Advanced

Detecting speculations, contrasts and conditionals in consumer reviews

Skeppstedt, Maria; Schamp-Bjerede, Teri LU ; Sahlgren, Magnus; Paradis, Carita LU and Kerren, Andreas (2015) 6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA '15) In 6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, WASSA 2015 : Workshop proceedings p.162-168
Abstract
A support vector classifier was compared to a lexicon-based approach for the task of detecting the stance categories speculation, contrast and conditional in English consumer reviews. Around 3,000 training instances were required to achieve a stable performance of an F-score of 90 for speculation. This outperformed the lexicon-based approach, for which an Fscore of just above 80 was achieved. The machine learning results for the other two categories showed a lower average (an approximate F-score of 60 for contrast and 70 for conditional), as well as a larger variance, and were only slightly better than lexicon matching. Therefore, while machine learning was successful for detecting speculation, a well-curated lexicon might be a more... (More)
A support vector classifier was compared to a lexicon-based approach for the task of detecting the stance categories speculation, contrast and conditional in English consumer reviews. Around 3,000 training instances were required to achieve a stable performance of an F-score of 90 for speculation. This outperformed the lexicon-based approach, for which an Fscore of just above 80 was achieved. The machine learning results for the other two categories showed a lower average (an approximate F-score of 60 for contrast and 70 for conditional), as well as a larger variance, and were only slightly better than lexicon matching. Therefore, while machine learning was successful for detecting speculation, a well-curated lexicon might be a more suitable approach for detecting contrast and conditional. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
consumer reviews, support vector classifier, stance
in
6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, WASSA 2015 : Workshop proceedings
editor
Alexandra, Balahur; Erik, van der Goot; Piek, Vossen and Andrés, Montoyo
pages
7 pages
publisher
Association for Computational Linguistics
conference name
6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA '15)
ISBN
978-1-941643-32-7
project
StaViCTA - Advances in the description and explanation of stance in discourse using visual and computational text analytics
language
English
LU publication?
yes
id
900a4c9b-8c53-48c0-8679-7aef36931455 (old id 8052276)
alternative location
http://www.aclweb.org/anthology/W/W15/W15-29.pdf#page.162
date added to LUP
2015-10-07 10:57:28
date last changed
2016-04-26 15:55:37
@misc{900a4c9b-8c53-48c0-8679-7aef36931455,
  abstract     = {A support vector classifier was compared to a lexicon-based approach for the task of detecting the stance categories speculation, contrast and conditional in English consumer reviews. Around 3,000 training instances were required to achieve a stable performance of an F-score of 90 for speculation. This outperformed the lexicon-based approach, for which an Fscore of just above 80 was achieved. The machine learning results for the other two categories showed a lower average (an approximate F-score of 60 for contrast and 70 for conditional), as well as a larger variance, and were only slightly better than lexicon matching. Therefore, while machine learning was successful for detecting speculation, a well-curated lexicon might be a more suitable approach for detecting contrast and conditional.},
  author       = {Skeppstedt, Maria and Schamp-Bjerede, Teri and Sahlgren, Magnus and Paradis, Carita and Kerren, Andreas},
  editor       = {Alexandra, Balahur and Erik, van der Goot and Piek, Vossen and Andrés, Montoyo},
  isbn         = {978-1-941643-32-7},
  keyword      = {consumer reviews,support vector classifier,stance},
  language     = {eng},
  pages        = {162--168},
  publisher    = {ARRAY(0x88f3340)},
  series       = {6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, WASSA 2015 : Workshop proceedings},
  title        = {Detecting speculations, contrasts and conditionals in consumer reviews},
  year         = {2015},
}