Literature Review

To carry out an effective literature review for the proposed research on document classification and management systems, the following steps have been undertaken

Click Here

Methodology

Methodology Steps

Defining the Scope

The scope of the literature review focuses on studies, articles, and reports related to document classification and management systems, particularly within the manufacturing industry. This includes understanding different methodologies for document classification such as those discussed in "Document Classification for Text Corpora with Multiple Labels" and "Hierarchical Document Classification with Reinforcement Learning". The emphasis will be on both electronic and manual systems, but special attention will be given to electronic document management processes.

Identifying Relevant Sources

Relevant sources have been identified through database searches on platforms such as Google Scholar, IEEE Xplore, and JSTOR. Keywords related to 'document management', 'document classification', 'information management', 'electronic document management systems' and 'manufacturing industry' will be used. The search has been expanded as necessary to include sources that discuss the challenges and potential solutions related to document management. Key sources include "A Survey on Document Management Systems" and "Effective Management of Electronic Documents in the Context of Organizational Knowledge".

Evaluating Sources

Each source has been evaluated for credibility, relevance, and timeliness. Peer-reviewed articles, research reports, and authoritative industry publications have been prioritized. For example, "Document Classification Using Genetic Programming" and "Document Classification Using Support Vector Machines" both provide valuable insights into document classification methods.

Reading and Summarizing

Each source has been read thoroughly and key points have been summarized. This includes the study's purpose, methodology, findings, and implications for the current research. For instance, the findings from "Integration of Document Management Systems with Enterprise Resource Planning" are summarized and its implications for the current research discussed.

Synthesizing Findings

The findings from each source have been synthesized to form a comprehensive understanding of the current state of document classification and management systems in the manufacturing industry. This involves drawing connections between different sources and integrating their findings into a cohesive narrative.

Identifying Gaps

The literature review aims to identify gaps in the current knowledge and practice of document management. These gaps will help guide the research process for the project. For example, the review identifies a lack of research on the integration of artificial intelligence in document management systems, indicating a potential area for future research.

Documenting the Review

The literature review has been documented clearly and succinctly, providing a comprehensive overview of the existing literature on document management systems in the manufacturing industry. This will provide a strong foundation for the proposed research project.

Document Classification

"Document Classification for Text Corpora with Multiple Labels" by P. Li, Y. Liu, and G. Yu
"Hierarchical Document Classification with Reinforcement Learning" by Y. Shen, X. Sun, Y. Yuan, and J. Yang
"Deep Learning for Document Classification: A Comparative Analysis" by F. M. R. Carvalho, V. B. Oliveira, and A. H. F. Laender
“A Survey on Text Classification Algorithms From Text to Predictions” by Andrea Gasparetto, Matteo Marcuzzo, Alessandro Zangari and Andrea Albarelli
"Text Classification Using Artificial Neural Networks" by R. J. Khemchandani and P. C. Saxena
"Feature Selection for Document Classification: A Review" by S. K. Jayanthi and N. Balasubramanian
"Graph-based Document Classification: A Survey" by M. Zhang, Z. Zhang, and W. Yu
"Semi-Supervised Document Classification: A Comprehensive Review" by L. Zhou, S. Huang, and K. Zheng
"Ensemble Methods for Document Classification: A Survey" by C. Zhang, B. Zhang, and X. Chen
"Transfer Learning for Document Classification: A Review" by H. Wu, Y. Zhang, and X. Wang
"Active Learning for Document Classification: A Survey" by J. Chen, Z. Wang, and Y. Liu
"Document Classification using Genetic Programming" by S. Sharma and M. K. Choudhary
"Document Classification Using Support Vector Machines" by M. Saharan and N. Saini

14. "Document Classification Using Naive Bayes Classifier" by R. K. Saha and U. Bhattacharya

Research Hierarchy

Research Relevance

Gaps Identified

Based on the literature review, there are a few potential gaps in the current research

Integration of AI and machine learning

There is limited research on the integration of artificial intelligence and machine learning techniques in document management systems. While some studies have looked at document classification using various machine learning techniques, there doesn't seem to be a comprehensive evaluation of AI-powered document management systems.

Blockchain Technology

The use of blockchain technology for securing document management systems is an emerging trend. However, there are few studies that delve into the benefits and challenges of integrating blockchain technology in document management systems.

Mobile Document Management

Although there are studies on mobile document management, the research on the challenges and opportunities of mobile document management, such as user interface design, mobile security, and offline access, seems to be limited.

Multi-label document classification

While there is research on document classification, there seems to be a gap in studies focusing on multi-label document classification, where a document can belong to multiple categories simultaneously.

Document Classification and Management