Evaluate a Free News Sentiment API核验免费新闻情感分析 API

What “free” must include for a news sentiment API免费新闻情感分析 API 必须说明哪些边界

A zero-dollar signup is only the first filter. The useful question is whether the free response contains both a traceable news record and an interpretable sentiment result. Some plans expose headlines but reserve sentiment for paid access; others score text you submit without supplying any news.

零成本注册只是第一道筛选。真正需要核对的是：免费响应是否同时包含可追溯的新闻记录和可解释的情感结果。有些套餐免费提供标题，却把情感字段放在付费层；另一些接口只分析你提交的文本，并不提供新闻。

Choose the sentiment grain before comparing APIs比较接口前先确定新闻情感评分粒度

“Positive” is incomplete unless the response says what the label describes. One article can be optimistic about an industry, negative for one company, and neutral toward another. Match the scoring unit to the decision your application makes.

仅返回“正面”并不完整，响应还必须说明它在描述什么。一篇报道可能看好整个行业、利空某家公司，同时对另一家公司保持中性。评分单位应与应用实际决策一致。

Choose between bundled sentiment and a two-stage pipeline选择一体化情感接口还是两阶段处理链路

A free news sentiment API can mean three different products: an endpoint that returns licensed news with scores, a classifier that scores text supplied by your application, or a workflow that combines a news feed with a separate model. Choose the architecture before comparing quotas. Otherwise, a generous text-classification allowance may look attractive even though it provides no articles, entity mapping, or publication metadata.

“免费新闻情感分析 API”可能指三种完全不同的产品：直接返回新闻与评分的一体化接口、只分析应用提交文本的分类器，或由新闻数据源与独立模型组成的两阶段链路。比较配额前应先确定架构，否则，一个额度看似充足的文本分类接口，可能既不提供新闻，也不负责实体映射和发布时间管理。

Trace every score back to news evidence让每个情感评分都能追溯到新闻证据

A sentiment number without provenance cannot be audited. For each record, retain the canonical article URL, publisher, publication time, provider ingestion time, language, matched entity or topic, and sentiment output. The three timestamps—publication, ingestion, and request—answer different freshness questions.

没有数据出处的情感数字无法审计。每条记录应保留新闻规范 URL、媒体、发布时间、服务商采集时间、语言、命中的实体或主题以及情感输出。发布时间、采集时间和请求时间分别回答不同的及时性问题。

Validate sentiment quality before trusting the score信任评分前，先验证情感分析质量

A sentiment endpoint can return valid JSON and still produce a poor financial signal. Evaluate it on articles that resemble the application’s real workload, not on a handful of obvious positive and negative headlines. Build a labeled test set with publication timestamps frozen at collection time, and keep the raw text or permitted evidence needed to reproduce each judgment.

情感接口即使返回格式正确的 JSON，也可能形成质量很差的金融信号。验证时应使用与应用真实场景相似的报道，而不是只挑几条明显的利好或利空标题。建议建立人工标注测试集，在采集时固定发布时间，并在许可范围内保留能够复现判断的原文或证据。

Build an evidence matrix for the free tier为免费套餐建立可核验的证据矩阵

Do not compare providers using plan names alone. Capture one documented statement and one observed response for every requirement. If the two disagree, treat the observed schema as a test result—not permission to ignore the contract.

不要只按套餐名称比较服务商。每项要求都应同时记录一条文档说明和一次实际响应。如果二者不一致，应把响应视为测试结果，而不是忽略合同条款的理由。

Normalize a news sentiment response without losing evidence规范化新闻情感响应时不要丢失证据

Keep a provider-neutral record for application logic and retain the provider payload separately where the terms permit. The normalized object below makes article identity, scoring target, timestamps, and scale explicit.

应用逻辑可以使用统一记录；在条款允许时，另行保留服务商原始响应。下面的规范化对象明确区分文章身份、评分对象、时间戳和量表。

from datetime import datetime, timezone

def normalize_news_sentiment(article, provider_name):
    target = article.get("entity") or article.get("topic")
    score = article.get("sentiment_score")

    return {
        "article": {
            "id": article["id"],
            "canonical_url": article["url"],
            "publisher": article["publisher"],
            "published_at": article["published_at"],
            "language": article.get("language"),
        },
        "sentiment": {
            "target": target,
            "label": article.get("sentiment_label"),
            "score": score,
            "scale": article.get("score_scale"),
            "is_missing": score is None,
        },
        "provenance": {
            "provider": provider_name,
            "ingested_at": article.get("ingested_at"),
            "requested_at": datetime.now(timezone.utc).isoformat(),
        },
    }

This is a normalization pattern, not a provider endpoint. Map only documented fields, preserve null values, and keep the provider’s original identifiers so records can be reconciled later.

这是规范化模式，不是真实服务商端点。只映射文档明确说明的字段，保留空值和原始标识，方便后续核对记录。

Turn article sentiment into a defensible time-series signal把文章情感转换成可解释的时间序列信号

Do not average every score returned for a ticker. News volume changes by company and event, syndicated stories can multiply one fact into dozens of rows, and old articles should not influence a current signal forever. Define the aggregation contract before using sentiment in alerts, rankings, or backtests.

不能把某个股票代码下返回的所有评分直接取平均值。不同公司和事件的报道数量差异很大，同一篇通讯社稿件可能被转载成数十条记录，旧报道也不应永久影响当前信号。在将情感用于提醒、排序或回测前，应先明确聚合规则。

Use QVeris to discover the capability, then verify the evidence用 QVeris 发现能力，再核验新闻证据

QVeris helps agents search for capabilities rather than hard-coding a provider name. For this use case, describe the required input and output precisely: topic or entity query, publication-time filters, traceable article metadata, and article- or entity-level sentiment.

QVeris 帮助 Agent 按能力搜索，而不是把服务商名称写死。针对本场景，应准确描述输入输出：主题或实体查询、发布时间筛选、可追溯的新闻元数据，以及文章级或实体级情感。

• Start with the QVeris tool details and search for news retrieval plus sentiment scoring.
• Use the Capability Map to separate news collection from text classification when one tool does not provide both.
• Follow the QVeris documentation to connect the verified capability to an agent workflow.

• 从 QVeris 工具详情开始，搜索新闻检索与情感评分能力。
• 使用 能力地图区分新闻采集和文本分类，处理单一工具无法同时提供两项能力的情况。
• 参考 QVeris 文档，把已核验能力接入 Agent 工作流。

FAQ

Verification sources核验资料