A deep learning approach for daily tourist flow forecasting with consumer search data

Zhang, Binru; Li, Nao; Shi, Feng; Law, Rob

doi:10.1080/10941665.2019.1709876

Cited by 51 publications

(28 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Weather: Except for extreme weather, heavy rain, other weather has little impact on tourist passenger demand [4,12], so only dummy variables are used for extreme weather, that is, the value of this variable is only 1 (heavy rain) or 0 (other weather). (2) Statutory holidays: The demand of tourist passenger transport is significantly affected by weekends, statutory holidays and working days [4,12,13], so two sets of dummy variables D1 and D2 need to be introduced to represent the above three states. When the forecast day is a legal holiday, D1 is set to 1, and in other cases, it is set to 0.…”

Section: A Selection Of Variablesmentioning

confidence: 99%

“…Lagging variables refer to variables that have an impact on the current explained variable in the past period. Zhang [13] and Yao [14] pointed out that for daily data, lagging variables above the third order have little contribution to improving the prediction accuracy. This paper will perform 1-3 order lag processing on the quantified social network data and incorporate them into the prediction model together.…”

Section: A Selection Of Variablesmentioning

confidence: 99%

“…In recent years, some scholars have paid more attention to the use of search engine data for tourism demand forecasting. Zhang [13] used search engine data and historical passenger flow data to predict tourism demand in scenic spots. Yao [14] used the Baidu Index to predict the daily passenger flow of tourist attractions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Forecast Model of Tourism Demand Driven by Social Network Data

et al. 2021

View full text Add to dashboard Cite

To improve the forecasting accuracy of tourism demand through forecasting model and data sources, this paper takes the social network data as an entry point, and collects the social network data by the web crawler, then quantifies the data based on the sentiment analysis of the BERT model. This paper uses structured variables such as social network data, weather, holidays, etc. to build a tourism demand forecasting model based on Gradient Boosting Regression Trees. At last, take Huang Shan as example, use actual statistics of passenger terminal and social network data to do an empirical analysis of Huang Shan tourism demand forecasting. Compared with the existing model and introduce ablation study to verify the effectiveness of the considered factors. The result shows that the model based on social network data has improved the forecasting accuracy from the existing ones, ablation study shows social network data helps to improve the accuracy of tourism demand forecasting.

show abstract

Section: A Selection Of Variablesmentioning

confidence: 99%

Section: A Selection Of Variablesmentioning

confidence: 99%

See 1 more Smart Citation

A Forecast Model of Tourism Demand Driven by Social Network Data

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Since the late 1990s, AI studies have been applied in tourism researches to forecast hotel occupancy and tourism demand (Law, 1998(Law, , 2000. Afterwards, researchers used AI in different kind of inquiries such as resource management in tourism companies (Casteleiro-Roca et al, 2018), examining social media data and online reviews (Kirilenko et al, 2018;Topal & Uçar, 2018), forecasting tourist flow and arrivals (Zhang et al, 2020), evaluating tourist satisfaction through facial expression recognition (González-Rodríguez et al, 2020), and making smart recommendations (Zheng et al, 2020). AI models are used in tourism studies increasingly because these models have much more flexibility and they can be used to estimate non-linear relationships without the limits of traditional methods (Hadavandi et al, 2011).…”

Section: Introduction "I Believe There Is No Deep Difference Between What Can Be Achieved By a Biological Brain Andmentioning

confidence: 99%

Artificial Intelligence in Tourism: A Review and Bibliometrics Research

Kirtil¹,

Aşkun²

2021

Advances in Hospitality and Tourism Research (AHTR)

View full text Add to dashboard Cite

Artificial Intelligence (AI) came up as an ambiguous concept from computer sciences and now it is being used in many areas of our life. It has stimulated academia's interest due to its alternative insights into complex problems. Therefore, a bibliometric method was applied in this study to observe the progress of AI in the tourism field. A total of 102 papers were collected from Scopus database. Key factors such as most productive authors, collaborations and institutions were identified, and research hotspots were determined using co-occurrence network and most common author keywords. Progress of AI was visualized with thematic evolution analysis. Findings indicate that there is a progressive interest in AI after 2017, and average citations signify that papers are highly cited. Since this is the first study conducting a bibliometric on AI in the tourism context, it could be considered useful for academics and tourism professionals as it provides general overview of AI, demonstrates research trends and popular papers.

show abstract

“…Du, Li, Gong, and Horng (2020) proposed a hybrid multimodal deep learning method, which consists of one‐dimensional convolutional neural networks (1D CNNs) and gated recurrent units (GRUs) with the attention mechanism for short‐term traffic flow prediction. Li and Cao (2018) and Zhang, Li, Shi, and Law (2020) used the LSTM model to predict tourist flow in scenic spots. Lu et al (2020) established an LSTM model that combined a convolutional neural network and optimized it through a genetic algorithm to predict tourist flow.…”

Section: Introductionmentioning

confidence: 99%

Prediction of tourist flow based on multi‐source traffic data in scenic spot

Zhang

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

At present, China's tourism industry has entered an era of rapid development. It is of great significance to predict the precise and real‐time tourist flow of the popular tourist areas with dense crowds, providing decision support for rational evacuation of tourist flow, activation of emergency plans, and prevention of security accidents. This article presents a long short‐term memory (LSTM) neural network model based on the global attention mechanism. The model first uses two LSTM layers to calculate attention weights using multi‐source data at different time steps to improve the model’s learning ability. Then the model predicts the tourist flow of the scenic spots in the next time period based on the weights and outputs previously obtained. At the final stage, the pre‐trained parameters of the network are used to initialize the model. To verify the validity of the model, we compared it with the LSTM model, back propagation neural network model, and autoregressive integrated moving average model based on the data of Beijing’s South Luogu Lane scenic spot. It turned out that the results of our solution were more in line with the true value, which proves that it is feasible for real‐time prediction of tourist flow in popular scenic spots.

show abstract

A deep learning approach for daily tourist flow forecasting with consumer search data

Cited by 51 publications

References 43 publications

A Forecast Model of Tourism Demand Driven by Social Network Data

A Forecast Model of Tourism Demand Driven by Social Network Data

Artificial Intelligence in Tourism: A Review and Bibliometrics Research

Prediction of tourist flow based on multi‐source traffic data in scenic spot

Contact Info

Product

Resources

About