What is Corporate Reputation?

This API provides a semantic tagging of multilingual content for Corporate Reputation analysis purposes.

It applies a Corporate Reputation model based on a set of reputational dimensions (e.g., innovation, social responsibility) and, inside each of them, an array of variables that influence an organization’s reputation.

The API receives a piece of content (e.g., tweet, news article) and analyzes it to identify what organizations are mentioned, related to which reputational variables and the polarity (positive, negative, neutral) of what is being said.

This result can later be used to calculate aggregations, identify trends and elaborate reports and dashboards.

First of all, the text provided will be fragmented into paragraphs or phrases (depending the detail needed for each case) in order to give a complete and detailed report about the reputational information obtained for each fragment.

For each fragment, two different analyses will be carried out:

  • Each fragment will be analyzed according to pre-established categories defined in a reputation model for business using automatic text classification. The algorithm used combines statistic classification with rule-based filtering, which allows to obtain a high degree of precision for very different environments.
  • Each fragment will be analyzed to extract the different named entities (people and organizations) using complex natural language processing techniques and to determine if each detected entity expresses a positive/negative/neutral sentiment; to do this, the local polarity of the different mentions of each entity will be identified and the relationship between them evaluated, resulting in a global polarity value for each entity in the whole fragment.

Once these two analyses are done, they will be combined and statistical methods will be applied to obtain the reputation associated in each fragment to each named entity detected for each category defined in the reputation model.