Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Summarizing Product Reviews Using Dynamic Relation Extraction

Gråborg, Mikael LU and Handmark, Oskar LU (2016) In LU-CS-EX 2016-40 EDA920 20161
Department of Computer Science
Abstract
The accumulated review data for a single product on Amazon.com could po-
tentially take several weeks to examine manually. Computationally extracting

the essence of a document is a substantial task, which has been explored pre-
viously through many different approaches. We explore how statistical predic-
tion can be used to perform dynamic relation extraction. Using patterns in the

syntactic structure of a sentence, each word is classified as either product fea-
ture or descriptor, and then linked together by association. The classifiers are

trained with a manually annotated training set and features from dependency

parse trees produced by the Stanford CoreNLP library.

In this thesis we compare the most widely used... (More)
The accumulated review data for a single product on Amazon.com could po-
tentially take several weeks to examine manually. Computationally extracting

the essence of a document is a substantial task, which has been explored pre-
viously through many different approaches. We explore how statistical predic-
tion can be used to perform dynamic relation extraction. Using patterns in the

syntactic structure of a sentence, each word is classified as either product fea-
ture or descriptor, and then linked together by association. The classifiers are

trained with a manually annotated training set and features from dependency

parse trees produced by the Stanford CoreNLP library.

In this thesis we compare the most widely used machine learning algo-
rithms to find the one most suitable for our scenario. We ultimately found

that the classification step was most successful with SVM, reaching an FS-
core of 80 percent for the relation extraction classification step. The results of

the predictions are presented in a graphical interface displaying the relations.

An end-to-end evaluation was also conducted, where our system achieved a

relaxed recall of 53.35%. (Less)
Please use this url to cite or link to this publication:
author
Gråborg, Mikael LU and Handmark, Oskar LU
supervisor
organization
course
EDA920 20161
year
type
H3 - Professional qualifications (4 Years - )
subject
keywords
review analysis, relation extraction, nlp, data mining, machine learning
publication/series
LU-CS-EX 2016-40
report number
LU-CS-EX 2016-40
ISSN
1650-2884
language
English
id
8894746
date added to LUP
2016-11-08 16:05:50
date last changed
2016-11-08 16:05:50
@misc{8894746,
  abstract     = {{The accumulated review data for a single product on Amazon.com could po-
tentially take several weeks to examine manually. Computationally extracting

the essence of a document is a substantial task, which has been explored pre-
viously through many different approaches. We explore how statistical predic-
tion can be used to perform dynamic relation extraction. Using patterns in the

syntactic structure of a sentence, each word is classified as either product fea-
ture or descriptor, and then linked together by association. The classifiers are

trained with a manually annotated training set and features from dependency

parse trees produced by the Stanford CoreNLP library.

In this thesis we compare the most widely used machine learning algo-
rithms to find the one most suitable for our scenario. We ultimately found

that the classification step was most successful with SVM, reaching an FS-
core of 80 percent for the relation extraction classification step. The results of

the predictions are presented in a graphical interface displaying the relations.

An end-to-end evaluation was also conducted, where our system achieved a

relaxed recall of 53.35%.}},
  author       = {{Gråborg, Mikael and Handmark, Oskar}},
  issn         = {{1650-2884}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{LU-CS-EX 2016-40}},
  title        = {{Summarizing Product Reviews Using Dynamic Relation Extraction}},
  year         = {{2016}},
}