Keboola App

Our Keboola app makes it easy to use our General API in Keboola Connection, a cloud ETL.

The app can be used to analyze any text, but the standard models are optimized for three domains: news articles, hospitality customer care and transportation customer care. If used in other areas, the obtained results will not be as good as they could be. In order to ensure the best possible outcome for your domain, we will be happy to provide you with a customized model. We offer a basic customization for free. Contact us at info@geneea.com.

Output Tables

When you run the app, it creates the following tables:

  • analysis-result-documents – document-level results

  • analysis-result-entities – entity-level results

  • analysis-result-relations – contains relations and attributes found

  • analysis-result-sentences – contains information about individual sentences

analysis-result-documents table

The analysis-result-documents table contains document-level results in the following columns:

  • all id columns from the input table (used as primary keys)

  • language – detected language of the document, as ISO 639-1 language code

  • sentimentValue – detected sentiment of the document (a decimal number between -1 and 1)

  • sentimentPolarity – detected sentiment of the document (1, 0 or -1)

  • sentimentLabel – sentiment of the document as a label (positive, neutral or negative)

  • usedChars – the number of characters used by this document

analysis-result-entities table

The analysis-result-entities table contains entity-level results has the following columns:

  • all id columns from the input table

  • type – type of the found entity, e.g. person, organization or tag

  • text – disambiguated and standardized form of the entity, e.g. John Smith, Keboola, safe carseat

Notes:

  • There can be multiple rows per one document. All columns are part of the primary key.

  • The table also contains topic tags, marked as tag in the type field.

  • For some entities, we perform ontology expansion. For example, when the text mentions beer, the table will contain multiple entities: beer, alcoholic drink, drink. The exact set is domain and work-flow dependent).

analysis-result-relations table

The analysis-result-relations table contains relations and attributes found in the text. For example, good in a good pizza or the pizza is good is an attribute of pizza, while eat in John ate a pizza is a relation between John and pizza.

The table has the following columns:

  • all id columns from the input table

  • typeATTR for an attribute, VERB for a relation

  • name `` – the standard form of the relation

  • negatedtrue for negated relations, false otherwise

  • subject – the subject of the relation or target of the attribute

  • object – the object of the relation, if any

  • subjectType – when the subject is an entity, its type (e.g. organization, food)

  • objectType – when the object is an entity, its type

  • subjectUid

  • objectUid

  • sentimentValue – average detected sentiment of the sentences with this relation (a decimal number between -1 and 1)

  • sentimentPolarity – polarity of sentimentValue (1, 0 or -1)

  • sentimentLabelsentimentValue expressed as a label (positive, neutral or negative)

For I ordered a good pizza., the table will contain the following rows

type

name

negated

subject

object

subjectType

objectType

subjectUid

objectUid

sentimentValue

sentimentPolarity

sentimentLabel

VERB

order

false

I

pizza

food

XYZ-17

0.1

1

positive

ATTR

good

false

pizza

food

XYZ-17

0.8

1

positive

There can be multiple relations per one document.

analysis-result-sentences table

The analysis-result-sentences table containing information about individual sentences in the documents. These results are in beta.

  • all id columns from the input table

  • index – a zero-based index of the sentence in the document

  • text – text of the sentence

  • sentimentValue – detected sentiment of the sentence (a decimal number between -1 and 1)

  • sentimentPolarity – detected sentiment of the sentence (1, 0 or -1)

  • sentimentLabel – sentiment of the sentence as a label (positive, neutral or negative)