Skip to content

Text mining analysis on wood science literature, focusing on keyword centrality and topic modeling to uncover research trends in the field.

Notifications You must be signed in to change notification settings

pywood21/text_mining_2024

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Wood Science Text Mining Project

Overview

This project involves text mining analysis on wood science literature to uncover research trends through keyword centrality analysis and topic modeling. The analysis focuses on identifying key research areas and trends by analyzing large sets of publications in the wood science field.

Data

The data used for this project consists of metadata collected from leading peer-reviewed wood science journals. The dataset includes fields such as Journal, Year, Volume, Issue, DOI, Authors, Affiliation, Country, Title, Keywords, and Abstract. This metadata was used for analyzing research trends and extracting important keywords from the literature.

Due to ongoing project requirements and data-sharing restrictions, the dataset is not publicly available at this time. Upon project completion and approval from the funding organization, the dataset will be shared.

Key Features

Descriptive Analytics: Provides an overview of the dataset by analyzing publication trends over time, country contributions, and keyword frequencies, giving insights into the distribution and characteristics of the data.
Keyword Centrality: Extracts important keywords from text data and calculates centrality measures such as degree centrality, betweenness centrality, and eigenvector centrality.
Topic Modeling: Utilizes Latent Dirichlet Allocation (LDA) to identify key research topics within the wood science literature.
Dynamic Topic Modeling: Analyzes the evolution of topics over time, identifying how research focus shifts across different periods and providing a temporal dimension to topic trends.
Visualization: Generates network graphs and visualizations of keyword trends and topic distributions.

Contributing

Contributions to improve the project or extend its functionality are welcome. Please create a pull request or submit an issue if you have suggestions or feedback.

Paper Information

This code is associated with the paper "Evolving research themes in six selected wood science journals: insights from text mining and latent dirichlet allocation". The paper has been published in "Journal of Wood Science".

Paper Link

You can access the full text of the research paper related to this project at the link below: https://jwoodscience.springeropen.com/articles/10.1186/s10086-024-02171-z

About

Text mining analysis on wood science literature, focusing on keyword centrality and topic modeling to uncover research trends in the field.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published