Towards an Abstractive Opinion Summarisation of Multiple Reviews in the Tourism Domain

Cyril Labbé 1 François Portet 2
1 SIGMA
LIG - Laboratoire d'Informatique de Grenoble
Abstract : Since the arrival of Web 2.0, there is an increasing amount of on-line Reviews and Ratings about diverse products or services. These reviews contain general comments as well as highly personal elements or opinions about their customers' experience with the product. Other customers or companies are facing the problem of extracting the relevant information from this mass of reviews. In this paper, we present a comparative study of three different summarisation techniques for reviews analysis. From this study, we propose a general architecture which relies on a customisable abstractive summarisation approach making use of domain knowledge and temporal analysis. The paper ends by identifying research directions for improving the efficiency of review summarisation methods.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00953455
Contributor : Sophie Dupuy-Chessa <>
Submitted on : Friday, February 28, 2014 - 11:52:29 AM
Last modification on : Monday, February 11, 2019 - 4:36:02 PM
Document(s) archivé(s) le : Friday, May 30, 2014 - 3:20:10 PM

File

sdad2012_submission_2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00953455, version 1

Citation

Cyril Labbé, François Portet. Towards an Abstractive Opinion Summarisation of Multiple Reviews in the Tourism Domain. The First International Workshop on Sentiment Discovery from Affective Data (SDAD 2012), 2012, Bristol, United Kingdom. pp.87--94. ⟨hal-00953455⟩

Share

Metrics

Record views

579

Files downloads

235