https://github.com/shuyib/pubmed-ke-nlp
Practice project to review skills in text summarization and text mining. Using a data set from NCBI edirect tool to find any trends in research direction in research done in Kenya.
https://github.com/shuyib/pubmed-ke-nlp
data-science machine-learning natural-language-processing nlp python
Last synced: 2 months ago
JSON representation
Practice project to review skills in text summarization and text mining. Using a data set from NCBI edirect tool to find any trends in research direction in research done in Kenya.
- Host: GitHub
- URL: https://github.com/shuyib/pubmed-ke-nlp
- Owner: Shuyib
- License: apache-2.0
- Created: 2021-02-28T07:49:33.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2024-06-17T23:10:52.000Z (about 2 years ago)
- Last Synced: 2025-01-27T09:41:24.810Z (over 1 year ago)
- Topics: data-science, machine-learning, natural-language-processing, nlp, python
- Language: HTML
- Homepage:
- Size: 4.35 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# pubmed-KE-NLP
This is a text mining and text summarization project from 1980 - 2019. The purpose is to see the research topic direction by looking at several publications from Kenyan authors whose publications are in PubMed. Using Natural language processing techniques that is, finding out the most common words from several topics that emerge from titles of the publications using word clouds (Unigrams) and Latent Dirichlet allocation to explore if topic modelling would be help us reveal any insights.
We discovered:
A lot of studies are centered around Malaria, HIV and diarrheal disease. These are the main causes of mortality in Kenya referencing the [CDC Kenya website](https://www.cdc.gov/globalhealth/countries/kenya/pdf/Kenya_Factsheet.pdf) at least from 2018. It was fascinating that whoever replicates this study can confirm this.
In order to run the project using the same requirements, use these commands:
Build docker image
`docker build -t pubmed-ke-nlp .`
Run the Docker image
`docker run -it -p 8888:8888 pubmed-ke-nlp:latest`
References:
* Bibcitation: Free Automatic Citation Maker. MLA, APA + more. (n.d.). Bibcitation. Retrieved November 28, 2021, from https://www.bibcitation.com/.
* Mwangi, K. W., Mainye, N., Ouso, D. O., Esoh, K., Muraya, A. W., Mwangi, C. K., Naitore, C., Karega, P., Kibet-Rono, G., Musundi, S., Mutisya, J., Mwangi, E., Mgawe, C., Miruka, S., & Kibet, C. K. (2021). Open science in Kenya: Where are we? Frontiers in Research Metrics and Analytics, 6. https://doi.org/10.3389/frma.2021.669675
* BioinfoNet. (n.d.). GitHub - BioinfoNet/Data-mining: Data mining to discover trends in Open Science in Kenya. GitHub. Retrieved April 19, 2022, from https://github.com/BioinfoNet/Data-mining
* Chicago Python Users Group. (2017). Data Science Workflows using Docker Containers [Video]. In YouTube. https://youtu.be/oO8n3y23b6M.
* [Datacamp project reference](https://www.datacamp.com/projects/158).
* Grigorev, A. (2021). Machine Learning Bookcamp: Build a portfolio of real-life projects (pp. 34–45). Simon and Schuster.
* Müller, A. C., Guido, S. (2016). Introduction to machine learning with python: A guide for data scientists (pp. 355–362). “O’Reilly Media, Inc.”