• July 28, 2020

Luminoso Launches Concept-Level Sentiment

Luminoso, a text analytics provider, today unveiled Concept-Level Sentiment, a deep learning model within its Luminoso Daylight solution for analyzing sentiment of multiple concepts within the same text-based document.

"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," said Adam Carte, CEO of Luminoso, in a statement. "This type of analysis is overly simplistic, as it fails to address nuanced comments, such as customers explaining what they like and dislike about a product or employee feedback about a company's strengths and weaknesses. With Concept-Level Sentiment in Luminoso Daylight, businesses across industries will be able to upload any text-based document and quickly receive a nuanced analysis of the author's sentiment."

Luminoso's 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 can identify the author's sentiment for each individual concept, as opposed to providing an analysis of the overall sentiment of the document.

"Other companies have attempted to analyze sentiment at the concept level, but they use unreliable, hard-to-maintain sentiment word lists," said Joanna Lowry-Duda, a research scientist at Luminoso, in a statement. "With Luminoso, customers benefit from our deep learning model that automatically creates a complex representation of the concept and its context to find sentiment across any industry."

With Luminoso, users can analyze the sentiment of concepts, natively in 15 languages.

CRM Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues

Related Articles

Luminoso Launches QuickLearn 2.0 Text Analytics

QuickLearn 2.0 reduces bias in AI-powered text analysis for more accurate insights.