Skip to content

Fetch meaningcloud sentence sentiment

NLP • text • 3rd party API • integration • model

Analyze sentence and entity sentiments in a text with MeaningCloud.

Each original text will be separated into individual sentences (one per row) in the resulting dataset. For each sentence an overall sentiment score will be calculated. Additionally, for each of five sentiment polarity levels (see below), any entities about which the respective sentiment has been expressed will be collected in a corresponding list.

API integration

To use this step your team needs to have the Meaning Cloud integration configured in Graphext. The corresponding credentials are required to connect to a third-party API. See our help center for details on how to configure your team's integrations.

To enable the Meaning Cloud integration in particular you will need access to Meaning Cloud's NLP service. Follow the instructions here to create the required API key.

Usage

The following are the step's expected inputs and outputs and their specific types.

Step signature
fetch_meaningCloud_sentence_sentiment(
    text_column: text,
    lang_column: category, 
    {
        "param": value
    }
) -> (ds_out: dataset)

where the object {"param": value} is optional in most cases and if present may contain any of the parameters described in the corresponding section below.

Example

Without explicitly limiting the number of requests per second (which may depend on your MeaningCloud subscription), simply use:

Example call (in recipe editor)
fetch_meaningCloud_sentence_sentiment(ds.text_column, ds.lang) -> (ds_out)

Inputs

text_column: column:text

lang_column: column:category

Outputs

ds_out: dataset

The new dataset will have the following columns:

  • original_index: index of the original text row a sentence was extracted from
  • sentence: the sentence extracted from the original text.
  • lang: identifier of the language of the sentence.
  • sentiment: sentiment polarity found (or not found) in the sentence, see here
  • ent_sent_PP: names of the entities detected with strong positive sentiment
  • ent_sent_P: names of the entities detected with positive sentiment
  • ent_sent_NONE: names of the entities detected without sentiment
  • ent_sent_NEU: names of the entities detected with neutral sentiment
  • ent_sent_N: names of the entities detected with negative sentiment
  • ent_sent_NN: names of the entities detected with strong negative sentiment.

Parameters

requests_per_second: number = 2

Request per Second.

integration: string