A Trust-Based Experience-Aware Framework for Integrating Fuzzy Recommendations
| Autor: | Aleksander Ignjatovic, Elisa Bertino, Haleh Amintoosi, Mohammad Allahbakhsh |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Information Systems and Management
Computer Networks and Communications business.industry Iterative method Computer science media_common.quotation_subject Aggregate (data warehouse) Comparison results Machine learning computer.software_genre Fuzzy logic Computer Science Applications Hardware and Architecture Quality (business) Stock market Artificial intelligence business computer media_common Educational systems |
| Zdroj: | IEEE Transactions on Services Computing. 15:698-709 |
| ISSN: | 2372-0204 |
| Popis: | Social rating systems are widely used for gathering user feedbacks on the quality of products, items and services. Social rating systems accept various forms of numeric and non-numeric recommendations as input to their aggregation algorithm. Fuzzy recommendations, as one form of input recommendations, while common in areas such as stock market and educational systems, are challenging in terms of aggregation and scaling. Also, taking into account trust and experience of raters while aggregating fuzzy variables is another challenge that needs investigations. In this paper, we propose a trust-based experience-aware method for aggregation of fuzzy recommendations. We propose to use trust and experience of raters along with the area under the curve of the membership of the fuzzy recommendations to compute a weight for recommendations. Then, we present an iterative algorithm to aggregate these computed weighted recommendations. We evaluate our method using a real-world dataset and compare its performance with three well-known iterative algorithms. The comparison results show the superiority of our method over other related approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|