Analyze each sentence of a text
Analyzes written communications like tweets, emails, documents, transcripts, and book passages for the author's tone. There are 7 tones (in 2 categories) that can be identified:
Emotion: Anger, Fear, Joy, Sadness
Language: Analytical, Confident*, Tentative
Note that the Confident tone is an estimation of the speaker/writer's confidence in his own words, not a confidence score as we usually encounter in statistical contexts. For example, "I am positive he is guilty" would be rated as Confident, whereas "I think he did it" would not; the latter may even be rated as Tentative*.
This activity has the following limitations:
- You may submit at most 1000 sentences to be analyzed collectively for Document Tone.
- You may submit at most 100 sentences to be analyzed individually for Sentence Tone.
- DisplayName - The display name of the activity.
- APIKey - The API key generated for your Tone Analyzer instance on IBM Cloud
- URL - The URL generated for your Tone Analyzer instance on IBM Cloud
- Text - The text to analyze for tone
- InLanguage - The language of the inputted text
- OutLanguage - The language in which the outputted tones are written
- Private - If selected, the values of variables and arguments are no longer logged at Verbose level.
- Document Tone - The tone most prominent in the submitted text as a whole. Given as a
- ToneName - The name of the tone
- Confidence - A value between 0 and 1 indicating the Tone Analyzer's confidence that the tone selected accurately describes the text
- Sentence Tones - An
Array<SentenceTone>variable holding analyses of each individual sentence in the submitted text.
- SentenceNumber - The index (starting at 0) at which the described sentence appears in the text.
- Text - The isolated text of the sentence
- ToneName - The name of the tone found in this sentence
- Confidence - A value between 0 and 1 indicating the Tone Analyzer's confidence that the tone selected accurately describes the sentence
Updated 3 months ago