Back to Details

monitoring-tiktok-mentions-of-brand

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Monitoring TikTok Mentions of a Brand

监控TikTok上的品牌提及内容

Tracks TikTok content mentioning a brand via branded hashtags and keyword searches. TikTok is the fastest-moving platform for brand sentiment — viral criticism or praise can emerge in hours.
通过品牌话题标签和关键词搜索，追踪提及品牌的TikTok内容。TikTok是品牌舆情传播最快的平台——负面评价或正面赞誉可能在数小时内迅速扩散。

Prerequisites

前提条件

  • APIFY_TOKEN
    environment variable set
  • Optional: Apify MCP server installed
  • 已设置
    APIFY_TOKEN
    环境变量
  • 可选：已安装Apify MCP服务器

Inputs

输入参数

ParameterTypeRequiredDefaultNotes
startUrls
arrayOptional
[]
TikTok URLs — user profiles, hashtags, music pages, search, locations
keywords
arrayOptional
[]
Search keywords/terms to find posts
sortType
stringOptional
RELEVANCE
Sort order for keyword results: 
RELEVANCE
, 
MOST_LIKED
, 
DATE_POSTED
location
stringOptional—ISO 3166-1 alpha-2 country code for regional filtering (e.g. 
US
, 
GB
)
maxItems
numberOptionalUnlimitedMaximum posts to return across the run
includeSearchKeywords
booleanOptional
false
Add the matched search keyword field to each post
customMapFunction
stringOptional—JavaScript function to transform each output object
参数类型是否必填默认值说明
startUrls
数组可选
[]
TikTok链接——用户主页、话题标签、音乐页面、搜索结果页、地点页面
keywords
数组可选
[]
用于查找帖子的搜索关键词/术语
sortType
字符串可选
RELEVANCE
关键词搜索结果的排序方式：
RELEVANCE
（相关性）、
MOST_LIKED
（点赞最多）、
DATE_POSTED
（发布日期）
location
字符串可选—用于区域过滤的ISO 3166-1 alpha-2国家代码（例如
US
、
GB
）
maxItems
数字可选无限制本次运行返回的最大帖子数量
includeSearchKeywords
布尔值可选
false
为每个帖子添加匹配的搜索关键词字段
customMapFunction
字符串可选—用于转换每个输出对象的JavaScript函数

Workflow

工作流程

Progress:
- [ ] Step 1: Run tiktok-scraper for branded hashtags
- [ ] Step 2: Filter by view count and date
- [ ] Step 3: Classify sentiment and content type
- [ ] Step 4: Identify trending posts and crisis signals
- [ ] Step 5: Deliver monitoring report
进度:
- [ ] 步骤1：针对品牌话题标签运行tiktok-scraper
- [ ] 步骤2：按浏览量和日期筛选内容
- [ ] 步骤3：分类情感倾向及内容类型
- [ ] 步骤4：识别热门帖子及危机信号
- [ ] 步骤5：交付监控报告

Step 1: Run the Actor

步骤1：运行Actor

Recommended — run_actor.js (handles waiting, output, and file saving automatically):
bash
undefined
推荐方式 — run_actor.js（自动处理等待、输出及文件保存）：
bash
undefined

Quick answer (prints table to chat)

快速查看结果（在聊天窗口打印表格）

node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'
node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'

Save as CSV

保存为CSV文件

node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'
--output YYYY-MM-DD_results.csv --format csv
node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'
--output YYYY-MM-DD_results.csv --format csv

Save as JSON

保存为JSON文件

node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'
--output YYYY-MM-DD_results.json --format json
> `APIFY_TOKEN` must be set in environment or `.env` file.

**If Apify MCP is available:**
Tool: apify:run-actor Actor: "apidojo~tiktok-scraper" Input: { "keywords": ["#[BRAND]", "#[BRAND]review", "#[BRAND]honest"], "maxItems": 200 }

**REST API fallback:**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~tiktok-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{
    "keywords": ["#[brand]", "#[brand]review", "#[brand]honest"],
    "maxItems": 200
  }'
node scripts/run_actor.js
--actor "apidojo~tiktok-scraper"
--input '{"param": "value"}'
--output YYYY-MM-DD_results.json --format json
> `APIFY_TOKEN`必须在环境变量或`.env`文件中设置。

**若Apify MCP可用：**
工具: apify:run-actor Actor: "apidojo~tiktok-scraper" 输入: { "keywords": ["#[BRAND]", "#[BRAND]review", "#[BRAND]honest"], "maxItems": 200 }

**REST API备选方案：**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~tiktok-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{
    "keywords": ["#[brand]", "#[brand]review", "#[brand]honest"],
    "maxItems": 200
  }'

Step 2: Classify and Score

步骤2：分类与评分

Content type:
UNBOXING = "unboxing", "first impression", "first look"
REVIEW = "review", "honest", "real talk", "thoughts on"
COMPLAINT = "disappointed", "refund", "scam", "doesn't work", "returning"
TUTORIAL = "how to", "tips", "tutorial"
ENTERTAINMENT = trend audio, no product focus
Sentiment (lexical — same model as Twitter sentiment skill):
  • Use positive/negative/neutral indicators
  • Weight by 
    diggCount
    (likes) as community agreement signal
Virality signal:
virality = playCount / (follower_count_of_creator + 1)
If 
virality > 2.0
: post is reaching well beyond the creator's audience — flag as 
TRENDING
内容类型：
UNBOXING = "unboxing", "first impression", "first look"
REVIEW = "review", "honest", "real talk", "thoughts on"
COMPLAINT = "disappointed", "refund", "scam", "doesn't work", "returning"
TUTORIAL = "how to", "tips", "tutorial"
ENTERTAINMENT = 潮流音频，无产品聚焦
情感倾向（基于词典——与Twitter情感分析工具使用相同模型）：
  • 使用正面/负面/中性指标
  • 以
    diggCount
    （点赞数）作为社区共识信号进行加权
爆款信号：
virality = playCount / (follower_count_of_creator + 1)
若
virality > 2.0
：该帖子的传播范围远超创作者的粉丝群体——标记为
TRENDING
（热门）

Step 3: Crisis Detection

步骤3：危机检测

Flag 
CRISIS_ALERT
when:
  • Any single post with 
    playCount > 500K
    AND 
    sentiment = NEGATIVE
  • More than 5 complaint posts in 48 hours
  • Comment-to-view ratio > 3% on a negative post (high engagement = controversy)
出现以下情况时标记
CRISIS_ALERT
（危机预警）：
  • 单条帖子
    playCount > 500K
    且
    sentiment = NEGATIVE
    （负面）
  • 48小时内出现5条以上投诉类帖子
  • 负面帖子的评论/浏览量占比>3%（高互动量意味着争议）

Step 4: Edge Cases

步骤4：边缘情况

  • Hashtag overloaded with unrelated content: Add brand sub-product or model name to narrow
  • Brand has low TikTok presence (< 10 posts): This is notable data — report it; brand may need proactive TikTok strategy
  • Duet/Stitch posts about brand: These count as mentions but are often reactions to original content — classify as 
    REACTION
    and note the source video
  • 话题标签包含大量无关内容：添加品牌子产品或型号名称以缩小范围
  • 品牌在TikTok上曝光度低（<10条帖子）：这是值得关注的数据——需在报告中提及；品牌可能需要制定积极的TikTok运营策略
  • 关于品牌的Duet/Stitch帖子：这些属于品牌提及内容，但通常是对原内容的回应——分类为
    REACTION
    （回应）并标注源视频

Output Format

输出格式

undefined
undefined

TikTok Brand Monitor: [BRAND_NAME]

TikTok品牌监控报告: [BRAND_NAME]

Period: [DATE_RANGE] | Posts collected: [N] | Total estimated reach: [N] views | Date: [DATE]
周期: [DATE_RANGE] | 收集到的帖子数量: [N] | 预估总覆盖量: [N] 次浏览 | 报告日期: [DATE]

Overall Sentiment

整体情感倾向

Positive: [X%] | Negative: [X%] | Neutral: [X%] ⚠️ CRISIS ALERTS: [N] (posts above threshold — see below)
正面: [X%] | 负面: [X%] | 中性: [X%] ⚠️ 危机预警: [N]（超过阈值的帖子——详见下方）

Content Type Distribution

内容类型分布

Unboxing: [N] | Reviews: [N] | Complaints: [N] | Tutorials: [N]
开箱视频: [N] | 评测: [N] | 投诉: [N] | 教程: [N]

Trending Posts (> 100K Views)

热门帖子（>10万次浏览）

Creator@HandleViewsLikesSentimentTypeCaption Preview
创作者@账号浏览量点赞数情感倾向类型文案预览

CRISIS ALERTS (Negative + High Reach)

危机预警（负面+高传播量）

CreatorViewsComplaint ThemeDays LivePost URL
创作者浏览量投诉主题发布时长（天）帖子链接

Top Advocates

核心支持者

Creator@HandleFollowersViewsPost TypeScore
undefined
创作者@账号粉丝数浏览量帖子类型评分
undefined

Troubleshooting

故障排查

Very few posts found: Brand may be using a different hashtag convention. Try product name without brand (
#[product]
not 
#[brand]product
). All results are unboxing/haul content: Normal for consumer brands — this is positive. Set monitoring to alert only on negative content. Crisis alert triggered by troll campaign: Check if complaint posts are from a cluster of new accounts (created within 30 days, < 100 followers) — may be coordinated; note this context in report.
找到的帖子极少：品牌可能使用了不同的话题标签规则。尝试仅使用产品名称而非品牌+产品（
#[product]
而非
#[brand]product
）。 所有结果均为开箱/购物分享内容：对于消费品牌而言这是正常现象，属于正面信号。可将监控设置为仅针对负面内容发出预警。 危机预警由水军活动触发：检查投诉帖子是否来自一批新账号（创建时间在30天内，粉丝数<100）——可能是有组织的水军行为；需在报告中注明该背景信息。