- Group project for 2190513 Data Science, Year 2 Semester 1
- Objective: to analyse, visualise, and predict data of research papers from Scopus
- To run the demo, please download the cleaned dataset first, then run
python -m streamlit run streamlit_app.py. You can also visit the website here.
- 6638031621 Jitawat Pinyosnit (@FaDeAWAYut)
- 6638139821 Pemika Chantaraseno (@amukamu2)
- 6638217021 Vinita Jungwiwattanaporn (@vinitian)
- 6638222121 Sasiras Yodruangsa (@Sasirasys)
- It must include the following three components:
- Data module: Data collection, data preparation, and data analysis.
- AI module: An AI model implementation, such as text classification, clustering, etc.
- Visualization module: Visualization using a tool like Streamlit or other BI dashboard tools.
- The primary data requirement is to focus on analyzing the provided data from Scopus.
- Each group must also use web scraping or an API to add at least 1,000 additional papers from external sources, such as Scopus, DBLP, or Google Scholar.
- Incorporating additional data sources, such as author locations or affiliation coordinates, will enhance the project’s appeal and may earn extra points.
- Data collection
- Data cleaning
- Data analysis
- Data visualisation
- AI model
- Slides & presentation video