An unsupervised aspect extraction strategy for monitoring real-time reviews stream

Mauro Dragoni, Marco Federici, Andi Rexha

Research output: Contribution to journalArticleResearchpeer-review

Abstract

One of the most important opinion mining research directions falls in the extraction of
polarities referring to specific entities (aspects) contained in the analyzed texts. The detection
of such aspects may be very critical especially when documents come from unknown
domains. Indeed, while in some contexts it is possible to train domain-specific
models for improving the effectiveness of aspects extraction algorithms, in others the
most suitable solution is to apply unsupervised techniques by making such algorithms
domain-independent. Moreover, an emerging need is to exploit the results of aspect-based
analysis for triggering actions based on these data. This led to the necessity
of providing solutions supporting both an effective analysis of user-generated content
and an efficient and intuitive way of visualizing collected data. In this work, we implemented
an opinion monitoring service implementing (i) a set of unsupervised strategies
for aspect-based opinion mining together with (ii) a monitoring tool supporting users
in visualizing analyzed data. The aspect extraction strategies are based on the use of semantic
resources for performing the extraction of aspects from texts. The effectiveness
of the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.
LanguageEnglish
Number of pages16
JournalInformation processing & management
DOIs
StatusAccepted/In press - 1 Nov 2018

Fingerprint

monitoring
Monitoring
campaign
semantics
Semantics
resources
time
Opinion mining
Benchmark
Train
User-generated content
Research directions
Resources

Cite this

An unsupervised aspect extraction strategy for monitoring real-time reviews stream. / Dragoni, Mauro; Federici, Marco; Rexha, Andi.

In: Information processing & management, 01.11.2018.

Research output: Contribution to journalArticleResearchpeer-review

@article{f029318477304dada381b2d15160e882,
title = "An unsupervised aspect extraction strategy for monitoring real-time reviews stream",
abstract = "One of the most important opinion mining research directions falls in the extraction ofpolarities referring to specific entities (aspects) contained in the analyzed texts. The detectionof such aspects may be very critical especially when documents come from unknowndomains. Indeed, while in some contexts it is possible to train domain-specificmodels for improving the effectiveness of aspects extraction algorithms, in others themost suitable solution is to apply unsupervised techniques by making such algorithmsdomain-independent. Moreover, an emerging need is to exploit the results of aspect-basedanalysis for triggering actions based on these data. This led to the necessityof providing solutions supporting both an effective analysis of user-generated contentand an efficient and intuitive way of visualizing collected data. In this work, we implementedan opinion monitoring service implementing (i) a set of unsupervised strategiesfor aspect-based opinion mining together with (ii) a monitoring tool supporting usersin visualizing analyzed data. The aspect extraction strategies are based on the use of semanticresources for performing the extraction of aspects from texts. The effectivenessof the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.",
author = "Mauro Dragoni and Marco Federici and Andi Rexha",
year = "2018",
month = "11",
day = "1",
doi = "10.1016/j.ipm.2018.04.010",
language = "English",
journal = "Information processing & management",
issn = "0306-4573",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - An unsupervised aspect extraction strategy for monitoring real-time reviews stream

AU - Dragoni,Mauro

AU - Federici,Marco

AU - Rexha,Andi

PY - 2018/11/1

Y1 - 2018/11/1

N2 - One of the most important opinion mining research directions falls in the extraction ofpolarities referring to specific entities (aspects) contained in the analyzed texts. The detectionof such aspects may be very critical especially when documents come from unknowndomains. Indeed, while in some contexts it is possible to train domain-specificmodels for improving the effectiveness of aspects extraction algorithms, in others themost suitable solution is to apply unsupervised techniques by making such algorithmsdomain-independent. Moreover, an emerging need is to exploit the results of aspect-basedanalysis for triggering actions based on these data. This led to the necessityof providing solutions supporting both an effective analysis of user-generated contentand an efficient and intuitive way of visualizing collected data. In this work, we implementedan opinion monitoring service implementing (i) a set of unsupervised strategiesfor aspect-based opinion mining together with (ii) a monitoring tool supporting usersin visualizing analyzed data. The aspect extraction strategies are based on the use of semanticresources for performing the extraction of aspects from texts. The effectivenessof the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.

AB - One of the most important opinion mining research directions falls in the extraction ofpolarities referring to specific entities (aspects) contained in the analyzed texts. The detectionof such aspects may be very critical especially when documents come from unknowndomains. Indeed, while in some contexts it is possible to train domain-specificmodels for improving the effectiveness of aspects extraction algorithms, in others themost suitable solution is to apply unsupervised techniques by making such algorithmsdomain-independent. Moreover, an emerging need is to exploit the results of aspect-basedanalysis for triggering actions based on these data. This led to the necessityof providing solutions supporting both an effective analysis of user-generated contentand an efficient and intuitive way of visualizing collected data. In this work, we implementedan opinion monitoring service implementing (i) a set of unsupervised strategiesfor aspect-based opinion mining together with (ii) a monitoring tool supporting usersin visualizing analyzed data. The aspect extraction strategies are based on the use of semanticresources for performing the extraction of aspects from texts. The effectivenessof the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.

U2 - 10.1016/j.ipm.2018.04.010

DO - 10.1016/j.ipm.2018.04.010

M3 - Article

JO - Information processing & management

T2 - Information processing & management

JF - Information processing & management

SN - 0306-4573

ER -