The Cloudburst Media Sentiment Engine is a software application that scans or "reads" text and determines whether the sentiment is positive, negative or neutral. It then provides calculations to communicate the results in a variety of intuitive, investor-friendly ways.
The software uses the latest Natural Language Processing technology to detect speech patterns that denote sentiment. For instance, it might scan the phrase "IBM surpasses earnings estimates" and recognize the phrase "surpasses earnings estimates" as something positive.
After scanning the entire article, the net number of positive indicators (i.e. good minus bad) is divided by the number of words in the article and added to the previous value of the Cloudburst Media Sentiment Index to arrive at the index's new value.
The words, phrases and speech patterns recognized by the Cloudburst Media Sentiment Engine are based on proprietary dictionaries developed Cloudburst Analytics. The sentiment engine also creates sub-indexes that measure sentiment by company, GICS sector, GICS industry and news source.