github.com/CAPCOMIN/UprrWebApp ↗
Research on User Profile and Resource Recommendation of Online Learning Platform Based on Collaborative Filtering Algorithm
An animated visualization of CAPCOMIN/UprrWebApp's Git history from March 2022 to May 2022, built by 2 contributors. The codebase reached 509 lines, mostly HTML. The video runs 17 seconds.
Render your own repo
Turn any GitHub repository into a video like this — free sample in seconds.
Open this visualization on its own page →
Language
HTML
Contributors
2
Lines of Code
509
From
2022-03-01
To
2022-05-05
Advertisement
About CAPCOMIN/UprrWebApp
UPRR Web App is a research platform for analyzing user profiles and recommending learning resources on online education platforms. Built with Python Flask, the application implements collaborative filtering algorithms and clustering analysis on user activity logs to generate personalized course recommendations and visual user profiles. The system is designed to help educators understand resource utilization patterns and improve course quality through data-driven insights.
The platform consists of three main modules: a recommendation engine that suggests courses to individual students based on collaborative filtering, a search function for finding detailed student enrollment information and course demographics, and a user portrait generator that creates visual word clouds representing each student's learning characteristics. The user portrait system processes course features through TF-IDF text analysis and word segmentation to identify and display the most relevant characteristics of each learner's educational profile.
The project uses sample data sourced and restructured from MoocData, an online learning platform dataset repository, containing user IDs, course information, and interaction logs. Deployment instructions cover both local development environments running on Flask's built-in server and production deployments using uWSGI on remote servers. The application generates recommendation metadata and supplementary data files that users can access for deeper analysis of recommendation results.
Advertisement