In this paper we propose a new ranking algorithm based on Swarm Intelligence, more specifically on the Ant Colony Optimization technique, to improve search engines’ performances and reduce the information overload by exploiting users’ collective behavior. We designed an online evaluation involving end users to test our algorithm in a real-world scenario dealing with informational queries. The development of a fully working prototype – based on the Wikipedia search engine – demonstrated promising preliminary results. © Springer International Publishing Switzerland 2016.
Collaborative information seeking with ant colony ranking in real-time
Turchi T.;Malizia A;
2015-01-01
Abstract
In this paper we propose a new ranking algorithm based on Swarm Intelligence, more specifically on the Ant Colony Optimization technique, to improve search engines’ performances and reduce the information overload by exploiting users’ collective behavior. We designed an online evaluation involving end users to test our algorithm in a real-world scenario dealing with informational queries. The development of a fully working prototype – based on the Wikipedia search engine – demonstrated promising preliminary results. © Springer International Publishing Switzerland 2016.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
