Summarizing Product Reviews Using Dynamic Relation Extraction
(2016) In LU-CS-EX 2016-40 EDA920 20161Department 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:
http://lup.lub.lu.se/student-papers/record/8894746
- author
- Gråborg, Mikael LU and Handmark, Oskar LU
- supervisor
- organization
- course
- EDA920 20161
- year
- 2016
- 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}},
}