News Recommendation System

About

An internet-based news aggregator, providing hot news scraping on popular news sources, with recommendation feature based on users' preference with the help of Machine Learning.

Chart with Machine Learning module for news topic classification

Chart with Recommendation module to match user preference

Tech stack:

Front end:( React, Node.js, JWT)
- Built a responsive single-page web application for users to browse news (React, Node.js, RPC, SOA, JWT)
Back end:(Python RPC, MongoDB, Redis, RabbitMQ, TF-IDF, NLP)
- Service Oriented, multiple backends serving via JSON RPC
- Implemented a data pipeline which monitors, scrapes and deduplicates news
Machine Learning back end: (Tensorflow, DNN, NLP)
- Designed and built an offline training pipeline for news topic modeling
- Implemented a click event log processor which collects users' click logs, updated a news model for each user
- Deployed an online classifying service for news topic modeling using trained model

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
backend_server		backend_server
common		common
config		config
logger		logger
logs		logs
news_pipeline		news_pipeline
news_recommendation_service		news_recommendation_service
news_topic_modeling_service		news_topic_modeling_service
web-server		web-server
README.md		README.md
chart.jpg		chart.jpg
dump.rdb		dump.rdb
launcher.sh		launcher.sh
news_pipeline_launcher.sh		news_pipeline_launcher.sh
requirements.txt		requirements.txt
with ML topic classification1.png		with ML topic classification1.png
with Recommendation module.png		with Recommendation module.png

zihaowangusa/news-recommendation-system

Folders and files

Latest commit

History

Repository files navigation

News Recommendation System

About

Chart with Machine Learning module for news topic classification

Chart with Recommendation module to match user preference

Tech stack:

About

Resources

Stars

Watchers

Forks

Languages