Topic Trend Aggregator avatar
Topic Trend Aggregator

Pricing

Pay per event

Go to Apify Store
Topic Trend Aggregator

Topic Trend Aggregator

Developed by

bySeitz AI & Automation

bySeitz AI & Automation

Maintained by Community

This actor is the central intelligence hub for a multi-pipeline news aggregation system. Its primary role is to fetch, unify, cleanse, and analyze raw news data from multiple Apify news pipeline actors, preparing a structured dataset of topical trends for downstream AI services.

0.0 (0)

Pricing

Pay per event

1

2

2

Last modified

18 hours ago

Topic Trend Aggregator Actor (topic_trend_aggregator_actor)

This actor is the central intelligence hub for a multi-pipeline news aggregation system. Its primary role is to fetch, unify, cleanse, and analyze raw news data from multiple Apify news pipeline actors, preparing a structured dataset of topical trends for downstream AI services.

🎯 Key Features

  • Dynamic Pipeline Aggregation: Fetches the most recent successful datasets from an arbitrary list of user-selected news pipeline actors (e.g., Global Markets, AI, World News).
  • Data Cleansing: Performs rigorous deduplication based on article URL and title to ensure a clean, unique dataset.
  • LLM-Powered Analysis (Mocked): Performs the heavy lifting for topic clustering and scoring (currently mocked for cost efficiency but designed for integration with models like OpenAI):
    • Extracts Key Entities (people, organizations, concepts).
    • Clusters Similar Stories into distinct, named topics (e.g., "AI Regulation").
    • Assigns a Trend Score (0-100) based on article volume, source diversity, and recency.
  • Structured Output: Delivers a clean, consistent JSON dataset for consumption by subsequent machine-learning and content generation actors.

⚙️ How It Fits into the Ecosystem

The topic_trend_aggregator_actor is the analytical layer that transforms raw data into actionable intelligence. Its output directly feeds the next stages of your content generation workflow:

Downstream ActorPurpose
keyword_opportunity_actorConsumes the topics and entities to identify high-potential, long-tail SEO keywords.
sentiment_intel_actorAnalyzes the articles within each trend to determine the prevailing sentiment (positive, negative, neutral).
content_idea_generator_actorUses the final trends, scores, keywords, and sentiment to generate high-quality, data-backed content ideas.

🛠️ Input Configuration

FieldTypeDescription
pipeline_actorsarray (select)Required. Select the news pipeline actors whose data should be aggregated (e.g., Global Markets Intelligence).
start_datestringOptional. Only include articles published after this date (ISO 8601 format).
end_datestringOptional. Only include articles published before this date (ISO 8601 format).
runTestModebooleanIf checked, the LLM analysis step is bypassed, and mock data is used for clustering/scoring (for development/cost saving).

🧱 Output Example

The actor outputs a list of aggregated trends, structured as follows:

[
{
"topic": "AI Regulation",
"trend_score": 87,
"category": "artificial_intelligence",
"entities": ["EU", "OpenAI", "Regulation", "AI"],
"articles": [
{
"title": "EU AI Act summary for business leaders",
"url": "https://example.com/ai-act",
"source": "TechCrunch",
"published": "2025-10-11T08:00:00Z"
}
// ... more articles
]
}
]