Opportunity Capture

alphaear-sentiment

Vor 45 Tagen aktualisiertSetup in <1 Min.

Überblick

AlphaEar Sentiment provides domain-specific sentiment analysis for financial texts, offering both a high-speed local FinBERT pipeline and an agent-driven LLM analysis mode for deeper reasoning.

AlphaEar Sentiment provides domain-specific sentiment analysis for financial texts, offering both a high-speed local FinBERT pipeline and an agent-driven LLM analysis mode for deeper reasoning. Key features include analyze_sentiment(text) which returns {score, label, reason} with a -1.0 to 1.0 score range, batch_update_news_sentiment(source, limit) for bulk processing of unanalyzed items, and update_single_news_sentiment(id, score, reason) to persist manual LLM judgments. Use FinBERT for scalable, low-latency scoring across news feeds and databases; use the LLM prompt workflow when nuance, contextual reasoning, or ambiguous cases require human-like interpretation. Typical use cases are news monitoring, trading signal generation, research, and compliance review. Core advantages: finance-tuned models, integrated database update helpers, and a clear scoring guide; dependencies include torch, transformers, and sqlite3.

Skill.md

So funktioniert diese Skill

SKILL.mdALPHIO / VERIFIZIERT

AlphaEar Sentiment Skill

Overview

This skill provides sentiment analysis capabilities tailored for financial texts, supporting both FinBERT (local model) and LLM-based analysis modes.

Capabilities

1. Analyze Sentiment (FinBERT / Local)

Use scripts/sentiment_tools.py for high-speed, local sentiment analysis using FinBERT.

Key Methods:

analyze_sentiment(text): Get sentiment score and label using localized FinBERT model.
- Returns: {'score': float, 'label': str, 'reason': str}.
- Score Range: -1.0 (Negative) to 1.0 (Positive).
batch_update_news_sentiment(source, limit): Batch process unanalyzed news in the database (FinBERT only).

2. Analyze Sentiment (LLM / Agentic)

For higher accuracy or reasoning capabilities, YOU (the Agent) should perform the analysis using the Prompt below, calling the LLM directly, and then update the database if necessary.

Sentiment Analysis Prompt

Use this prompt to analyze financial texts if the local tool is insufficient or if reasoning is required.

请分析以下金融/新闻文本的情绪极性。返回严格的 JSON 格式: {"score": <float: -1.0到1.0>, "label": "<positive/negative/neutral>", "reason": "<简短理由>"}

文本: {text}

Scoring Guide:

Positive (0.1 to 1.0): Optimistic news, profit growth, policy support, etc.
Negative (-1.0 to -0.1): Losses, sanctions, price drops, pessimism.
Neutral (-0.1 to 0.1): Factual reporting, sideways movement, ambiguous impact.