Please use this identifier to cite or link to this item:
http://localhost:8080/xmlui/handle/123456789/436| Title: | Text classification using deep learning techniques: a bibliometric analysis and future research directions |
| Authors: | Sarin, Gaurav |
| Keywords: | Data Mining Classification Deep Learning |
| Issue Date: | 2023 |
| Publisher: | Emarald Insight |
| Abstract: | –Text classification is a widely accepted and adopted technique in organizations to mine and analyze unstructured and semi-structured data. With advancement of technological computing, deep learning has become more popular among academicians and professionals to perform mining and analytical operations. In this work, the authors study the research carried out in field of text classification using deep learning techniques to identify gaps and opportunities for doing research. |
| Description: | Text classification (TC) is the process of dividing a specific text into organized groups from an unstructured data set by assigning labels to various text units. It is one of the classical problems in the natural language processing (NLP) domain. Based on the content, text classifiers use NLP to analyze the text automatically and subsequently determine a suitable set of predefined labels. TC has become a crucial part of businesses due to its ability to get remarkable insight from unstructured data and gradually assist businesses in making rational and comprehensive decisions about their future strategies for a product or a service. Some of the most prominent use cases of TC include sentiment analysis, which is a handy tool for understanding the polarity of a text. It is helpful to businesses in familiarizing themselves with the perception of customers about their brand or a specific product. Language detection is another application of TC that helps in detecting the language of a given text. Businesses that have a user base across the globe use language detection to help them with their requests. |
| URI: | http://localhost:8080/xmlui/handle/123456789/436 |
| Appears in Collections: | PGDM |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.