The social media analytics service has created a neural network that evaluates comments, including profanity and slang. “Olga Stanislavovna” trained on 500 thousand comments, dictionaries, emoji and helps to assess the audience’s loyalty to the brand.
A representative from the developer, LiveDune, spoke about the development of RB.
The neural network was named “Olga Stanislavovna” after LiveDune founder Igor Krasyuk’s teacher.
According to the developers, the neural network has an updated vocabulary of modern Russian slang, which in most cases is used by users in social networks. “Olga Stanislavovna” trained on 500 thousand records, emoji, comments.
“Dictionaries that set the language norm have always lagged behind live speech, but the emergence of such a neural network can help philologists more accurately track language development,” noted philologist Maria Rogozhina. .
The neural network evaluates the comments by categories: positive, negative, neutral. This will help the brand gauge audience loyalty. LiveDune reported that 6,000 accounts use the service, mainly representing tourism, automotive business and markets.
“The neural network monitors the possible negative and the employee, having filtered the answer, can solve it and return the customer’s loyalty”, explained Olesya Jig, manager of LiveDune CSM.
Author:
Kirill Bilyk
Source: RB
I am Bret Jackson, a professional journalist and author for Gadget Onus, where I specialize in writing about the gaming industry. With over 6 years of experience in my field, I have built up an extensive portfolio that ranges from reviews to interviews with top figures within the industry. My work has been featured on various news sites, providing readers with insightful analysis regarding the current state of gaming culture.
