Sentiment Analysis Demo

With the Content Analysis AI API, you can determine the sentiment load of a paragraph or text document. This AI model combines NLP and ML techniques to assign weighted sentiment scores to a text document. This way, the sentences of a text document and the text document as a whole can be characterized by their polarity, a measure that summarizes the overall emotional charge:


A text sentiment metric summarizing the overall emotional charge of a sentence or a document. The polarity of a text sentence or document takes a value in the range [-1, +1]. Large negative values indicate a strong negative emotional charge, and conversely, large positive values indicate a strong positive emotional charge. Values close to zero indicate an overall neutral emotional charge.

Polarity is a quantitative metric, resulting from the combination of the following two emotional characteristics:

  • Valence: the emotional value, how enjoyable a stimulus is; ranges from pleasant / happy (+1) to unpleasant / unhappy (-1). The valence is the base variable for estimating the overall polarity charge (positive, neutral or negative).
  • Arousal: the psychological state of being awoken. It ranges from calm (0.0) to excited (1.0). The arousal works as a catalyzer of the base stimulus provided by the valence, reinforcing the overall polarity charge when the arousal is high and suppressing it when the arousal is low.

The Valence / Arousal relationship could be displayed in a circumplex model as a function of the valence’s emotional charge and the arousal’s intensity. Words in the lexicons could be displayed in a two-dimensional affective space. The following figures depict some examples:


Try the API for Yourself with Our Demo

  1. Enter text in the box
  2. Click “Analyze”
  3. Evaluate the total scores and the scores for each sentence

Valid for English and Spanish text

Sherpa Europe, S.L. (Sherpa) accepts no liability for the content of this information, or for the consequences of any actions taken on the basis of the information provided. Anyone who receives this information are cautioned to consider that its contents are unaudited and that it may contain inaccurate, incomplete or summarized information, which may be change without notice. This information is confidential and its contents may not be totally or partially disclosed or reproduced, without the prior written consent of Sherpa. By allowing you access to the aforementioned information we shall have no liability, duty or obligation of any kind to you.