https://github.com/sam9111/recommender-system
https://github.com/sam9111/recommender-system
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/sam9111/recommender-system
- Owner: sam9111
- Created: 2023-04-22T18:26:23.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-10T18:50:51.000Z (over 1 year ago)
- Last Synced: 2025-04-23T00:45:23.807Z (about 1 month ago)
- Language: Python
- Size: 27.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
The project presents a novel approach to topic modeling specifically for the Tamil language using BERTopic. This method adapts standard procedures to better handle the intricacies of Tamil, addressing challenges in tokenization, embedding, and topic representation. It surpasses previous methods, like LDA, in identifying relevant Tamil text topics. Additionally, the project introduces a Clustered Semantic Recommender system, designed for recommending articles. This system, unique in not requiring user data, is particularly advantageous for content-based recommendation in online Tamil newspapers. It effectively circumvents the cold start problem common in recommender systems.