2018
DOI: 10.3390/ijgi7040158
|View full text |Cite
|
Sign up to set email alerts
|

Using the TensorFlow Deep Neural Network to Classify Mainland China Visitor Behaviours in Hong Kong from Check-in Data

Abstract: Over the past decade, big data, including Global Positioning System (GPS) data, mobile phone tracking data and social media check-in data, have been widely used to analyse human movements and behaviours. Tourism management researchers have noted the potential of applying these data to study tourist behaviours, and many studies have shown that social media check-in data can provide new opportunities for extracting tourism activities and tourist behaviours. However, traditional methods may not be suitable for ex… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
24
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
8
2

Relationship

2
8

Authors

Journals

citations
Cited by 39 publications
(24 citation statements)
references
References 37 publications
0
24
0
Order By: Relevance
“…Different studies have been oriented to classify different groups of visitors using geotagged crowdsourced data, under the assumption that different groups tend to have different travel preferences [12]. [13], for example, used a deep neural network using TensorFlow to classify visitors' behaviour to six groups in Honk-Kong based on geo-located data of the Weibo social check-in platform, receiving an accuracy of close to 90%. In the study of [4], the authors used Weibo data for comparing the activity of locals and tourists in the Shanghai region, showing that the activities of tourists are significantly different from those of locals in terms of their spatiotemporal patterns.…”
Section: Photographer Groupsmentioning
confidence: 99%
“…Different studies have been oriented to classify different groups of visitors using geotagged crowdsourced data, under the assumption that different groups tend to have different travel preferences [12]. [13], for example, used a deep neural network using TensorFlow to classify visitors' behaviour to six groups in Honk-Kong based on geo-located data of the Weibo social check-in platform, receiving an accuracy of close to 90%. In the study of [4], the authors used Weibo data for comparing the activity of locals and tourists in the Shanghai region, showing that the activities of tourists are significantly different from those of locals in terms of their spatiotemporal patterns.…”
Section: Photographer Groupsmentioning
confidence: 99%
“…Deep convolutional neural networks (CNNs) are able to automatically learn the features required for image classification from training-image data, thus improving classification accuracy and efficiency without relying on artificial feature selection. Very recent studies have proposed deep learning algorithms to achieve significant empirical improvements in areas such as image classification [14], object detection [15], human behavior recognition [16,17], speech recognition [18,19], traffic signal recognition [20,21], clinical diagnosis [22,23], and plant disease identification [11,24]. The successes of applying CNNs to image recognition have led geologists to investigate their use in identifying rock types [8,9,25], and deep learning has been used in several studies to identify the rock types from images.…”
Section: Introductionmentioning
confidence: 99%
“…It is challenging to capture such features using numeric variables. Deep learning learns through multiple layers of representations or features and produces state-of-the-art results based on both structured and unstructured data [23][24][25]. Accordingly, deep learning techniques have been successfully used for mining textual information in many fields; nonetheless, their application in rental market modeling and prediction is still limited.…”
Section: Introductionmentioning
confidence: 99%