Название: Extracting Knowledge From Opinion Mining
Автор: Rashmi Agrawal, Neha Gupta
Издательство: IGI Global
Серия: Advances in Data Mining and Database Management
Год: 2018
Страниц: 375
Язык: английский
Формат: pdf (true)
Размер: 13.1 MB

Data mining techniques are commonly used to extract meaningful information from the web, such as data from web documents, website usage logs, and hyperlinks. Building on this, modern organizations are focusing on running and improving their business methods and returns by using opinion mining.

In this book, through introducing the Deep Learning and relation between Deep Learning (DL) and Artificial Intelligence (AI), and especially Machine Learning (ML), the authors discuss machine learning and deep learning techniques, the literature focuses on applied deep learning techniques for extracting opinions. It can be found that opinion mining without using deep learning is not meaningful. In this way, authors mention the history of deep learning and appearance of it and some important and useful deep learning algorithms for opinion mining; learning methods and customized deep learning techniques for opinion mining will also be described to understand how these algorithms and techniques are used as an applicable solution. Future trends of deep learning in opinion mining are introduced through some clues about the applications and future usages of deep learning and opinion mining and how intelligent agents develop automatic deep learning.

Extracting Knowledge From Opinion Mining is an essential resource that presents detailed information on web mining, business intelligence through opinion mining, and how to effectively use knowledge retrieved through mining operations. While highlighting relevant topics, including the differences between ontology-based opinion mining and feature-based opinion mining, this book is an ideal reference source for information technology professionals within research or business settings, graduate and post-graduate students, as well as scholars.

Contents: