This post is also available in: heעברית (Hebrew)

Sentiment analysis is the interpretation and classification of emotions (positive, negative and neutral) within text data. These tools allow businesses to identify customer sentiment toward products, brands or services in online feedback. Sentiment in conflict zones can be analyzed through social media texts.

While sentiment analysis has been prevalent for well over a decade, the most common form of sentiment analysis today involves evaluating whether a document’s sentiment is overall more positive than negative. This type of analysis, based on hard-to-maintain sentiment word lists, is overly-simplistic, as it fails to address nuanced comments. 

A new deep learning model will analyze the sentiment of multiple concepts within the same text-based document. The model was unveiled by Luminoso, which automatically turns unstructured text data into business-critical and other insights.

According to aithority.com, the technology will turn any text-based document into a nuanced analysis of the author’s sentiment. The new deep learning model understands documents using multiple layers of attention, a mechanism that identifies which words are relevant to get context around a specific concept as expressed by a word or phrase. This model is capable of identifying the author’s sentiment for each individual concept they’ve written about, as opposed to providing an analysis of the overall sentiment of the document.

Using Concept-Level Sentiment, users will be able to effectively analyze mixed feedback.

Uncovering negative comments in overwhelmingly positive open-ended survey responses is critical for better understanding customers and employees. The technology enables users to quickly identify and understand “buried” feedback, such as negative points in an overwhelmingly positive HR survey.