In this paper we present RELEVANTNews, a web feed reader that automatically groups news related to the same topic published in different newspapers in different days. The tool is based on RELEVANT, a previously developed tool, which computes the “relevant values”, i.e. a subset of the values of a string attribute.Clustering the titles of the news feeds selected by the user, it is possible identify sets of related news on the basis of syntactic and lexical similarity.RELEVANTNews may be used in its default configuration or in a personalized way: the user may tune some parameters in order to improve the grouping results. We tested the tool with more than 700 news published in 30 newspapers in four daysand some preliminary results are discussed.
Relevant News: a semantic news feed aggregator / Bergamaschi, Sonia; Guerra, Francesco; Orsini, Mirko; Sartori, C; Vincini, Maurizio. - ELETTRONICO. - 314:(2007), pp. 150-159. (Intervento presentato al convegno Semantic Web Applications and Perspectives tenutosi a Bari nel 18 - 20 Dicembre 2007).
Relevant News: a semantic news feed aggregator
BERGAMASCHI, Sonia;GUERRA, Francesco;ORSINI, Mirko;VINCINI, Maurizio
2007
Abstract
In this paper we present RELEVANTNews, a web feed reader that automatically groups news related to the same topic published in different newspapers in different days. The tool is based on RELEVANT, a previously developed tool, which computes the “relevant values”, i.e. a subset of the values of a string attribute.Clustering the titles of the news feeds selected by the user, it is possible identify sets of related news on the basis of syntactic and lexical similarity.RELEVANTNews may be used in its default configuration or in a personalized way: the user may tune some parameters in order to improve the grouping results. We tested the tool with more than 700 news published in 30 newspapers in four daysand some preliminary results are discussed.
| File | Dimensione | Formato | |
|---|---|---|---|
|
45.pdf
Open access
Tipologia:
Versione pubblicata dall'editore
Dimensione
259.83 kB
Formato
Adobe PDF
|
259.83 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
