Impact of convolutional neural network and FastText embedding on text classification

Efficient word representation techniques (word embeddings) with modern machine learning models have shown reasonable improvement on automatic text classification tasks. However, the effectiveness of such techniques has not been evaluated yet in terms of insufficient word vector representation for tr...

Full description

Saved in:
Bibliographic Details
Published inMultimedia tools and applications Vol. 82; no. 4; pp. 5569 - 5585
Main Authors Umer, Muhammad, Imtiaz, Zainab, Ahmad, Muhammad, Nappi, Michele, Medaglia, Carlo, Choi, Gyu Sang, Mehmood, Arif
Format Journal Article
LanguageEnglish
Published New York Springer US 01.02.2023
Springer Nature B.V
Subjects
1178: Pattern Recognition for Adaptive User Interfaces
Artificial intelligence
Artificial neural networks
Automatic classification
Benchmarks
Classification
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Datasets
Deep learning
Embedding
Experimentation
Experiments
Image analysis
Machine learning
Multimedia
Multimedia Information Systems
Natural language
Neural networks
Object recognition
Pattern analysis
Pattern recognition
Regression analysis
Representations
Special Purpose and Application-Based Systems
Text categorization
Text mining
Deep learning
Natural language processing
Convolutional Neural Network (CNN)
FastText
Online AccessGet full text

Cover

More Information
Summary:Efficient word representation techniques (word embeddings) with modern machine learning models have shown reasonable improvement on automatic text classification tasks. However, the effectiveness of such techniques has not been evaluated yet in terms of insufficient word vector representation for training. Convolutional Neural Network has achieved significant results in pattern recognition, image analysis, and text classification. This study investigates the application of the CNN model on text classification problems by experimentation and analysis. We trained our classification model with a prominent word embedding generation model, Fast Text on publically available datasets, six benchmark datasets including Ag News, Amazon Full and Polarity, Yahoo Question Answer, Yelp Full, and Polarity. Furthermore, the proposed model has been tested on the Twitter US airlines non-benchmark dataset as well. The analysis indicates that using Fast Text as word embedding is a very promising approach.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-022-13459-x