Information Retrieval is mainly thought as an inverted index technology. In real IR systems, post processing or other mining functions are hardly used to modify and visualize retrieval sets. Even query expansion is often used in batch mode.

However, Big Data technologies and algorithms for mining massive data can be profitably used in information retrieval to set up new modalities to index, to visualize or aggregate result sets, with new modalities that go beyond the usual presentation of a ranked list.

Freshness, sentiment, content, authority, similarity and cluster of results should be suitably combined and visualised. In this seminar we will illustrate how different technologies and algorithms can be integrated to efficiently aggregate and visualize search.

Gianni Amati leads the Laboratory on Data Mining & Text Mining at the Fondazione Ugo Bordoni in Rome, Italy. He is also Adjunct Professor of “Information Retrieval” for the advanced Course on Information Science at University of Roma Due, Tor Vergata. Gianni was the initial developer of Terrier, a high performance and scalable open-source search engine, and is currently involved in industrial projects on search, sentimental analysis, massive clustering and visualization of Social Networks. Finally, he has been involved in the organization and management of the main annual conferences (e.g., SIGIR, CIKM, ECIR, ICTIR).