Coping with unfair ratings in reputation systems based on learning approach
| Autor: | Hamid Reza Shahriari, Amir Khoshkbarchi |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Coping (psychology)
Information Systems and Management Learning automata Computer science media_common.quotation_subject 02 engineering and technology Computer security computer.software_genre Computer Science Applications 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing computer Reputation media_common |
| Zdroj: | Enterprise Information Systems. 11:1481-1499 |
| ISSN: | 1751-7583 1751-7575 |
| DOI: | 10.1080/17517575.2016.1221999 |
| Popis: | One of the problems in service-oriented environments is the existence of deceptive agents and their intentional or unintentional malicious behaviour. A more complex challenge is unpredictable changes that some agents make to their behaviour, which is a cause of performance decrease in trust systems. Many trust models have been developed based on feedback mechanisms, but most of them are unable to detect inaccurate information that a deceptive agent may generate; therefore, the trust systems face difficulties in separating the fair from the unfair agents. In this paper, we used learning automata to separate fair from deceptive agents based on an aggregation of their feedback from the votes on each service attribute. The main contribution of this work was a new scheme for separating fair from unfair agents and for estimating the quality of services. We took a more detailed view of service attributes by decomposing a service to its qualitative elements to reach a better match between recommended serv... |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|