Open AccessConvolution Neural Network for Text Mining and Natural Language Processing
Author(s) -
Nelly Indriani Widiastuti
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/662/5/052010
Subject(s) - computer science , convolutional neural network , sentiment analysis , representation (politics) , domain (mathematical analysis) , natural language processing , artificial intelligence , process (computing) , convolution (computer science) , information retrieval , artificial neural network , mathematical analysis , mathematics , politics , political science , law , operating system
The objective of this study is to get an overview of the improvements applied in a number of studies and problems that have not been resolved. We have surveyed more than 30 scientific articles obtained from scientific article portals such as Science Direct, IEEE explore, Arxiv, and Google Scholar. Based on this abstract, we obtain similarities and differences based on the problem solved, the pre-processing method for data input, and the approach taken to achieve the goal. The results show that some problems have not been resolved by CNN in the text mining domain and NLP. This happens because CNN is used to solve problems in each case such as sentiment analysis, classification of documents or NLP cases such as entities and their relationships, or semantic representation. CNN that is proficient in image classification has proven its ability to process text. Appropriate data representations and methods have brought that success. However, a number of studies only convey the results they are working on. No one has specifically discussed high computing problems on CNN with consistent and measurable parameters. Thus there are still many studies that use CNN for mining text and NLP are still open to completion