My PhD project focuses on the suggestion of information categories in exploratory search in a geographical domain. Geographical maps may challenge the user in the exploration of possibly complex information spaces, making difficult to find all the relevant data for the completion of her/his search task. I propose different models for concepts suggestion which, given a search query, allow the creation of clusters of categories useful for query expansion as a "you might be interested in" function. The training of these models is done by exploiting different types of information: search sessions, users» preferences and social data coming from Twitter.

Suggestion Models in Geographic Exploratory Search

Mauro, Noemi
2018-01-01

Abstract

My PhD project focuses on the suggestion of information categories in exploratory search in a geographical domain. Geographical maps may challenge the user in the exploration of possibly complex information spaces, making difficult to find all the relevant data for the completion of her/his search task. I propose different models for concepts suggestion which, given a search query, allow the creation of clusters of categories useful for query expansion as a "you might be interested in" function. The training of these models is done by exploiting different types of information: search sessions, users» preferences and social data coming from Twitter.
2018
23rd International Conference on Intelligent User Interfaces, IUI 2018
Tokyo, Japan
2018
International Conference on Intelligent User Interfaces, Proceedings IUI
Association for Computing Machinery
669
670
9781450349451
https://dl.acm.org/citation.cfm?id=3173148
Geographical Information Retrieval; Session-based Concept Suggestion; Query Expansion.
Mauro, Noemi
File in questo prodotto:
File Dimensione Formato  
p669-mauro.pdf

Accesso riservato

Tipo di file: PDF EDITORIALE
Dimensione 311.73 kB
Formato Adobe PDF
311.73 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
IUI2018___Doctoral_Consortium (1).pdf

Accesso aperto

Descrizione: Articolo completo
Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 81.53 kB
Formato Adobe PDF
81.53 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1664300
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact