Using deep learning and visual analytics to explore hotel reviews and responses

This study aims to use computational linguistics, visual analytics, and deep learning techniques to analyze hotel reviews and responses collected on TripAdvisor and to identify response strategies. To this end, we collected and analyzed 113,685 hotel reviews and responses and their semantic and syntactic relations. We are among the first to use visual analytics and deep learning-based natural language processing to empirically identify managerial responses. The empirical results indicate that our proposed multi-feature fusion, convolutional neural network model can make different types of data complement each other, thereby outperforming the comparisons. The visualization results can also be used to improve the performance of the proposed model and provide insights into response strategies, which further shows the theoretical and technical contributions of this study.     

Development of a conflict management model as a tool for improved project outcomes in community based tourism

Community based tourism (CBT) offers many opportunities, however, conflict frequently occurs while developing CBT in communities around the world. Despite conflict limiting the potential of CBT, conflict management in CBT has not previously been systematically studied. To investigate conflict and conflict management during CBT, a linear model of conflict management was developed and subsequently tested through a three phase qualitative process: analysis of CBT literature, online international survey of 29 CBT stakeholders, and in-depth interviews of 23 CBT stakeholders. Results endorse the proposed linear model of ‘conflict themes’: an ‘instance’ of conflict, followed by a ‘response’, which results in an ‘impact’. The rich data highlights the complexity involved, which was incorporated into the expanded model with three additional scenarios: ‘new conflict develops’, ‘interrelated conflict themes’, and ‘simultaneous conflict themes’. The complete Conflict Management Model provides stakeholders with a tool to address conflict, thereby improving the outcomes of CBT.     

Seasonality and regional productivity in the Spanish accommodation sector

This study quantifies the impact of peak demand and seasonality on regional productivity in the Spanish accommodation sector. We then identify factors affecting seasonal fluctuations and their relative contributions to regional variations in seasonality. The results show that demand for accommodation in the peak season mainly determines productivity. Thus, improving a region's attractiveness as a tourist destination is most effective for tourism-based regional development. In addition, reducing seasonal variations has a non-negligible impact on productivity. A decomposition analysis reveals that providing climate-independent tourist attractions and attracting business travelers are effective in reducing seasonality.     

基于点轴理论的丝绸之路甘肃段旅游空间结构分析

科学合理地规划区域旅游的空间结构,可以极大地促进该区域旅游业的发展。本文以点轴理论为依据,通过理论分析和定量论证,发现丝绸之路甘肃段旅游空间结构分布着甘肃省数量众多的优质旅游资源、90%的优秀旅游城市和星级饭店、四通八达的交通运输网、较高的旅游总收入及旅游人气,这些都为区域旅游业的全面发展打下了基础提供了保障。丝绸之路甘肃段旅游空间结构的提出对提升甘肃旅游发展水平有着重要的实践意义,有助于甘肃省向旅游强省迈进一步。     

The effects of tourism on HSR: Spanish empirical evidence derived from a multi-criteria corridor selection methodology

The exorbitant cost of new High-Speed Rail (HSR) lines requires a selection methodology to define which HSR corridors within a network should be built first, and the most suitable evaluation tool appears to be the multi-criteria approach. In any corridor-ranking methodology, and especially in countries with high tourism attractiveness, tourism impacts on HSR should be considered as a variable.In addition to economic geography and destination choice models, the current literature on tourism demand is dominated by econometric models using a single-equation time-series based approach. However little research has been done so far on methodologies to rank HSR corridors taking into account the tourism variable. In 2014, a ranking methodology developed by Todorovich and Hagler was validated using the current Spanish HSR network. Twelve variables were used to create an index to assign scores to the city pairs, but tourism was not included as a variable. The findings showed the consistency of the model for ranking pairs mainly in the top O–D relations; however the tool failed to discriminate clearly between secondary groups of corridors.The aim of this paper is to assess empirically the positive effect of tourism on HSR and to enhance the abovementioned ranking tool with a tourism database. The new methodology is tested by application to 1176 city pairs in Spain, and the results clearly show that the implementation of a tourism variable helps discriminate between secondary groups of corridors and offers a more effective approach for determining the implications of tourism on HSR.     

Impacts of seasonal patterns of climate on recurrent fluctuations in tourism demand: Evidence from Aruba

This study estimates the effect of seasonal patterns of pull and push climate elements (rainfall, temperature, wind, and cloud coverage) on recurrent fluctuations in tourism demand from the United States (USA) and Venezuela to Aruba. The seasonal patterns were first isolated from the series using the Census X-12 decomposition method, after which the analysis included panel data unit root testing, panel data regression, and Euclidean distance calculation. The results show that both pull and push seasonal factors of climate were relevant in determining the seasonal variations in tourism demand from both countries. The study derives two theoretical propositions: (1) climate is a significant push and pull factor affecting tourism demand; and (2) tourism demand and climate are bounded by intertemporal climate constraints.     

温泉度假村旅游服务质量评价实证研究——以河源御临门温泉度假村为例

以河源御临门温泉度假村为例,以温泉旅游服务质量评价问卷为基础,对影响温泉旅游服务质量的20个因素进行了分析,探讨游客对温泉度假村整体旅游服务质量的总体评价。建议度假村从"原生态"温泉文化、温泉旅游解说系统的建设、特色客家温泉饮食文化、员工培训等四个方面进行完善与提高,提升服务满意度。     

Short-term forecasting of Japanese tourist inflow to South Korea using Google trends data

We utilize the Internet search data from Google Trends to provide short-term forecasts for the inflow of Japanese tourists to South Korea. We construct the Google variable in a systematic way by combining keywords to minimize mean squared or mean absolute forecasting errors. We augment the Google variable to the standard time-series forecasting models and compare their forecasting accuracies. We find that Google-augmented models perform much better than the standard time-series models in terms of short-term forecasting accuracy. In particular, Google models show better out-of-sample forecasting performance than in-sample forecasting.     

‘Stop Being a Tourist!’ New Dynamics of Urban Tourism in Berlin‐Kreuzberg

Berlin is witnessing a massive tourism boom, and parts of it can be described as ‘new urban tourism’, which shows a preference for off the beaten track areas and ‘authentic’ experiences of the city. This form of tourism seems especially salient in Kreuzberg. It is here that an openly articulated critique of tourism attracted national attention in 2011 and has not ceased to do so since. This article aims to better understand the conflictive potential of (new urban) tourism in Kreuzberg. We argue that the readily expressed negative attitudes against tourists and the easily accepted link between tourism and gentrification have to be explained against the backdrop of certain housing‐market dynamics. Rising rents and a diminution in the number of flats available for rent are fuelling fears of gentrification in Kreuzberg, while the interest shown in new urban tourism and the comparatively low‐priced real‐estate market in Berlin result in a growing number of holiday flats. Although adding only slightly to the tightening of the housing market, holiday flats render complex processes of neighborhood change visible and further sustain an already prevalent tourism critique.     

Reciprocal effect of tourist destinations on the strength of national tourism brands

The assignment of a brand to a product affects consumer's perceptions not only about the product, but also about the brand itself. The reciprocal effect of the product on its brand can be either positive or negative. Extending the concept of reciprocal effect to a new context, this study analyzed how consumer's perceptions about tourist destinations can affect the national tourism brand. An experiment showed that destinations leading to attitudes that are more positive than the average can strengthen the national tourism brand, while destinations leading to attitudes below the average can weaken it. Brand dilution can happen even when the outcome is effective from the destination's perspective. Because of the reciprocal effect, the determination of public policies in the destination level is usually inefficient from the country's perspective. These results reinforce the need for national brand governance.