Neural Network Approach for Emotional Recognition in Text
Journal Title: Бионика интеллекта - Year 2019, Vol 1, Issue 92
Abstract
The article is devoted to one of the most popular trends in the field of IT today - natural language processing, in particular, the extraction of emotions from the text using the neural network approach. The main task was to solve the problem of the high costs of time and human resources for companies to receive feedback from users and process emotional reactions of the second one. That to decide the task it was necessary to make modelling and learn neural network using own architecture based on the backpropagation algorithm that to recognize the emotional component in the text.The emotional component of reviews was used as a metric for evaluating user reactions. It was decided to work with five types of emotions that will help to provide better results. The neural network architecture consists of interconnected layers: embedding, bidirectional LSTM, pooling, dropout layers and two dense layers. For the neural network learning was selected an open dataset consisted of 47,288-tagged posts from Twitter. As a result, the F-measure on the test dataset was 0.62 and which is a worthy indicator in comparison with large business solutions.
Authors and Affiliations
Дмитро Назаренко, Ірина Афанас'єва, Наталія Голян
Keywords
Related Articles
- EP ID EP665922
- DOI -
- Views 112
- Downloads 0
Метод порівняння текстово-графічних фрагментів в електронних документах за гібридним критерієм
Розглянуто метод порівняння текстово-графічних фрагментів в електронних документах за гібридним критерієм. Цей метод дозволяє визначати інтегроване значення подібності між запитом, пов’язаним з зображенням в запиті, та т...
The Q# programming language investigation
This work is the investigation of the current state of the existing tools for quantum computing, especially the Q# programming language as the most developed tool for this nowadays. Since quantum computing is one of the...
Розробка інформаційної технології інтелектуального аналізу фактографічної інформації
З швидким розвитком технологій — інформацію розглядають як один з основних ресурсів розвитку спільноти, а інформаційні системи та технології – як знаряддя удосконалення продуктивності праці та ефективності роботи особово...
Fuzzy clustering of data arrays based on the evolutionary method of cat swarm optimization
The problem of fuzzy clustering of an array of observations based on a fuzzy probabilistic approach, based on the algorithm of fuzzy C-means, reformulated into the problem of unconditional multi-extremal optimization, is...
Copyright Protection Using Blockchain
This article examines the potential and limitations of blockchain technology and blockchain-based smart contracts in relation to copyright. Copyright has long been enforced through technological means, specifically Digit...