Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 47578 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Jalili, Mahdi
- Abstract:
- With the over-increasing growth of the information provided for the web users, from content providing systems and web stores to social networks, the exictence of recommender systems is strongly needed. Recommender systems personalize web for the users and help them with finding relevent information in the huge era of World Wide Web. Collaborative filtering methods are known as the most successful and vastly used recommendation systems. Although they generally outperform content-based algorithms, in cold-start situation and especially in the presence of the new items, they fail to predict ratings for the new items or make good recommendations. This problem is not negligible in the systems which items are constantly changing, for example in news websites or TV. In contrast, content-based methods deal with the new items as they deal with the other items; but their low precision is not satisfactory and also they are not able to predict exact ratings. In this work we introduced a method in which rating and content information are used together to make predictions more accurate. First, user ratings are used to extract content feature relation and then using this relation we calculate the similarity of the new items with the other items, predicting rate for them through an item-item collaborative filtering process. In addition we have introduced a novel content-based method that outperforms state of the art methods in precision
- Keywords:
- Recommender System ; Content Information ; Hybrid Recommender Systems ; Content Features Relation
Digital Object List
محتواي کتاب
Bookmark