Examples of applications span from the massive compression of web pages to the development of personalized search engines that properly cluster Web results with the use of our natural language understanding software tools. The technology of our compressed data structures has also been used for the design of efficient algorithms for the retrieval of social media friends (and friends-of-friends). Unsupervised classification of short texts as well as the mining and analysis of social media posts and their trends are just a few other successful test cases resulted from our research.
WISER: A Semantic Search Engine for Experts. The last application (2019) of our technology has concerned with the design and development of a new semantic search engine, named WISER, for the automatic profiling and finding of experts. WISER models a person through a novel profiling technique which represents her expertise with a small, labeled and weighted graph drawn from Wikipedia. Profiles can be explored through a modern GUI, which enables users not only to get a glimpse of the expertise of the author, but also to understand how her research topics evolved during the years. Thes semantic profiles are also used for the efficient and effective retrieval of experts: as opposed to classical search engines, which aim at solving an input query with the retrieval of relevant documents, WISER aims at solving an input query with the retrieval of relevant experts.
WISER is adopted internally by the Technology Transfer Office of the University of Pisa and it currently supports its activities: from the finding of colleagues for joint projects to allow companies and other research organizations to access to the expertise offered by our Faculty.
Software & Datasets
Paolo Cifariello, Paolo Ferragina, Marco Ponza: WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking. Inf. Sys. (2019)
Paolo Ferragina, Francesco Piccinno, Rossano Venturini: Compressed Indexes for String Searching in Labeled Graphs. WWW 2015: 322-332
Paolo Ferragina, Francesco Piccinno, Roberto Santoro: On Analyzing Hashtags in Twitter. ICWSM 2015: 110-119
Ugo Scaiella, Paolo Ferragina, Andrea Marino, Massimiliano Ciaramita: Topical clustering of search results. WSDM 2012: 223-232
Daniele Vitale, Paolo Ferragina, Ugo Scaiella: Classification of Short Texts by Deploying Topical Annotations. ECIR 2012: 376-387
Paolo Ferragina, Giovanni Manzini: On compressing the textual web. WSDM 2010: 391-400
Paolo Ferragina, Antonio Gulli: A personalized search engine based on Web-snippet hierarchical clustering. Softw., Pract. Exper. 38(2): 189-225 (2008)