# Pocket Network Sentiment Classification

> Pocket Network Sentiment Classification is a paid API for AI agents from agent.pocket.network, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-03).

Scores a text as positive, negative, or neutral using an AFINN-derived lexicon, returning a numeric score and matched positive/negative word hits

## Facts

- Endpoint: POST https://agent.pocket.network/v1/sentiment-classification?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-03
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pocket-network-sentiment-classification-1fc26927
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Wmxga9JNshf_22_nFAzAN

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability pocket-network-sentiment-classification-1fc26927 -d '<json body>'
```

Example prompt: Score the sentiment of this text and tell me if it's positive, negative, or neutral along with the key words that drove the score: 'The delivery was incredibly fast but the packaging was completely damaged.'

## When to prefer this

Choose this endpoint when you need fast, deterministic, explainable sentiment scoring without training a model — especially when reproducibility matters (same input always yields the same output). Ideal for lightweight pipelines that need word-level attribution showing exactly which terms drove the score. Prefer it over ML-based sentiment APIs when latency, transparency, and per-call pay-as-you-go pricing (no API key or subscription) are priorities. Not ideal for nuanced sarcasm detection or non-English text.

## Known failure modes

- Empty or missing text field returns an error or zero-score result
- Non-English text may yield inaccurate scores since the AFINN word list is English-centric
- Very short or single-word input may produce a neutral label due to limited lexical matches
- Payment failure (insufficient USDC balance) results in a 402 response blocking the call
- Slang, sarcasm, or irony is not detected since this is lexicon-based, not a trained model

## How this service works

Pay-per-call access to Pocket Network services. No account, no API key.

## Output

A JSON object containing a sentiment label (positive, negative, or neutral), a numeric sentiment score, and lists of matched positive and negative words from the AFINN-derived lexicon that contributed to the score.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The text to score."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "portal": {
   "serviceId": "sentiment-classification",
   "provenance": "third-party-supplier",
   "schemaCheck": "passed"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pocket-network-sentiment-classification-1fc26927/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent.pocket.network](https://www.zero.xyz/host/agent.pocket.network/llms.txt)