Stocktwits Sentiment & Retail Flow Analyzer

Turn Stocktwits-style message datasets into ticker sentiment shifts, retail attention, volume breakouts and deterministic watch signals.

Why use this Actor

Stocktwits messages are easy to collect, but researchers need recurring ticker-level intelligence about sentiment shifts, attention breakouts and retail-flow changes rather than another raw message feed.

Key features

• Buyer-native inputs aligned to stocktwits sentiment.
• Predictable structured output in the default Apify Dataset.
• Pay Per Event pricing tied to measurable result rows or reports.
• Optional MCP connector delivery for downstream automation and AI agents.

Quick start

Start with this working example and replace the target values with your own:

{
  "currentItems": [
    {
      "id": "m1",
      "symbol": "NVDA",
      "sentiment": "Bullish",
      "body": "NVDA breakout and strong upside, bullish long setup",
      "likes": 12,
      "replies": 3
    },
    {
      "id": "m2",
      "symbol": "NVDA",
      "sentiment": "Bullish",
      "body": "NVDA momentum",
      "likes": 8
    },
    {
      "id": "m3",
      "symbol": "TSLA",
      "sentiment": "Bearish",
      "body": "TSLA downside risk and bearish breakdown, short pressure",
      "likes": 10,
      "replies": 2
    },
    {
      "id": "m4",
      "symbol": "AAPL",
      "sentiment": "Bullish",
      "body": "AAPL constructive",
      "likes": 2
    }
  ],
  "previousItems": [
    {
      "id": "p1",
      "symbol": "NVDA",
      "sentiment": "Bearish",
      "body": "NVDA bearish",
      "likes": 3
    },
    {
      "id": "p2",
      "symbol": "TSLA",
      "sentiment": "Bullish",
      "body": "TSLA bullish",
      "likes": 4
    }
  ],
  "watchTickers": [
    "NVDA"
  ]
}

The Actor writes structured results to the default Apify Dataset and can be used from the Store, API, schedules, Tasks, automations and MCP-compatible AI workflows.

Input

• currentItems — Current message rows: Current Stocktwits or normalized market-message rows.
• currentDatasetId — Current Apify Dataset ID: Optional Apify Dataset with current messages.
• previousDatasetId — Previous Apify Dataset ID: Optional prior Apify Dataset.
• watchTickers — Watch tickers: Tickers to prioritize in agent actions.
• maxItems — Maximum input rows: Maximum number of input rows loaded and analyzed in this run.

All integration and advanced analysis fields are optional. The default example is intentionally runnable without configuring MCP or a previous-run baseline.

Output

The Dataset exposes predictable machine-readable output. Representative fields include results, report.

Pricing

This Actor uses Pay Per Event. The current factory base price is $0.010000 per result event. The Apify Store remains the source of truth for the price and plan/tier details shown to the buyer.

Use cases

• Run the buyer-ready workflows exposed as Apify Tasks without preparing a custom integration first.
• Use the Actor from API or schedules for recurring collection, comparison or monitoring.
• Feed the structured Dataset output into spreadsheets, databases, automations or AI agents.
• Compare repeat runs when the product supports snapshots or previous-run inputs.

Automation and AI

Use the same Actor through Apify API, schedules, public Tasks and the Apify MCP server. Outputs are structured for downstream workflows and AI agents rather than requiring manual copy/paste.

Limitations

• Public websites and upstream APIs can change markup, access rules, rate limits or field availability without notice.
• Fields that are not publicly available are returned as unavailable or omitted rather than fabricated.
• Analytical outputs depend on the quality and coverage of the supplied or collected source data.
• Treat marketplace, reputation, workforce, safety or commercial signals as decision support and validate material decisions against the underlying source evidence.

Detailed documentation

Detailed documentation

Why use this Actor

Use this Actor when raw upstream records are not enough and you need a compact, repeatable intelligence layer with deterministic change signals.

Key features

The product normalizes public upstream data, compares optional previous snapshots, aggregates decision-relevant signals, writes one compact report to the Dataset, and stores a reusable snapshot in the Key-Value Store.

Example

Run the default example input from the Actor console. It uses a small synthetic current/previous sample so the output shows change detection, aggregated scores, and agentAction without requiring credentials.

Use cases

Scheduled monitoring, research dashboards, AI-agent tools, data pipelines, webhook workflows, and analyst review queues.

Pricing

Pay per primary intelligence result. One run produces one decision-ready report; pricing is tied to the analytical outcome rather than charging separately for every derived table inside the report.

Limitations

The Actor analyzes the supplied public-data sample. Coverage depends on upstream data completeness, and derived scores describe observed patterns rather than guaranteeing real-world outcomes.

Turn Stocktwits-style message datasets into ticker-level sentiment and attention intelligence. This Actor is not another social scraper. It is designed to sit downstream from a Stocktwits data source, compare periods, and identify which symbols are gaining attention, changing sentiment, or showing unusual message-volume behavior.

What it does

Provide current messages directly or select an Apify Dataset. Add a previous dataset when you want period-over-period intelligence. The Actor normalizes common ticker, sentiment, message and engagement fields, then aggregates them by symbol.

For each ticker it calculates message count, bullish and bearish label counts, a normalized sentiment index, mention share, engagement, mention growth, sentiment shift and a deterministic breakout score. It also identifies sentiment reversals and attention breakouts.

Intelligence produced

• bullish versus bearish pressure by ticker;
• prior-period sentiment change;
• mention growth and attention share;
• engagement change;
• breakout scoring based on attention, sentiment movement and volume growth;
• watchlist prioritization;
• deterministic actions such as SENTIMENT_REVERSAL, BULLISH_BREAKOUT, BEARISH_BREAKOUT, VOLUME_BREAKOUT, WATCHLIST_REVIEW and MONITOR;
• reusable normalized snapshots for recurring Tasks.

Input flexibility

The Actor accepts currentItems or currentDatasetId, plus optional previous rows or a previous Dataset. It recognizes common fields such as symbol, ticker, symbols, sentiment, body, text, likes, replies, and related aliases.

When an upstream source already supplies bullish/bearish labels, those labels are used. When no label exists, a deliberately conservative lexical fallback may classify only strongly directional messages; weak text stays UNLABELED rather than being forced into a sentiment bucket.

Why this is different

A Stocktwits scraper solves extraction. This Actor solves the next problem: deciding what changed across a market-message batch. The primary output is one compact intelligence report rather than thousands of raw messages. That is useful for scheduled monitoring, dashboards, AI-agent tools, research notebooks, webhook alerts and market-news workflows.

Responsible interpretation

Retail-message sentiment can be noisy, coordinated, ironic, delayed or unrelated to future price movement. sentimentIndex, breakoutScore and agentAction describe patterns in the supplied public-message sample. They do not predict returns, certify market manipulation or constitute investment advice.

Automation

Run the Actor after your Stocktwits data-collection Task, pass the newest Dataset as current input and the prior Dataset as baseline, then route the single report to Slack, Sheets, a database, an AI agent or your own alerting logic.