douyin-sentiment-dashboard

douyin-sentiment-dashboard Douyin short video operations growth assistant

Quick start

More skills

Overview

The Douyin short video operations growth assistant is used to answer "how to operate Douyin short videos," analyze comment feedback, assess sentiment and public opinion risks, and examine user profiles and intent. It is suitable for content creators, operators, brands, and e-commerce businesses to use after clarifying business goals, content materials, or analysis targets. It combines inputs such as video/note links and pasted Douyin share links, organizes key context, and outputs sentiment and public opinion judgments, user profiles and intent signals, operational suggestions, and reply suggestions, making it easy to continue execution, review, or deliver.

When to use

Applicable scenarios

• The user provides a Douyin content link
• The user wants to analyze comment sentiment, user profiles, public opinion, or operational insights
• The user wants to review feedback on already published content

How to invoke

After running the script, it automatically completes three steps: parse the share link, create an analysis task, and poll until the task is completed.

Command example

Analyze Douyin video comments

python3 scripts/run.py --params '{"link":"https://v.douyin.com/xxxxx"}'

Parameter description

Parameter	Type	Required	Default	Description
videoUrl	string	Yes	-	Paste the Douyin share link

For the complete machine-readable parameter structure, see references/form-schema.json。

Parameter value reference

This skill currently has no categorical parameters that require an additional lookup table.

Supported input formats

Paste a Douyin share link or video ID; all of the following formats can be tried directly:

• https://www.douyin.com/video/7462574818594200872
• https://v.douyin.com/iNsVxxx/
• 7462574818594200872

Example request

The example parameters below can be passed directly to scripts/run.py , and the script will automatically complete parsing the link, creating the task, and polling for the result.

python3 scripts/run.py --params '{"link":"https://v.douyin.com/xxxxx"}'

Equivalent --params JSON：

{
  "link": "https://v.douyin.com/xxxxx"
}

Example returned result

{
  "success": true,
  "data": {
    "task": {
      "id": "task_demo_123",
      "platform": "douyin",
      "contentId": "7505866362912425270",
      "contentTitle": "抖音运营拆解示例",
      "status": "completed",
      "progress": 100,
      "progressMessage": "分析完成",
      "result": {
        "summary": {
          "analyzedComments": 168,
          "timeRange": {
            "start": "2026-04-23T00:00:00.000Z",
            "end": "2026-04-24T00:00:00.000Z"
          },
          "platform": "douyin",
          "contentId": "7505866362912425270",
          "contentTitle": "抖音运营拆解示例",
          "analyzedAt": "2026-04-24T11:35:00.000Z"
        },
        "aiInsights": {
          "summary": "评论区主要在追问选题拆解、发布时间和账号定位，适合继续做系列内容。",
          "sentiment": {
            "trend": "mixed",
            "label": "正向为主",
            "riskLevel": "low"
          },
          "operationAdvice": [
            {
              "category": "content",
              "priority": "P1",
              "title": "继续做系列",
              "detail": "围绕这条内容延展 3 个具体场景，继续承接评论区追问。",
              "reason": "高频评论集中在“下一条怎么做”，说明用户有连续追更意愿。"
            }
          ]
        },
        "labeledComments": [
          {
            "id": "comment_1",
            "content": "讲得很清楚，想看你下一条怎么实操。",
            "sentiment": "positive",
            "likes": 26
          }
        ]
      }
    }
  }
}

Deliverables

• Overall comment section conclusion: helps quickly determine content reputation, discussion focus, and potential public opinion risks.
• User feedback breakdown: extracts high-frequency demands, typical comments, sentiment tendencies, and user profile clues.
• Operational action suggestions: provides directions for subsequent content optimization, comment replies, series topic selection, or conversion follow-up.

Suggestions for using the results

• First look at the overall sentiment and one-sentence summary to determine whether the content feedback is positive, controversial, watchful, or risky.
• Then look at high-frequency comments and user profiles to identify the issues users truly care about, purchase/interaction intent, and content gaps.
• Finally, turn the operational suggestions into the next content topic, comment reply strategy, or private-domain follow-up action.

Preparation before running

• AISKILLS_BASE_URL: default https://ai-skills.ai
• AISKILLS_API_KEY: required, used for authenticated calls
• AISKILLS_TENANT_ID: default default