tracking-twitter-thought-leaders

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Tracking Twitter Thought Leaders

追踪Twitter意见领袖

Finds Twitter/X accounts with genuine influence in a topic area — not just high follower counts, but accounts whose tweets get shared and discussed. Delivers a ranked list for PR outreach, community engagement, or partnership targeting.

查找在某主题领域具有真实影响力的Twitter/X账号——不仅是粉丝数多，而是推文被大量分享和讨论的账号。提供排名列表，用于公关拓展、社区互动或合作目标定位。

Prerequisites

前置条件

```
APIFY_TOKEN
```
environment variable set
Optional: Apify MCP server installed

```
APIFY_TOKEN
```
环境变量已设置
可选：已安装Apify MCP服务器

Inputs

输入参数

Parameter	Type	Required	Default	Notes
`startUrls`	array	Optional	`[]`	Twitter profile or tweet URLs
`twitterHandles`	array	Optional	`[]`	Twitter usernames (without @)
`twitterUserIds`	array	Optional	`[]`	Twitter user IDs
`getFollowers`	boolean	Optional	`false`	Extract follower lists
`getFollowing`	boolean	Optional	`false`	Extract following lists
`getRetweeters`	boolean	Optional	`false`	Extract retweeters of a tweet URL
`includeUnavailableUsers`	boolean	Optional	`false`	Include unavailable/suspended users
`maxItems`	number	Optional	Unlimited	Maximum users to return
`customMapFunction`	string	Optional	—	JavaScript function to transform each output object

参数	类型	是否必填	默认值	说明
`startUrls`	array	可选	`[]`	Twitter个人主页或推文URL
`twitterHandles`	array	可选	`[]`	Twitter用户名（不带@）
`twitterUserIds`	array	可选	`[]`	Twitter用户ID
`getFollowers`	boolean	可选	`false`	提取粉丝列表
`getFollowing`	boolean	可选	`false`	提取关注列表
`getRetweeters`	boolean	可选	`false`	提取某推文URL的转发者
`includeUnavailableUsers`	boolean	可选	`false`	包含不可用/被封禁用户
`maxItems`	number	可选	无限制	返回的最大用户数量
`customMapFunction`	string	可选	—	用于转换每个输出对象的JavaScript函数

Workflow

工作流程

Progress:
- [ ] Step 1: Define topic, industry, and influence criteria
- [ ] Step 2: Search for topic-relevant tweets to find active voices
- [ ] Step 3: Enrich top accounts with profile data
- [ ] Step 4: Score by influence signals
- [ ] Step 5: Deliver ranked thought leader list

进度:
- [ ] 步骤1：定义主题、行业及影响力标准
- [ ] 步骤2：搜索主题相关推文以找到活跃发声者
- [ ] 步骤3：为顶级账号补充个人资料数据
- [ ] 步骤4：根据影响力指标打分
- [ ] 步骤5：输出排名后的意见领袖列表

Step 1: Clarify Parameters

步骤1：明确参数

Ask the user for:

Topic or industry (e.g., "AI safety", "B2B SaaS growth", "climate tech")
Influence type — broad reach (high followers), community depth (high engagement), or rising voices (growing fast)
Follower range (default: 5,000–2,000,000 — excludes unknown accounts and mega-celebrities)
Geography/language (optional)
List size (default: 25)

向用户询问以下信息：

主题或行业（例如："AI safety", "B2B SaaS growth", "climate tech"）
影响力类型——广泛覆盖（高粉丝数）、社区深度（高互动率）或新兴发声者（快速增长）
粉丝数量范围（默认：5000–2000000——排除不知名账号和超级名人）
地域/语言（可选）
列表规模（默认：25个）

Step 2: Search for Topic Tweets

步骤2：搜索主题相关推文

Find who's actively tweeting about the topic — recent activity matters more than old follower counts.

Recommended — run_actor.js (handles waiting, output, and file saving automatically):

bash

undefined

找出正在积极发布该主题推文的用户——近期活跃度比过往粉丝数更重要。

推荐使用 — run_actor.js（自动处理等待、输出和文件保存）：

bash

undefined

Quick answer (prints table to chat)

快速输出（在聊天中打印表格）

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

Save as CSV

保存为CSV格式

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

Save as JSON

保存为JSON格式

node scripts/run_actor.js
--actor "apidojo~twitter-user-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~tweet-scraper" Input: { "searchTerms": ["[TOPIC_KEYWORD_1]", "[TOPIC_KEYWORD_2]", "[TOPIC_KEYWORD_3]"], "maxItems": 300, "tweetLanguage": "en" }


**REST API fallback:**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "searchTerms": ["[TOPIC_KEYWORD_1]", "[TOPIC_KEYWORD_2]"],
    "maxItems": 300
  }'

Extract unique

author.username

values from all results. Sort by their tweet's retweet+like count — accounts whose topic tweets get the most engagement are the most influential voices.

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

> 必须在环境变量或`.env`文件中设置`APIFY_TOKEN`。

**如果Apify MCP可用：**

工具: apify:run-actor Actor: "apidojo~tweet-scraper" 输入: { "searchTerms": ["[TOPIC_KEYWORD_1]", "[TOPIC_KEYWORD_2]", "[TOPIC_KEYWORD_3]"], "maxItems": 300, "tweetLanguage": "en" }


**REST API备选方案：**
```bash
curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "searchTerms": ["[TOPIC_KEYWORD_1]", "[TOPIC_KEYWORD_2]"],
    "maxItems": 300
  }'

从所有结果中提取唯一的

author.username

值。根据推文的转发+点赞数排序——主题推文获得最多互动的账号就是最具影响力的发声者。

Step 3: Enrich with Profile Data

步骤3：补充个人资料数据

Take top 100 candidate usernames. Fetch full profiles.

If Apify MCP is available:

Tool: apify:run-actor
Actor: "apidojo~twitter-user-scraper"
Input:
{
  "usernames": ["[username1]", "[username2]", "...up to 100"]
}

REST API fallback:

bash

curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["[username1]", "[username2]"]}'

选取前100个候选用户名，获取完整的个人资料。

如果Apify MCP可用：

工具: apify:run-actor
Actor: "apidojo~twitter-user-scraper"
输入:
{
  "usernames": ["[username1]", "[username2]", "...最多100个"]
}

REST API备选方案：

bash

curl -X POST \
  "https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=$APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"usernames": ["[username1]", "[username2]"]}'

Step 4: Score by Influence

步骤4：影响力打分

Calculate composite influence score for each account:

topic_engagement = avg(likes + retweets) on topic-related tweets
audience_quality = followers / following ratio (>1 is healthy)
influence_score = topic_engagement * log(followers) * audience_quality

Filter: keep only accounts within follower range AND whose bio suggests topical relevance.

为每个账号计算综合影响力得分：

topic_engagement = 主题相关推文的平均点赞+转发数
audience_quality = 粉丝数 / 关注数比值（>1为健康状态）
influence_score = topic_engagement * log(followers) * audience_quality

筛选：仅保留粉丝数在指定范围内且简介显示与主题相关的账号。

Step 5: Format Output

步骤5：格式化输出

Output Format

输出格式

undefined

undefined

Twitter Thought Leaders: [TOPIC/INDUSTRY]

Twitter意见领袖：[主题/行业]

Accounts analyzed: [N] | Final list: [N] | Date: [DATE]

分析账号数量：[N] | 最终列表数量：[N] | 日期：[DATE]

Top Thought Leaders

顶级意见领袖

#	Name	@Handle	Followers	Influence Score	Bio Excerpt	Recent Top Tweet
1	[name]	@[handle]	[N]	[score]	[bio]	"[tweet excerpt]"

排名	姓名	@账号	粉丝数	影响力得分	简介摘录	近期热门推文
1	[姓名]	@[账号]	[N]	[得分]	[简介]	"[推文摘录]"

Tier Breakdown

层级划分

🏆 Power Voices (500K+ followers)

🏆 核心大V（50万+粉丝）

[list with brief bio and latest relevant tweet]

[列表包含简短简介和最新相关推文]

🎯 Core Influencers (50K–500K followers)

🎯 关键影响者（5万–50万粉丝）

[list — best for outreach: big enough to matter, accessible enough to respond]

[列表——最适合拓展：规模足够大，回复可能性高]

🌱 Rising Voices (5K–50K followers)

🌱 新兴发声者（5千–5万粉丝）

[list — early partnership opportunity, lower cost, high engagement]

[列表——早期合作机会，成本更低，互动率高]

Best Accounts for Direct Outreach

适合直接拓展的最佳账号

[Top 5 picks with rationale — why they're ideal for PR, partnership, or co-content]

[前5个推荐账号及理由——为何适合公关、合作或联合内容创作]

Content Themes These Voices Tweet About

这些发声者的推文主题

[Theme 1]: [N] of the accounts tweet regularly about this
[Theme 2]: [N] accounts

undefined

[主题1]：[N]个账号定期发布该主题内容
[主题2]：[N]个账号

undefined

Troubleshooting

故障排查

Results dominated by one person: Some topics have one mega-voice. Exclude them and surface the next tier. Not enough topically relevant accounts: Expand keyword list with synonyms, adjacent topic terms, and industry jargon. Follower counts seem off: Cached data — for final list, spot-check top 5 accounts directly on Twitter.

结果被单一用户主导： 某些主题存在超级发声者。排除他们，展示下一层级的用户。 主题相关账号不足： 使用同义词、相邻主题术语和行业行话扩展关键词列表。 粉丝数似乎不准确： 数据来自缓存——对于最终列表，直接在Twitter上抽查前5个账号。