Search engines are essential internet services, enabling users to efficiently find the information they need. Session search employs users’ session logs of queries solve complex retrieval tasks, in which multiple times until interested documents found. Most existing models focus on contextual within current search, ignoring evidence from historical sessions. Considering fact that many ongoing t...

According to the “Wisdom of Crowds” phenomenon, a large crowd can perform better than smaller groups or few individuals. This article investigates the performance of share recommendations, which have been published by members of a stock prediction community on the Internet. Participants of these online communities publish buy and sell recommendations for shares and try to predict the stock mark...

The QUATRO Plus project, a follow on from the original QUATRO Project, aims to balance the wisdom of the crowds with the knowledge of the experts. It uses a mixture of authenticated data sources and the opinions of end users expressed through social networking software to build a dataset that is authoritative and trustworthy. The dataset describes online resources using RDF with the upcoming W3...

The “self-organizing” of online crowds—or workers, more generally— into teams is a non-trivial problem of coordination and matching, in a context in which other parties are simultaneously competing for partners. Here, we experimentally investigate the capacity for workers in online crowds to self-organize into teams, within a scientific crowdsourcing contest. We compare matching outcomes and pe...

We analyze how advice from an AI affects complementarities between humans and AI, in particular what know that does not know: “unique human knowledge.” In a multi-method study consisting of analytical model, experimental studies, simulation study, our main finding is choices converge toward similar responses improving individual accuracy. However, as overall accuracy the group improves, unique ...