logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-09232008-165307


Tipo di tesi
Tesi di laurea specialistica
Autore
BACCIANELLA, STEFANO
URN
etd-09232008-165307
Titolo
Multi-facet rating of online hotel reviews: issues, methods and experiments
Dipartimento
SCIENZE MATEMATICHE, FISICHE E NATURALI
Corso di studi
INFORMATICA
Relatori
Relatore Dott. Sebastiani, Fabrizio
Relatore Dott. Esuli, Andrea
Relatore Prof. Ferragina, Paolo
Parole chiave
  • classifier
  • hotel
  • jatecs
  • pattern
  • rating
  • regression
  • reviews
  • tripadvisor
Data inizio appello
10/10/2008
Consultabilità
Completa
Riassunto
Online product reviews are becoming increasingly popular, and are being
used more and more frequently by consumers in order to choose among
competing products. Tools that rank competing products in terms of the
satisfaction of consumers that have purchased the product before, are thus
also becoming popular. We tackle the problem of rating (i.e., attributing
a numerical score of satisfaction to) consumer reviews based on their tex-
tual content. In this work we focus on multi-facet rating of hotel reviews,
i.e., on the case in which the review of a hotel must be rated several times,
according to several aspects (e.g., cleanliness, dining facilities, centrality of
location). We explore several aspects of the problem, including the vectorial
representation of the text based on sentiment analysis, collocation analysis,
and feature selection for ordinal-regression learning. We present the results
of experiments conducted on a corpus of approximately 15,000 hotel reviews
that we have crawled from a popular hotel review site.
File