Abstract | ||
---|---|---|
In this paper, we propose a new recommender algorithm based on user's social profile and new measurements. It's used by our recommender system that uses external knowledge to solve the cold start problem. Most of Collaborative filtering algorithms are based on user's rating profile, we propose to introduce external resource to create several communities to predict recommendation. These systems are achieving widespread success in E-tourism nowadays. We evaluate our algorithm on tourism dataset and we have shown good results. We compared our algorithm to SVD, Slope One and Weight Slope One. We have obtained an improvement of 8% in precision and recall as well an improvement of 18 % in RMSE and nDCG. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-662-49390-8_8 | Intelligent Information and Database Systems, ACIIDS 2016, Pt II |
Keywords | Field | DocType |
Recommendation system, Tourism recommendation, Collaborative filtering, Machine learning, Social information extraction | Data mining,Learning to rank,Slope One,Computer science,Artificial intelligence,Empirical research,Recommender system,Singular value decomposition,Collaborative filtering,Cold start,Precision and recall,Algorithm,Machine learning | Conference |
Volume | ISSN | Citations |
9622 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Firas Ben Kharrat | 1 | 0 | 0.34 |
Aymen Elkhlifi | 2 | 27 | 5.10 |
Rim Faiz | 3 | 98 | 36.23 |