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 systematic review paper aims to investigate seasonal ambient change’s impact on the incidence of falls among older adults.

The population, exposure, outcome (PEO) structured framework was used to frame the research question prior to using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis framework. Three databases were searched, and a total of 12 studies were found for inclusion, and quality appraisal was carried out. Data extraction was performed, and narrative analysis was carried out.

Of the 12 studies, 2 found no link between seasonality and fall incidence. One study found fall rates increased during warmer months, and 9 of the 12 studies found that winter months and their associated seasonal changes led to an increase in the incidence in falls. The overall result was that cooler temperatures typically seen during winter months carried an increased risk of falling for older adults.

Additional research is needed, most likely examining the climate one lives in. However, the findings are relevant and can be used to inform health-care providers and older adults of the increased risk of falling during the winter.

This study aims to predict overnight stays in Italy at tourist accommodation facilities through a nonlinear, single factor, stochastic model called CIR#. The contribution of this study is twofold: in terms of forecast accuracy and in terms of parsimony (both from the perspective of the data and the complexity of the modeling), especially when a regular pattern in the time series is disrupted. This study shows that the CIR# not only performs better than the considered baseline models but also has a much lower error than other additional models or approaches reported in the literature.

Typically, tourism demand tends to follow regular trends, such as low and high seasons on a quarterly/monthly level and weekends and holidays on a daily level. The data set consists of nights spent in Italy at tourist accommodation establishments as collected on a monthly basis by Eurostat before and during the COVID-19 pandemic breaking regular patterns.

Traditional tourism demand forecasting models may face challenges when massive amounts of search intensity indices are adopted as tourism demand indicators. In addition, given the importance of accurate forecasts, many studies have proposed novel hybrid models or used various combinations of methods. Thus, although there are clear benefits in adopting more complex approaches, the risk is that of dealing with unwieldy models. To demonstrate how this approach can be fruitfully extended to tourism, the accuracy of the CIR# is tested by using standard metrics such as root mean squared errors, mean absolute errors, mean absolute percentage error or average relative mean squared error.

The CIR# model is notably simpler than other models found in literature and does not rely on black box techniques such as those used in neural network (NN) or data science-based models. The carried analysis suggests that the CIR# model outperforms other reference predictions in terms of statistical significance of the error.

The proposed model stands out for being a viable option to the Holt–Winters (HW) model, particularly when dealing with irregular data.

The proposed model has demonstrated superiority even when compared to other models in the literature, and it can be especially useful for tourism stakeholders when making decisions in the presence of disruptions in data patterns.

The novelty lies in the fact that the proposed model is a valid alternative to the HW, especially when the data are not regular. In addition, compared to many existing models in the literature, the CIR# model is notably simpler and more transparent, avoiding the “black box” nature of NN and data science-based models.

一般来说, 旅游需求往往遵循规律的趋势, 例如季度/月的淡季和旺季, 以及日常的周末和假期。该数据集包括欧盟统计局在打破常规模式的2019冠状病毒病大流行之前和期间每月收集的在意大利旅游住宿设施度过的夜晚。

本研究旨在通过一个名为cir#的非线性单因素随机模型来预测意大利游客住宿设施的过夜住宿情况。这项研究的贡献是双重的:在预测准确性方面和在简洁方面(从数据和建模复杂性的角度来看), 特别是当时间序列中的规则模式被打乱时。我们表明, cir#不仅比考虑的基线模型表现更好, 而且比文献中报告的其他模型或方法具有更低的误差。

当大量搜索强度指标被作为旅游需求指标时, 传统的旅游需求预测模型将面临挑战。此外, 鉴于准确预测的重要性, 许多研究提出了新的混合模型或使用各种方法的组合。因此, 尽管采用更复杂的方法有明显的好处, 但风险在于处理难使用的模型。为了证明这种方法能有效地扩展到旅游业, 使用RMSE、MAE、MAPE或AvgReIMSE等标准指标来测试cir#的准确性。

cir#模型明显比文献中发现的其他模型简单, 并且不依赖于黑盒技术, 例如在神经网络或基于数据科学的模型中使用的技术。所进行的分析表明, cir#模型在误差的统计显著性方面优于其他参考预测。

这个模型作为Holt-Winters模型的一个拟议模型, 特别是在处理不规则数据时。

即使与文献中的其他模型相比, 所提出的模型也显示出优越性, 并且在数据模式中断时对旅游利益相关者做出决策特别有用。

创新之处在于所提出的模型是Holt-Winters模型的有效替代方案, 特别是当数据不规律时。此外, 与文献中的许多现有模型相比, cir#模型明显更简单、更透明, 避免了神经网络和基于数据科学的模型的“黑箱”性质。

Normalmente, la demanda turística tiende a seguir tendencias regulares, como temporadas altas y bajas a nivel trimestral/mensual y fines de semana y festivos a nivel diario. El conjunto de datos consiste en las pernoctaciones en Italia en establecimientos de alojamiento turístico recogidas mensualmente por Eurostat antes y durante la pandemia de COVID-19, rompiendo los patrones regulares.

El presente estudio pretende predecir las pernoctaciones en Italia en establecimientos de alojamiento turístico mediante un modelo estocástico no lineal de un solo factor denominado CIR#. La contribución de este estudio es doble: en términos de precisión de la predicción y en términos de parsimonia (tanto desde la perspectiva de los datos como de la complejidad de la modelización), especialmente cuando un patrón regular en la serie temporal se ve interrumpido. Demostramos que el CIR# no sólo aplica mejor que los modelos de referencia considerados, sino que también tiene un error mucho menor que otros modelos o enfoques adicionales de los que se informa en la literatura.

Los modelos tradicionales de previsión de la demanda turística pueden enfrentarse a desafíos cuando se adoptan cantidades masivas de índices de intensidad de búsqueda como indicadores de la demanda turística. Además, dada la importancia de unas previsiones precisas, muchos estudios han propuesto modelos híbridos novedosos o han utilizado diversas combinaciones de métodos. Así pues, aunque la adopción de enfoques más complejos presenta ventajas evidentes, el riesgo es el de enfrentarse a modelos poco manejables. Para demostrar cómo este enfoque puede extenderse de forma fructífera al turismo, se comprueba la precisión del CIR# utilizando métricas estándar como RMSE, MAE, MAPE o AvgReIMSE.

El modelo CIR# es notablemente más sencillo que otros modelos encontrados en la literatura y no se basa en técnicas de caja negra como las utilizadas en los modelos basados en redes neuronales o en la ciencia de datos. El análisis realizado sugiere que el modelo CIR# supera a otras predicciones de referencia en términos de significación estadística del error.

El modelo propuesto destaca por ser una opción viable al modelo Holt-Winters, sobre todo cuando se trata de datos irregulares.

El modelo propuesto ha demostrado su superioridad incluso cuando se compara con otros modelos de la bibliografía, y puede ser especialmente útil para los agentes del sector turístico a la hora de tomar decisiones cuando se producen alteraciones en los patrones de datos.

La novedad radica en que el modelo propuesto es una alternativa válida al Holt-Winters especialmente cuando los datos no son regulares. Además, en comparación con muchos modelos existentes en la literatura, el modelo CIR# es notablemente más sencillo y transparente, evitando la naturaleza de “caja negra” de los modelos basados en redes neuronales y en ciencia de datos.

Tropical wetland ecosystems are threatened by climate change but also play a key role in its mitigation and adaptation through management of land use and other drivers. Local-level assessments are needed to support evidence-based wetland management in the face of climate change. This study aims to examine the local communities’ knowledge and perception of climate change in Yala wetland, Kenya, and compare them with observed data on climate trends. Such comparisons are useful to inform context-specific climate change adaptation actions.

The study used a mixed methods approach that combined analysis of climate data with perceptions from the local community. Gridded data on temperature and rainfall for the period from 1981 to 2018 were compared with data on climate change perceptions from semi-structured questionnaires with 286 key informants and community members.

Majority of the respondents had observed changes in climate parameters – severe drought (88.5%), increased frequency of floods (86.0%) and irregular onset and termination of rains (90.9%) in the past 20 years. The perceptions corresponded with climate trends that showed a significant increasing trend in the short rains and the average maximum temperature, high incidence of very wet years and variability in onset and termination of rainfall between 1981 and 2018. Gender, age and education had little influence on knowledge and awareness of climate change, except for frequency of floods and self-reported understanding of climate change. The community perceived the wetland to be important for climate change adaptation, particularly the provision of resources such as grazing grounds during drought.

The study faced challenges of low sample size, use of gridded climate data and reproducibility in other contexts. The results of this study apply to local communities in a tropical wetland in Western Kenya, which has a bi-modal pattern of rainfall. The sample of the study was regional and may therefore not be representative of the whole of Kenya, which has diverse socioeconomic and ecological contexts. Potential problems have been identified with the use of gridded data (for example, regional biases in models), although their usefulness in data scarce contexts is well established. Moreover, the sample size has been found to be a less important factor in research of highly complex socio-ecological systems where there is an attempt to bridge natural and social sciences.

This study addresses the paucity of studies on climate change trends in papyrus wetlands of sub-Saharan Africa and the role of local knowledge and perceptions in influencing the management of such wetlands. Perceptions largely influence local stakeholders’ decisions, and a study that compares perceptions vs “reality” provides evidence for engagement with the stakeholders in managing these highly vulnerable ecosystems. The study showed that the local community’s perceptions corresponded with the climate record and that adaptation measures are already ongoing in the area.

This study presents a case for the understanding of community perceptions and knowledge of climate change in a tropical wetland under threat from climate change and land use change, to inform management under a changing climate.

This paper was set to develop a model for forecasting maize production in Tanzania using the autoregressive integrated moving average (ARIMA) approach. The aim is to forecast future production of maize for the next 10 years to help identify the population at risk of food insecurity and quantify the anticipated maize shortage.

Annual historical data on maize production (hg/ha) from 1961 to 2021 obtained from the FAOSTAT database were used. The ARIMA method is a robust framework for forecasting time-series data with non-seasonal components. The model was selected based on the Akaike Information Criteria corrected (AICc) minimum values and maximum log-likelihood. Model adequacy was checked using plots of residuals and the Ljung-Box test.

The results suggest that ARIMA (1,1,1) is the most suitable model to forecast maize production in Tanzania. The selected model proved efficient in forecasting maize production in the coming years and is recommended for application.

The study used partially processed secondary data to fit for Time series analysis using ARIMA (1,1,1) and hence reliable and conclusive results.

The variance between the winning bid and the owner's estimated cost (OEC) is one of the construction management risks in the pre-tendering phase. The study aims to enhance the quality of the owner's estimation for predicting precisely the contract cost at the pre-tendering phase and avoiding future issues that arise through the construction phase.

This paper integrated artificial neural networks (ANN), deep neural networks (DNN) and time series (TS) techniques to estimate the ratio of a low bid to the OEC (R) for different size contracts and three types of contracts (building, electric and mechanic) accurately based on 94 contracts from King Saud University. The ANN and DNN models were evaluated using mean absolute percentage error (MAPE), mean sum square error (MSSE) and root mean sums square error (RMSSE).

The main finding is that the ANN provides high accuracy with MAPE, MSSE and RMSSE a 2.94%, 0.0015 and 0.039, respectively. The DNN's precision was high, with an RMSSE of 0.15 on average.

The owner and consultant are expected to use the study's findings to create more accuracy of the owner's estimate and decrease the difference between the owner's estimate and the lowest submitted offer for better decision-making.

This study fills the knowledge gap by developing an ANN model to handle missing TS data and forecasting the difference between a low bid and an OEC at the pre-tendering phase.

An unreliable supply of grid electricity has a strong negative impact on industrial and commercial profitability as well as on household activities and government services that rely on electricity supply. This unreliable grid electricity could be a result of technical and security factors affecting the grid network. Therefore, this study aims to investigate the effects of technical and security factors on the transmission and distribution of grid electricity in Uganda.

This study used the ordinary least squares (OLS) and autoregressive distributed lag (ARDL) models to examine the effects of technical and security factors on grid electricity reliability in Uganda. The study draws upon secondary time series monthly data sourced from the Uganda Electricity Transmission Company Limited (UETCL) government utility, which transmits electricity to both distributors and grid users. Additionally, data from Umeme Limited, the largest power distribution utility in Uganda, were incorporated into the analysis.

The findings revealed that technical faults, failed grid equipment, system overload and theft and vandalism affected grid electricity reliability in the transmission and distribution subsystems of the Ugandan power grid network. The effect was computed both in terms of frequency and duration of power outages. For instance, the number of power outages was 116 and 2,307 for transmission and distribution subsystems, respectively. In terms of duration, the power outages reported on average were 1,248 h and 5,826 h, respectively, for transmission and distribution subsystems.

This paper investigates the effects of technical and security factors on the transmission and distribution grid electricity reliability, specifically focusing on frequency and duration of power outages, in the Ugandan context. It combines both OLS and ARDL models for analysis and adopts the systems reliability theory in the area of grid electricity reliability research.

This study aims to construct an evaluation system for farmers’ livelihood capital in minority areas and evaluate the impact of relocation in response to climate change on farmers’ livelihood capital.

According to the characteristics of Yunnan minority areas, the livelihood capital of farmers in minority areas is divided into natural, physical, financial, social, human and cultural capital. The improved livelihood capital evaluation system measures farmers’ livelihood capital from 2015 to 2021. The net impact of relocation on farmers’ livelihood capital was separated using propensity score matching and the difference-in-difference (PSM-DID) method.

The shortage of livelihood capital makes it difficult for farmers to resist climate change, and the negative impacts of climate change further aggravate their livelihood vulnerability and reduce their livelihood capital. Relocation has dramatically increased the livelihood capital of farmers living in areas with poor natural conditions by 15.67% and has enhanced their ability to cope with climate change and realise sustainable livelihoods.

An improved livelihood capital evaluation system is constructed to realise the future localisation and development of livelihood capital research. The PSM-DID method was used to overcome endogeneity problems and sample selection bias of the policy evaluation methods. This study provides new ideas for academic research and policy formulation by integrating climate change, poverty governance and sustainable livelihoods.

This study aims to explore the smallholder farmers’ perceptions of climate change and its adaptation options (changing crop variety; improved crop and livestock; soil and water conservation [SWC]; and irrigation practices) and drought indices in the Dire Dawa Administration Zone, Eastern Ethiopia.

A cross-sectional household survey was used. A structured interview schedule for respondent households for key informants and focus group discussions were used. This study used both descriptive statistics and an econometric model. The model was used to compute the determinants of climate adaptation options in the study area. Drought characterization was carried out by DrinC software.

The results revealed households adapted to selected adaptation options. The model results confirmed that education level, farm size, tropical livestock units (TLUs) and access to agricultural extension services have positive and significant impacts on changing crop variety by 0.0014%, 0.045%, 0.032% and 0.035%, respectively. The likelihood of farmers’ decisions to use adaptation strategies (family size, TLU, agricultural extension service and distance from the market) has positive and significant impacts on SWC. The reconnaissance drought index (RDI6) of ONDJFM and AMJJAS showed extreme and severe drought index values of −2.88 and −1.96, respectively.

This study used a locally adopted climate change adaptation intervention for smallholder farmers, revealing the importance of drought characterization indices both seasonally and annually.

The purpose of this paper was to examine smallholder farmers’ perceptions of climate change risks, adaptation responses and the links between adaptation strategies and perceived/experienced climate change risks in South Gondar, Ethiopia.

This paper used a convergent mixed methods design, which enables us to concurrently collect quantitative and qualitative data. Survey data was collected from 352 households, stratified into Lay Gayint 138 (39%), Tach Gayint 117 (33%) and Simada district 97 (28%). A four-point Likert scale was used to produce a standardised risk perception index for 14 climate events. Moreover, using a one-way analysis of variance, statistical differences in selecting adaptation strategies between the three districts were measured. A post hoc analysis was also carried out to identify the source of the variation. The findings of this paper are supplemented by qualitative data gathered through focus group discussions and key informant interviews of households who were chosen at random.

The standardised climate change risk perception index suggests that persistent drought, delayed onset of rainfall, early termination of rainfall and food insecurity were the major potentially dangerous climate change risks perceived by households in the study area. In response to climate change risks, households used several adaptation strategies such as adjusting crop planting dates, crop diversification, terracing, tree planting, cultivating drought-tolerant crop varieties and off-farm activities. A Tukey’s post hoc test revealed a significant difference in off-farm activities, crop diversification and planting drought-tolerant crop types among the adaptation strategies in the study area between Lay Gayint and Simada districts (p < 0.05). This difference reconfirms that adaptation strategies are location-specific.

Although many studies are available on coping and adaptation strategies to climate change, this paper is one of the few studies focusing on the linkages between climate change risk perceptions and adaptation responses of households in the study area. The findings of this paper could be helpful for policymakers and development practitioners in designing locally specific, actual adaptation options that shape adaptation to recent and future climate change risks.