Attributes prediction from IoT consumer reviews in the hotel sectors using conventional neural network: deep learning techniques

Alaa Shoukry () and Fares Aldeek
Additional contact information
Alaa Shoukry: King Saud University
Fares Aldeek: King Saud University

Electronic Commerce Research, 2020, vol. 20, issue 2, No 1, 223-240

Abstract: Abstract The Internet of Things (IoT) plays an important role in helping the hotel industry increase customer satisfaction while maintaining affordable costs. IoT consumers review and rate the hotels online. The ratings are based on the Value, Apartment, Site, Sanitation, Front Desk, Facility, Professional Provision, Internet, and Packing. Traditional systems that predict hotel ratings with minimum accuracy create complexity through their analysis of the ratings. Thus, the effective deep learning techniques are used to analyze the reviews in order to help consumers choose better hotels. In this paper, different classification algorithms, such as convolutional neural network-based deep learning (CNN-DL), support vector machine network-based deep learning are applied to predict attributes. The system utilizes the TripAdvisor site, which is a well-known America dataset for examining system efficiency. The experimental results show that the CNN-DL algorithm has better classification accuracy and a lower error rate as compared to other algorithms.

Keywords: IoT; Deep learning; Internet reviews; Prediction; Sentiments (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1007/s10660-019-09373-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:elcore:v:20:y:2020:i:2:d:10.1007_s10660-019-09373-4

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10660

DOI: 10.1007/s10660-019-09373-4

Access Statistics for this article

Electronic Commerce Research is currently edited by James Westland

More articles in Electronic Commerce Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().