ORCID Identifiers

0000-0001-6941-6555

Document Type

Conference Proceeding

Source of Publication

Procedia Computer Science

Publication Date

1-1-2017

Abstract

© 2017 The Authors. Published by Elsevier B.V. Many e-commerce websites allow customers to provide reviews that reflect their experiences and opinions about the business's products or services. Such published reviews potentially benefit the business's reputation, improve both current and future customers' trust in the business, and accordingly improve the business. Negative reviews can inform the merchant of issues that, when addressed, also improve the business. However, when reviews reflect negative experiences and the merchant fails to respond, the business faces potential loss of reputation, trust, and damage. We present the Sentiminder system that identifies reviews with negative sentiment, organizes them, and helps the merchant develop a plan with an end date by which issues will be addressed. In this paper we address the problem of quickly finding subtasks in a large set of reviews, which may help the merchant to identify, from the set of reviews, subtasks that need to be addressed. We do this by identify nouns that frequently occur only in the reviews with negative sentiment.

ISSN

1877-0509

Publisher

Elsevier B.V.

Volume

113

First Page

217

Last Page

222

Disciplines

Business | Computer Sciences

Keywords

Clustering, Costs Estimation, Sentiment Extraction, Social business analysts

Scopus ID

85033485587

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Gold: This publication is openly available in an open access journal/series

Share

COinS