several videos, for example a launch against your usual videos, or yours against a competitor's
📄 Three outputs	An HTML report, a short JSON summary for code and AI agents, and one dataset row per comment

How to use it

1. With video URLs: paste TikTok video links (open the video, choose Share → Copy link; short vm.tiktok.com links work too) and click Start. We scrape their comments with TikTok Comments Scraper on your account first, then analyze them.
2. With a dataset you already have: put the dataset ID from a TikTok Comments Scraper run in Dataset ID.
3. Automatically after every scrape: open the scraper (or its saved task), go to Integrations, add TikTok Comments Analyzer (AI). The scraper's dataset is passed in automatically, so each scheduled scrape produces a fresh report.

The video's creator is recognised from the video link: their own comments and replies are left out of the numbers, the drafts and the charges, and questions they already replied to get no draft. If you also comment from another account, add it under Your other TikTok accounts.

Then open the Report tab of the run for the HTML report, or the Summary tab for JSON.

How much does it cost

You pay per result. Running the Actor itself costs you nothing extra: no compute or proxy charges.

Event	Free & Starter	Scale	Business and up
Analyzed comments (per 1,000)	$0.80	$0.65	$0.50
Report (per run)	$0.05	$0.05	$0.05
Reply draft (each)	$0.01	$0.01	$0.01

Never charged: the demo run, reactions (comments made only of emoji, stickers, images or @tags; they still count in the totals and the daily trend), the creator's own comments, comments we could not analyze, and runs that find no comments. Spam is analyzed and charged, so you can see how much of it there is.

Examples on the Free and Starter plans:

• One video with 1,000 comments, about 700 of them with words: $0.56 + $0.05 report + up to $0.25 of reply drafts = up to $0.86.
• An agency reporting on 20 videos a month with 500 comments each, about 350 with words: $5.60 + $1.00 for 20 reports = about $6.60 a month, plus up to $5 for reply drafts ($0.25 per video).

Reply drafts are on by default. Each run drafts replies to up to 25 unanswered questions and complaints (10 on the Free plan) at $0.01 each: up to +$0.25 per run on paid plans and up to +$0.10 on Free. Drafts are written to fit TikTok's 150 characters. To skip that cost, turn off Draft replies (draftReplies: false) or lower Max reply drafts (maxReplyDrafts).

Scraping is billed separately. If you give video URLs, TikTok Comments Scraper charges for the scrape on your account: $1.25 per 1,000 comments on the Free plan, down to $0.50 on Business. Deleted or private videos still cost one result each there. Replies (maxRepliesPerComment, 0 by default) count toward the comments per video.

Free-plan runs analyze up to 1,000 comments and draft up to 10 replies each. Your run's spending limit is always respected, for the scrape too: if it is lower than the full job, we analyze what fits and tell you in the status message.

Output

JSON summary (the OUTPUT record), shortened, from the free demo run on 40 fictional comments on two videos of a cooking creator who sells a spice blend:

{
  "coverage": { "comments": 38, "analyzed": 30, "reactions": 8, "own": 2, "spam": 2, "skipped": 0 },
  "overall": {
    "mood": { "positive": 0.53, "neutral": 0.21, "negative": 0.26, "mixed": 0 },
    "spamShare": 0.07,
    "questions": [
      { "name": "Are the noodles gluten free?", "count": 3, "likes": 271, "quote": "Are these noodles gluten free?" },
      { "name": "How spicy is the dish?", "count": 2, "likes": 107, "quote": "How spicy is this actually?" }
    ],
    "requests": [{ "name": "Part 2 with tofu", "count": 1, "likes": 230, "quote": "part 2 with tofu please!!" }],
    "topComplaints": [{ "name": "Delivery takes forever", "count": 3, "likes": 227, "quote": "Ordered 3 weeks ago and still no tracking update" }],
    "buyingIntent": { "count": 4, "share": 0.14 },
    "urgentCount": 2
  },
  "replies": [{ "commentId": "demo-03", "draft": "Thanks for asking! Our ingredient details are on the product page, [link]. Please check the label or DM us for celiac-safe confirmation." }],
  "creator": {
    "liked": 4, "pinned": 1, "replied": 1, "questions": 7, "questionsEngaged": 3,
    "unansweredQuestions": [{ "commentId": "demo-09", "text": "Where's the full recipe? The video goes so fast", "likes": 77, "url": null }]
  }
}

Dataset, one row per comment: video, reply or not, likes, date, text (with tagged people replaced by @user), whether the creator liked, pinned or replied to it, whether the creator wrote it, analysis status (analyzed, reaction, creator_comment or skipped), sentiment and score, topics, intents, phrases with verified excerpts, urgent flag and reason. Export it to Excel, CSV or JSON from the Storage tab.

How accurate is it

On a hand-labeled test set of 60 TikTok comments about food, beauty, fashion, tech and comedy in 6 languages, with slang, "😭" as laughter, "part 2?" and one-word comments (2026-10-18):

Check	Result
Overall sentiment matches the label	98.3%
Topics found (F1)	0.91
Intents found (F1): question, request, praise, complaint, buying intent, spam	0.97
Questions found	93%
Spam found	100%, no false alarms
Comments that need attention caught	100%, no false alarms in 60 comments
Quotes that are word for word from the comment	100% (enforced by code: anything else is dropped)

The AI only labels comments. Every count, share, ranking and trend is computed by code from those labels, so the numbers add up.

What it does not do: it does not watch the video or read its caption. TikTok has no links to single comments, so quotes link to the video. It analyzes the replies TikTok Comments Scraper returns, which may not be all of them. It does not detect bought followers or likes, and it never posts anything: reply drafts are for you to edit and post. AI labels can be wrong on sarcasm, slang or one-word comments, which is why every theme shows its quotes.

For AI agents and automations

• Free demo: call it with {} to get a full sample report and JSON summary at no cost.
• Minimal input: { "videoUrls": ["https://www.tiktok.com/@creator/video/..."] } or { "datasetId": "<dataset id>" }.
• Read the result: the OUTPUT record is a short JSON summary designed to fit in one tool call (under 20,000 characters; with many videos, per-video detail is shortened first, and with many reply drafts only the first ones are kept): coverage, mood by likes, spam share, top questions, requests, praise and complaints with one quote each, buying intent, the daily trend, reply drafts, the creator's likes, pins and unanswered questions, and a link to the HTML report.
• Never charged: no comments found, reactions, the creator's own comments, and comments that could not be analyzed. The status message says why.
• Works through Apify's MCP server, the Apify API and SDKs, and Make, Zapier or n8n.

FAQ

Which languages does it support? Comments in any language. Theme names are in the language you choose (reportLanguage, default English) and report headings are in English. Questions asked in several languages are merged into one FAQ entry. Quotes stay in each comment's own language.

Can I analyze several videos, or a competitor's videos? Yes. Give several video URLs (or a dataset with several videos) and the report adds a video comparison table, with a summary per video in the JSON. Each video's creator is recognised from its link, so on a competitor's video their own replies are left out too.

Does it collect usernames? No. Usernames, user IDs, avatars and the names of tagged people are removed from the data before anything else happens, and tagged people inside comments are replaced by @user, also when TikTok shows them by display name without "@". The creator is matched only from the video link, and accounts you add under Your other TikTok accounts are only matched, never saved in the results.

What counts as a reaction? A comment with no words: only emoji, a sticker, an image, punctuation or @tags, such as "😍😍" or "@user". Reactions are counted, shown in the daily trend, and never charged.

How does it know what the creator answered? TikTok marks comments the creator liked or pinned, and the creator's own replies sit under the comment they answer. Scrape replies (maxRepliesPerComment above 0) to see which questions the creator replied to; likes and pins come with every comment.

Where is comment text processed? By the Anthropic API (Claude). SignalSift keeps nothing after the run; your results stay in your Apify storage.

Is it legal? It analyzes publicly available comments. You are responsible for how you use the results and for complying with the laws that apply to you, including GDPR when you handle personal data.

Something is wrong or missing? Open an issue on the Issues tab. We read every one.

Changelog

• 0.1 (2026-10-18): First release. Video URLs (short links too), datasets and integrations; audience mood weighted by likes; comments that need attention now; top questions as a ready FAQ; creator engagement with liked, pinned and unanswered questions; requests and content ideas; buying intent; praise and complaint themes with verified quotes; spam share; reply drafts within 150 characters; daily trend; video comparison; the creator's own comments left out; HTML report and JSON summary; free demo.

---

SignalSift is not affiliated with or endorsed by Google, Amazon, TikTok, Meta or YouTube. Their logos only show which platform each Actor works with.