2011
DOI: 10.1016/j.fss.2010.10.015
|View full text |Cite
|
Sign up to set email alerts
|

Practical aggregation operators for gradual trust and distrust

Abstract: Trust and distrust are two increasingly important metrics in social networks, reflecting users' attitudes and relationships towards each other. In this paper, we study the indirect derivation of these metrics' values for users that do not know each other, but are connected through the network. In particular, we study bilattice-based aggregation approaches and investigate how they can be improved by using ordered weighted averaging techniques, or through the incorporation of knowledge defects. Experiments on a … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
70
0

Year Published

2012
2012
2017
2017

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 130 publications
(70 citation statements)
references
References 27 publications
0
70
0
Order By: Relevance
“…Therefore, it could also be argued its inability to model appropriately vague statements that are assessed using the concepts of 'trust' and 'distrust'. The concept of trust function has been regarded in [34,35] as a reliable tool to deal with agents' vague by trust degree and distrust degree. Considering that multiple experts might have fuzzier and more uncertainty opinions about alternatives as previously said, this article aims to investigate an interval-valued trust score space in which the trust degree and distrust degree are expressed by interval-valued numbers rather than trip values as FSs allow to.…”
Section: Interval-valued Trust Decision Making Spacementioning
confidence: 99%
“…Therefore, it could also be argued its inability to model appropriately vague statements that are assessed using the concepts of 'trust' and 'distrust'. The concept of trust function has been regarded in [34,35] as a reliable tool to deal with agents' vague by trust degree and distrust degree. Considering that multiple experts might have fuzzier and more uncertainty opinions about alternatives as previously said, this article aims to investigate an interval-valued trust score space in which the trust degree and distrust degree are expressed by interval-valued numbers rather than trip values as FSs allow to.…”
Section: Interval-valued Trust Decision Making Spacementioning
confidence: 99%
“…The most important difference is the inclusion of a previous step, prior to the consensus phase, in which the large group of experts is simplified into a "selected experts group" or spokespersons by using a clustering algorithm, trying to maintain the diversity on the opinions of the whole group. Once this simplification is made, the experts that have not been selected will provide information about the trust that the selected experts inspire to them, thus creating a trust network [27]. After this initial step the consensus process begins, but only the selected experts that are allowed to take part in the process.…”
Section: B Trust Based Consensus Modelsmentioning
confidence: 99%
“…For instance, in the experiments in [14], h = 2 was used, meaning that only trust scores resulting from one-step propagation were considered, and consequently all paths have the same length.…”
Section: Trust Selectionmentioning
confidence: 99%
“…The generated trust estimations can then be evaluated by means of their accuracy. To measure accuracy, we may use the following two variations [14] on mean absolute error (MAE) and root mean squared error (RMSE), with (…”
Section: Evaluation Of Trust Metricsmentioning
confidence: 99%
See 1 more Smart Citation