apidojo-io/apidojo-skills

analyzing-twitter-sentiment-for-topic

Analyzes public sentiment on Twitter/X for any topic, brand, or event using apidojo's Tweet scrapers on Apify.

소스 보기

사용 방법

  1. 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
  2. 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
  3. 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/apidojo-io/apidojo-skills --skill analyzing-twitter-sentiment-for-topic

시작 전 확인

  • 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
  • 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Analyzing Twitter Sentiment for a Topic

Collects a sample of tweets about any topic or keyword and performs sentiment analysis across the dataset. Identifies dominant emotional tone, key themes driving positive/negative sentiment, and volume patterns over time.

Prerequisites

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

Inputs

ParameterTypeRequiredDefaultNotes
searchTermsarray✅[]Twitter advanced search queries (e.g. ["#AI lang:en", "from:NASA"])
sortstringOptionalTopSort order: Latest, Top, or Latest+Top
tweetLanguagestringOptional—ISO 639-1 language code (e.g. en)
maxItemsnumberOptionalUnlimitedMaximum tweets to return
onlyVerifiedUsersbooleanOptionalfalseOnly tweets from verified users
onlyTwitterBluebooleanOptionalfalseOnly Twitter Blue subscribers
onlyImagebooleanOptionalfalseOnly tweets with images
onlyVideobooleanOptionalfalseOnly tweets with videos
onlyQuotebooleanOptionalfalseOnly quote tweets
authorstringOptional—Filter to a specific author handle
inReplyTostringOptional—Tweets replying to a specific handle
mentioningstringOptional—Tweets mentioning a specific handle
geotaggedNearstringOptional—Tweets near a location
withinRadiusstringOptional—Radius around geotaggedNear
geocodestringOptional—Lat/lng + radius string
placeObjectIdstringOptional—Tweets tagged with a place
minimumRetweetsnumberOptional—Minimum retweet count
minimumFavoritesnumberOptional—Minimum like count
minimumRepliesnumberOptional—Minimum reply count
startstringOptional—Tweets after this date (YYYY-MM-DD)
endstringOptional—Tweets before this date (YYYY-MM-DD)
includeSearchTermsbooleanOptionalfalseAdd the matched search term to each tweet
customMapFunctionstringOptional—JavaScript function to transform each output object

Workflow

Progress:
- [ ] Step 1: Define topic and sentiment scope
- [ ] Step 2: Collect tweets via search
- [ ] Step 3: Classify sentiment per tweet
- [ ] Step 4: Identify themes per sentiment bucket
- [ ] Step 5: Deliver sentiment report

Step 1: Clarify Parameters

Ask the user for:

  • Topic, keyword, or brand to analyze
  • Date range (default: last 7 days — Twitter sentiment data decays fast)
  • Language (default: English)
  • Sample size (default: 500 tweets — sufficient for reliable distribution)
  • Exclude retweets? (default: yes — reduces duplicated opinion signals)
  • Comparison topic (optional — for side-by-side sentiment comparison)

Step 2: Collect Tweets

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

bash
# Quick answer (prints table to chat)
node scripts/run_actor.js \
  --actor "apidojo~tweet-scraper" \
  --input '{"param": "value"}'

# Save as CSV
node scripts/run_actor.js \
  --actor "apidojo~tweet-scraper" \
  --input '{"param": "value"}' \
  --output YYYY-MM-DD_results.csv --format csv

# Save as JSON
node scripts/run_actor.js \
  --actor "apidojo~tweet-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]"],
  "maxItems": 500,
  "tweetLanguage": "en",
  "since": "[YYYY-MM-DD]",
  "until": "[YYYY-MM-DD]"
}

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]"],
    "maxItems": 500,
    "tweetLanguage": "en",
    "since": "[YYYY-MM-DD]"
  }'

Step 3: Classify Sentiment

For each tweet's text, classify as Positive, Negative, or Neutral using lexical signals:

Positive indicators: love, great, amazing, perfect, best, win, excited, congrats, excellent, recommend, beautiful, proud, happy, thank, awesome, incredible Negative indicators: hate, awful, worst, terrible, broken, scam, disappointed, angry, frustrated, disgusted, avoid, never again, shame, sad, fail, wrong, bad Strong negative amplifiers: "can't believe", "what a joke", "are you serious", "wtf", "this is ridiculous" Neutral default: Everything else

For ambiguous cases, use emoji signals:

  • 😍🥰❤️🙌👏✨🔥 → lean Positive
  • 😡🤬😤💀🗑️🤢👎 → lean Negative
  • 🤔😐🤷 → lean Neutral

Weight tweets by engagement: a tweet with 1,000 likes carries more signal than one with 0.

Step 4: Theme Extraction

For Negative tweets: identify the top 3-5 recurring nouns/themes. What are people upset about specifically? For Positive tweets: identify the top 3-5 recurring praise themes.

Look for proper nouns (people, places, products), specific events, or feature names that appear repeatedly.

Step 5: Format Report

Output Format

# Twitter Sentiment Analysis: "[TOPIC]"
Period: [DATE_RANGE] | Tweets analyzed: [N] | Date: [DATE]

## Overall Sentiment

████████████░░░░░░░░ Positive: [X%] ([N] tweets) ████░░░░░░░░░░░░░░░░ Negative: [X%] ([N] tweets) ██████████░░░░░░░░░░ Neutral: [X%] ([N] tweets)


Weighted by engagement:
- Positive sentiment accounts for [X%] of total likes/RTs
- Negative sentiment accounts for [X%] of total likes/RTs

**Overall verdict:** [Mostly Positive / Mixed / Mostly Negative / Polarized]

## Top Negative Themes
1. "[Theme]" — [N] tweets, [N] total likes
   Example: "@[handle]: [tweet excerpt]"
2. "[Theme]" — [N] tweets
3. "[Theme]" — [N] tweets

## Top Positive Themes
1. "[Theme]" — [N] tweets, [N] total likes
   Example: "@[handle]: [tweet excerpt]"
2. "[Theme]" — [N] tweets

## Most Engaged Tweets
🔴 Most-liked negative: @[handle] ([N] likes): "[excerpt]"
🟢 Most-liked positive: @[handle] ([N] likes): "[excerpt]"

## Volume Over Time
[Day 1]: [N] tweets | [Day 2]: [N] tweets | [Day 3]: [N] tweets

## Notable Spikes
[Date with highest volume] — [N] tweets | Likely cause: [describe if detectable from tweet context]

Troubleshooting

Sentiment feels inaccurate: Lexical analysis misses sarcasm. For high-stakes decisions, manually review the top 20 tweets per bucket. Topic too broad: Narrow the search term. "Apple" returns tech and food — use "Apple iPhone" instead. Very low tweet volume: Topic may not be actively discussed on Twitter right now. Expand date range.

관련 작업

같은 저장소의 Skills

더 많은 Skills

모든 Skills
apidojo-io
커뮤니티

discovering-tiktok-creators-by-niche

Discovers and ranks TikTok creators in any niche or topic using apidojo's TikTok scrapers on Apify. Triggers when the user asks to: find TikTok influencers in a specific niche, discover creators for a campaign, identify who's growing fastest on TikTok in a category, find micro-influencers on TikTok under a certain follower count, build a list of TikTok creators for brand partnerships, compare TikTok creator engagement rates in a vertical, or identify rising TikTok stars. Returns creator username

1시간 설치 수
2
GitHub Stars
1
업데이트
5월 13일
apidojo-io
커뮤니티

finding-gaming-content-creators

Finds gaming content creators on TikTok and YouTube using apidojo's scrapers on Apify. Triggers when the user asks to: find gaming influencers for brand campaigns, discover streamers or gaming YouTubers in a specific game or genre, find TikTok creators posting gaming content, identify gaming micro-influencers for product sponsorships, find gaming creators who review hardware or accessories, build a gaming creator outreach list for a gaming brand or peripheral company, or discover rising gaming c

1시간 설치 수
2
GitHub Stars
1
업데이트
5월 13일
apidojo-io
커뮤니티

scraping-instagram-posts-by-hashtag

Scrapes Instagram posts for any hashtag using apidojo's Instagram scraper on Apify. Triggers when the user asks to: get Instagram posts for a hashtag, scrape Instagram content by tag, export Instagram post data for a keyword or topic, fetch posts under an Instagram challenge or trend, collect Instagram media for a specific tag, or download Instagram post metadata by hashtag. Returns post URL, caption, like count, comment count, author handle, and timestamp per post. Ideal for trend analysts, UGC

1시간 설치 수
2
GitHub Stars
1
업데이트
5월 13일
apidojo-io
커뮤니티

scraping-tiktok-profile-data

Scrapes TikTok profile statistics and metadata for any list of accounts using apidojo's TikTok Profile scraper on Apify. Triggers when the user asks to: get TikTok profile stats for an account, fetch follower count and engagement data for TikTok users, scrape TikTok account metadata in bulk, export TikTok profile information for a list of creators, check TikTok stats for multiple usernames, or get bio and follower data from TikTok profiles. Returns username, follower count, following count, tota

1시간 설치 수
1
GitHub Stars
1
업데이트
5월 13일