Latent semantic indexing collaborative filtering recommendation system
The recent increase in the amount of information available online pushed the traditional query-based search methods to the limit. The information retrieval (IR) community made a counterproposal stating that building a personalized web surfing experience to the user. The aim of this research was to d...
Saved in:
| Main Author: | |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
2011
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_bachelors/2642 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | The recent increase in the amount of information available online pushed the traditional query-based search methods to the limit. The information retrieval (IR) community made a counterproposal stating that building a personalized web surfing experience to the user. The aim of this research was to design a recommendation system that uses Tversky commonality model with LSI algorithm to solve the issues that the traditional collaborative filtering based recommender systems pose: sparsity and scalability. With the help of the commonality and similarity measurement, The LSI algorithm with commonality and similarity performed better than the traditional LSI-based recommendation algorithm. |
|---|