Search results

This study explores the pioneering approach of utilising machine learning (ML) models and integrating social media data for predicting tourist arrivals in Sri Lanka.

Two sets of experiments are performed in this research. First, the predictive accuracy of three ML models, support vector regression (SVR), random forest (RF) and artificial neural network (ANN), is compared against the seasonal autoregressive integrated moving average (SARIMA) model using historical tourist arrivals as features. Subsequently, the impact of incorporating social media data from TripAdvisor and Google Trends as additional features is investigated.

The findings reveal that the ML models generally outperform the SARIMA model, particularly from 2019 to 2021, when several unexpected events occurred in Sri Lanka. When integrating social media data, the RF model performs significantly better during most years, whereas the SVR model does not exhibit significant improvement. Although adding social media data to the ANN model does not yield superior forecasts, it exhibits proficiency in capturing data trends.

The findings offer substantial implications for the industry's growth and resilience, allowing stakeholders to make accurate data-driven decisions to navigate the unpredictable dynamics of Sri Lanka's tourism sector.

This study presents the first exploration of ML models and the integration of social media data for forecasting Sri Lankan tourist arrivals, contributing to the advancement of research in this domain.

This research constructs the critical predictors of visitation that shall allow the practitioners to foresee the visitation in the years to come through secondary data. For this study, tourist arrival data associated with the most popular forest park (i.e., Xiton Forest Park) in Taiwan along with relevant socio-economic data are utilized. This research adopts a group of analytical procedures involving correlation analysis, regression, and curve estimation analyses. The results show that the number of holiday per month and the average monthly rainfall have positive and negative correlations, respectively, with the visitation. Meanwhile, average monthly temperature and monthly gross domestic product per capita show a positive correlation in all three analytical methods and therefore are regarded as the primary predictors of tourist arrival. Consequently, this study provides managerial implications to increase the tourist arrivals to the forest park.

The aim of this chapter is to examine the role of real exchange rates in the relationship between tourist arrival and economic growth in Malaysia over the period of 2000–2018. We disaggregate Malaysian tourists into six geographical regions, namely Asia, Singapore, Europe, Pacific region, Americas, and Africa. Using a non-linear autoregressive distributed lag model, we find that the appreciation of real exchange rates with positive growth of economy plays a prominent role in influencing international tourist arrivals from Singapore, other Asian countries, Pacific region, Europe, and Americas. Our study suggests that real appreciation is important in providing some insights into the effectiveness of growth-led-tourism policies. In line with this, some implications are provided at the end of this chapter.

The purpose of this study is to empirically examine the determinants of foreign and domestic tourist arrivals and revenue receipts from tourism using state-level panel data in 25 Indian states for the period 1995 to 2011.

The study uses IV-2SLS method to examine the determinants of foreign and domestic tourist arrivals in Indian states. Economic development (proxied by per capita income, PCI) is an endogenous variable. We have used the state-wise “liable to flood prone area” as an instrument for PCI to control for endogeneity. An inverse relationship exists between state-wise “liable to flood prone area” and real PCI, in a sense that states with greater proportion of area marked as liable to flood experience lower economic development. For robust analysis, the study has also used IV-Tobit model to examine the effects of economic development and crime on revenue receipts from tourism.

The empirical results based on IV-2SLS method suggest that, in addition to economic development, other factors such as the presence of world-class monuments, natural landscapes and cultural heritage also encourage both international and domestic visitors in Indian states. While crime activities adversely affect the inflow of foreign and domestic tourist arrivals, terror activities do not significantly impact tourist arrivals and tourism receipts. Finally, the estimates of IV-Tobit model show that economic development and government expenditure on tourism sector leads to a significant increase in tourism receipts.

To the best of our knowledge, this is the first study done in Indian context in which state-level panel data have been used to examine the impact of economic, social and cultural factors on tourist arrivals and revenue earnings from tourism. Hence, the present study not only contributes to existing tourism literature, but also makes an important contribution to structuring suitable tourism management policies for the Indian states.

This study analyzes the impact of exchange rate volatility (ERV) on inbound tourist arrivals from four ASEAN countries namely Indonesia, the Philippines, Singapore, and Thailand during 1970–2017. Volatility in the exchange rates between the tourist currency and ringgit Malaysia is measured using the Generalized Autoregressive Conditional Heteroskedasticity model. The results from Autoregressive Distributed Lagged models indicate that ERV has no significant impact on tourist arrivals from ASEAN to Malaysia. This implies that tourists from these countries may not be sensitive to ERV when choosing Malaysia as their travel destination. There are two possible explanations for the results. First, Malaysian ringgit has been depreciating against major currencies and regional currencies in recent years, which makes ringgit relatively cheaper than other ASEAN currencies. Second, the empirical results of the study support the argument that ERV has a more serious impact on tourist spending compared to tourist arrivals.

Most of the European Mediterranean countries are suffering from seasonality and the problems caused by it. By applying different methods, this study proposes to measure seasonality in a Mediterranean country, Turkey. Studying seasonality and its measurement with the comparison of different methods could first provide useful guidelines for the countries, which may have similar problems, and could also broaden the current view in the related literature since the focus is also on the comparison of the widely used methods in the literature.

The study depends on the current literature and makes evaluations based on the secondary data acquired from the statistical publications of The Turkish Ministry of Culture and Tourism.

The findings reveal that none of the methods is superior to any other. They complement the weaknesses of one another. Therefore, it is suggested that destinations, when measuring their seasonality, should evaluate seasonality by applying different methods in order to give a proper decision to solve the problem caused by seasonality.

The study contributes to the seasonality literature by employing different measurement methods in a holistic way. It reveals differences and similarities among the different methods, using the case of a Mediterranean country, Turkey.

It is essential to understand how the countries with the highest number of tourist arrivals have managed to recover or not based on the competitiveness of the tourism industry during the pandemic stage. It is necessary to evaluate the policies implemented by each government to maintain the competitive performance of their industries. This chapter proposes a comprehensive review of the policies implemented in the 10 most visited countries according to UNWTO data. Most of these policies are geared toward economic and financial flexibility strategies for companies and individuals in the industry under study. The effectiveness of these policies is evaluated with statistical information extracted from a unified UNWTO database to reduce biases in the effectiveness analysis. Finally, concluding remarks are offered on the effectiveness of the policies and their contribution to the sector's recovery.

The main purpose of the present research is to explore the possible effectiveness of information and communication technology (ICT), infrastructure development, exchange rate and governance on inbound tourism demand using time series data in India.

The stationarity of the variables is checked by using the ADF, PP and KPSS unit root tests. The paper uses the Bayer-Hanck and auto-regressive distributed lag (ARDL) bounds testing approach to cointegration to examine the existence of long-run relationships; the error-correction mechanism for the short-run dynamics and the vector error correction method (VECM) to test the direction of causality.

The findings of the research indicate the presence of cointegration among the variables. Further, long-run results indicate infrastructure development, word-of-mouth and ICT have a positive and significant linkage with international tourist arrivals in India. However, ICT has a positive and significant effect on tourist arrivals in the short run as well. The VECM results indicate long-run unidirectional causality from infrastructure, ICT, governance and exchange rate to tourist arrivals.

This study implies that inbound tourism demand in India can be augmented by improving infrastructure, governance quality and ICT penetration. For an emerging country like India, this may have far-reaching implications for sustaining and improving tourism sector growth.

This paper is the first of its kind to empirically examine the impact of ICT, infrastructure and governance quality in India using modern econometric techniques. Inbound tourism demand research aids government and policymakers in developing effective public policies that would reposition India to gain from a highly competitive global tourism industry.

This research presents machine learning models for predicting international tourist arrivals in Indonesia during the COVID-19 pandemic using multisource Internet data.

To develop the prediction models, this research utilizes multisource Internet data from TripAdvisor travel forum and Google Trends. Temporal factors, posts and comments, search queries index and previous tourist arrivals records are set as predictors. Four sets of predictors and three distinct data compositions were utilized for training the machine learning models, namely artificial neural networks (ANNs), support vector regression (SVR) and random forest (RF). To evaluate the models, this research uses three accuracy metrics, namely root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE).

Prediction models trained using multisource Internet data predictors have better accuracy than those trained using single-source Internet data or other predictors. In addition, using more training sets that cover the phenomenon of interest, such as COVID-19, will enhance the prediction model's learning process and accuracy. The experiments show that the RF models have better prediction accuracy than the ANN and SVR models.

First, this study pioneers the practice of a multisource Internet data approach in predicting tourist arrivals amid the unprecedented COVID-19 pandemic. Second, the use of multisource Internet data to improve prediction performance is validated with real empirical data. Finally, this is one of the few papers to provide perspectives on the current dynamics of Indonesia's tourism demand.

The purpose of this study is to provide up-to-date evidence on the net effect of COVID-19 pandemic on international arrivals and occupancy rates in Greece. Analysis and forecasting point out the demand for 2020, and thus yielding more concrete evidence on the pure effect of the pandemic on the tourism industry.

Monthly observations from January 2000 to December 2020 were extracted from the Tourist Enterprises Association (SETE) for Athens, Thessaloniki, Kalamata, Rhodes, Mytilene, Santorini, Zante, Kefalonia and Crete. To model and forecast the volatility and the time trend effect of tourist arrivals individually, the study applies the autoregressive integrated moving average (ARIMA) (p,d,q) and the error, trend, seasonality (ETS) model.

Empirical results suggested that Athens, Thessaloniki and Crete were three destinations with the worst losses in international tourist arrivals. Specifically, Athens was expecting to have (without the existence of COVID-19) more than 330,000 tourist arrivals in December 2020 while instead only 73,000 international tourists visited Athens that period. Similarly, Thessaloniki and the island of Crete lost more than 150,000 international visitors during December 2020.

The author’s study adds to a growing number of studies regarding the impact of COVID-19 by incorporating monthly international arrival data and occupancy rate data for the whole 2020 reflecting differences in transportation or vacation choices. Also, the authors operationalized multiple time-series forecasting models (ETS and ARIMA) for reaching more concrete forecasts and estimates on the effect of COVID-19 on the Greek tourism sector.