A Unified Latent Variable Model for Contrastive Opinion Mining

Emmanuel Ebuka Ibeke, Chenghua Lin, Adam Wyner, Mohamad Hardyman Barawi

Research output: Contribution to journalArticle

Abstract

There are large and growing textual corpora in which people express contrastive opinions about the same topic. This has led to an increasing number of studies about contrastive opinion mining. However, there are several notable issues with the existing studies. They mostly focus on mining contrastive opinions from multiple data collections, which need to be separated into their respective collections beforehand. In addition, existing models are opaque in terms of the relationship between topics that are extracted and the sentences in the corpus which express the topics; this opacity does not help us understand the opinions expressed in the corpus. Finally, contrastive opinion is mostly analysed qualitatively rather than quantitatively. This paper addresses these matters and proposes a novel unified latent variable model (contraLDA), which: mines contrastive opinions from both single and multiple data collections, extracts
the sentences that project the contrastive opinion, and measures the strength of opinion contrastiveness towards the extracted topics. Experimental results show the effectiveness of our model in mining contrasted opinions, which outperformed our baselines in extracting coherent and informative sentiment-bearing topics. We further show the accuracy of our model in classifying topics and sentiments of textual data, and we compared our results to five strong baselines.
Original languageEnglish
JournalFrontiers of Computer Science
Publication statusAccepted/In press - 3 Nov 2017

Fingerprint

Opinion Mining
Latent Variable Models
Baseline
Express
Opacity
Bearings (structural)
Model
Experimental Results
Corpus

Keywords

  • Sentiment analysis
  • Topic modelling
  • Contrastive opinion mining

Cite this

Ibeke, E. E., Lin, C., Wyner, A., & Barawi, M. H. (Accepted/In press). A Unified Latent Variable Model for Contrastive Opinion Mining. Frontiers of Computer Science.

A Unified Latent Variable Model for Contrastive Opinion Mining. / Ibeke, Emmanuel Ebuka; Lin, Chenghua; Wyner, Adam; Barawi, Mohamad Hardyman.

In: Frontiers of Computer Science, 03.11.2017.

Research output: Contribution to journalArticle

Ibeke, Emmanuel Ebuka ; Lin, Chenghua ; Wyner, Adam ; Barawi, Mohamad Hardyman. / A Unified Latent Variable Model for Contrastive Opinion Mining. In: Frontiers of Computer Science. 2017.
@article{843da36b14c94a81bb41d80f9ac0157b,
title = "A Unified Latent Variable Model for Contrastive Opinion Mining",
abstract = "There are large and growing textual corpora in which people express contrastive opinions about the same topic. This has led to an increasing number of studies about contrastive opinion mining. However, there are several notable issues with the existing studies. They mostly focus on mining contrastive opinions from multiple data collections, which need to be separated into their respective collections beforehand. In addition, existing models are opaque in terms of the relationship between topics that are extracted and the sentences in the corpus which express the topics; this opacity does not help us understand the opinions expressed in the corpus. Finally, contrastive opinion is mostly analysed qualitatively rather than quantitatively. This paper addresses these matters and proposes a novel unified latent variable model (contraLDA), which: mines contrastive opinions from both single and multiple data collections, extractsthe sentences that project the contrastive opinion, and measures the strength of opinion contrastiveness towards the extracted topics. Experimental results show the effectiveness of our model in mining contrasted opinions, which outperformed our baselines in extracting coherent and informative sentiment-bearing topics. We further show the accuracy of our model in classifying topics and sentiments of textual data, and we compared our results to five strong baselines.",
keywords = "Sentiment analysis , Topic modelling, Contrastive opinion mining",
author = "Ibeke, {Emmanuel Ebuka} and Chenghua Lin and Adam Wyner and Barawi, {Mohamad Hardyman}",
note = "This work is supported by the award made by the UK Engineering and Physical Sciences Research Council (Grant number: EP/P005810/1).",
year = "2017",
month = "11",
day = "3",
language = "English",
journal = "Frontiers of Computer Science",
issn = "2095-2236",
publisher = "Springer Science + Business Media",

}

TY - JOUR

T1 - A Unified Latent Variable Model for Contrastive Opinion Mining

AU - Ibeke, Emmanuel Ebuka

AU - Lin, Chenghua

AU - Wyner, Adam

AU - Barawi, Mohamad Hardyman

N1 - This work is supported by the award made by the UK Engineering and Physical Sciences Research Council (Grant number: EP/P005810/1).

PY - 2017/11/3

Y1 - 2017/11/3

N2 - There are large and growing textual corpora in which people express contrastive opinions about the same topic. This has led to an increasing number of studies about contrastive opinion mining. However, there are several notable issues with the existing studies. They mostly focus on mining contrastive opinions from multiple data collections, which need to be separated into their respective collections beforehand. In addition, existing models are opaque in terms of the relationship between topics that are extracted and the sentences in the corpus which express the topics; this opacity does not help us understand the opinions expressed in the corpus. Finally, contrastive opinion is mostly analysed qualitatively rather than quantitatively. This paper addresses these matters and proposes a novel unified latent variable model (contraLDA), which: mines contrastive opinions from both single and multiple data collections, extractsthe sentences that project the contrastive opinion, and measures the strength of opinion contrastiveness towards the extracted topics. Experimental results show the effectiveness of our model in mining contrasted opinions, which outperformed our baselines in extracting coherent and informative sentiment-bearing topics. We further show the accuracy of our model in classifying topics and sentiments of textual data, and we compared our results to five strong baselines.

AB - There are large and growing textual corpora in which people express contrastive opinions about the same topic. This has led to an increasing number of studies about contrastive opinion mining. However, there are several notable issues with the existing studies. They mostly focus on mining contrastive opinions from multiple data collections, which need to be separated into their respective collections beforehand. In addition, existing models are opaque in terms of the relationship between topics that are extracted and the sentences in the corpus which express the topics; this opacity does not help us understand the opinions expressed in the corpus. Finally, contrastive opinion is mostly analysed qualitatively rather than quantitatively. This paper addresses these matters and proposes a novel unified latent variable model (contraLDA), which: mines contrastive opinions from both single and multiple data collections, extractsthe sentences that project the contrastive opinion, and measures the strength of opinion contrastiveness towards the extracted topics. Experimental results show the effectiveness of our model in mining contrasted opinions, which outperformed our baselines in extracting coherent and informative sentiment-bearing topics. We further show the accuracy of our model in classifying topics and sentiments of textual data, and we compared our results to five strong baselines.

KW - Sentiment analysis

KW - Topic modelling

KW - Contrastive opinion mining

M3 - Article

JO - Frontiers of Computer Science

JF - Frontiers of Computer Science

SN - 2095-2236

ER -