On this page

Sentiment Analysis

Scores the tone of text the pipeline already produced.

The sentiment node scores the tone of text your pipeline has already produced. It does not look at the media itself — it has a single text input port that accepts any text type, so you can connect Tika document content, OCR text, a caption, or a VLM / LLM answer to it. The node labels whatever arrives positive, neutral or negative, with a confidence score and a signed polarity value you can sort and filter on.

German and English are handled by dedicated models — German with german-sentiment-bert, English with a RoBERTa model trained on social text — rather than one generic multilingual model, because a language specialist is measurably better on its own language. Both run behind a small HTTP sidecar, so the node stays a pure client and needs no model runtime of its own.

Kind

sentiment

Applies to

Any asset (the text comes from an upstream node, not from the media)

Input ports

text — accepts any text type, so a document body, an OCR result, a caption or a transcript can all be wired into it

Output ports

label (String), score (Number), result (the structure below)

Languages

German and English, detected automatically; other languages fall back to a multilingual model

Requirements

A running sentiment sidecar (/v1/sentiment). CPU is sufficient; GPU optional

Persists to

asset_json_comp — one row per text source, discriminated by the port the text was connected from

What it produces

{
  "label": "NEGATIVE",
  "score": 0.87,
  "polarity": -0.81,
  "scores": { "positive": 0.06, "neutral": 0.07, "negative": 0.87 },
  "lang": "de",
  "model": "oliverguhr/german-sentiment-bert",
  "source": { "node": "tika", "port": "content" },
  "textChars": 4211,
  "chunks": 12
}

polarity is the positive share minus the negative share, so it runs from -1 (wholly negative) to +1 (wholly positive) with neutral text near zero. It is the value to sort or threshold on when you want "the most negative documents first".

Long text is handled automatically: the sidecar splits it into sentence-aligned chunks, scores each, and combines them weighted by length — so a long complaint is not diluted by a short pleasantry.

Configuration

The Sentiment Analysis settings panel: Sidecar Host
Figure 1. The node’s settings in the pipeline editor

Set these in the panel above, or in the node’s options block in a pipeline definition:

Option Meaning

sentimentHost / sentimentPort

Address of the sentiment sidecar (default localhost:9110)

language

de, en, or auto to detect it per text (default auto)

modelDe / modelEn

Override the sidecar’s German / English model — e.g. a finance-specific German model

maxChars

Upper bound on the text sent for analysis (default 200000)

There is no option naming where the text comes from: the text port accepts any text type, so you draw a connection instead. A PDF pipeline wires Tika's content into it, a scan pipeline wires OCR's text, and a photo pipeline wires captioning's caption. Wanting all three in one pipeline means one sentiment node per source, each with its own row.

Seeing it run

Turn on Debug Mode and every node keeps what it produced, on the card itself. Below is a real run over a German complaint — "Wir haben die Lieferung heute erhalten, aber zwei Kartons waren beschädigt" — at the shipped language: auto.

The sentiment node after a run

The strip lists what each output port carried — label, score, result. The interesting part is in result: the sidecar detected de and routed to the German checkpoint on its own, which is what auto buys you. The same text scored by an English model would be a different number about a sentence it did not understand.

Use Cases

  • Review and feedback triage — surface the most negative documents in an ingest first.

  • Brand and press monitoring — track the tone of coverage across a German and English corpus.

  • Content moderation support — flag strongly negative material for human review.

  • Media library insight — combine with captioning to score the tone of what images and videos depict.

The sidecar is a small FastAPI service; see the sidecars/sentiment directory for how to run it.

Model attribution

The default English model is published under CC-BY-4.0, which permits commercial use but requires attribution. The model actually used is recorded with every result, so it can be surfaced wherever you display sentiment. If your deployment cannot carry that attribution, point modelEn at an Apache-2.0 alternative — the sidecar’s fallback multilingual model is one.

Looking for something else?

All documentation Feature overview