The average estimates of a group of individuals are generally better than the estimates of the individuals alone, a phenomenon commonly referred to as the wisdom of crowds. This has been shown to work for many types of simple tasks, but has generally been performed on subjects that do not communicate with one another. We report group aggregation performance for more complex tasks, involving rec...

The literature on the wisdom of crowds argues that in most situations, the aggregated judgments of a large crowd perform well relative to the average individual. There are, however, many real-world cases where crowds perform poorly. A small crowd literature has since developed, finding that better performing small crowds often exist within whole crowds. We compare previously proposed small crow...

We present a traffic analysis of the ADU anonymity scheme presented at ESORICS 2008, and the related RADU scheme. We show that optimal attacks are able to de-anonymize messages more effectively than believed before. Our analysis applies to single messages as well as long term observations using multiple messages. The search of a “better” scheme is bound to fail, since we prove that the original...

It is often claimed that opinions are more likely to be correct if they are held independently by many individuals. But what does it mean to hold independent opinions? To clarify this condition, we distinguish four notions of probabilistic opinion independence. Which notion applies depends on environmental factors such as commonly perceived evidence. More formally, it depends on the causal netw...

When dealing with subjective, noisy, or otherwise nebulous features, the “wisdom of crowds” suggests that one may benefit from multiple judgments of the same feature on the same object. We give theoreticallymotivated feature multi-selection algorithms that choose, among a large set of candidate features, not only which features to judge but how many times to judge each one. We demonstrate the e...

Previous studies have shown that one can exploit “wisdom of crowds” by oneself. This is achieved by aggregating multiple “quasi-independent” estimates from the same person. However, previous methods were not necessarily easy to utilize. Therefore, we propose an efficient method based on perspective-taking. The procedure is as follows: First, one makes her/his own estimation. Second, one estimat...

Statistical aggregation is often used to combine multiple opinions within a group. Such aggregates outperform individuals, including experts, in various prediction and estimation tasks. This result is attributed to the "wisdom of crowds". We seek to improve the quality of such aggregates by identifying and eliminating poor performing individuals from the crowd. We propose a new measure of contr...