Sentiment Prediction on E-commerce Sites Based on Dempster-Shafer Theory

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12510%2F16%3A43891632" target="_blank" >RIV/60076658:12510/16:43891632 - isvavai.cz</a>

Result on the web

<a href="http://mme2016.tul.cz/conferenceproceedings/mme2016_conference_proceedings.pdf" target="_blank" >http://mme2016.tul.cz/conferenceproceedings/mme2016_conference_proceedings.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Sentiment Prediction on E-commerce Sites Based on Dempster-Shafer Theory

Original language description

Sentiment predictions on e-commerce sites are usually based on assigning a numerical score that is followed eventually by free text review. On the basis of the analysis of existing methods, we propose a new method that aggregate score on the base of the Dempster-Shafer theory of evidence. In the proposed method, we first determine the polarity of reviews with the use of machine learning and then consider a sentence scores as evidence for an overall assessment review. Results from online data files show the usefulness of our method in comparison with existing methods.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2016

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Mathematical Methods in Economics

ISBN

978-80-7494-296-9

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

"43 ? 48"

Publisher name

Technical University of Liberec, Faculty of Economics

Place of publication

Liberec

Event location

Liberec

Event date

Sep 6, 2016

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

000385239500008