• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.35-37
• /
• 2021

Analyzing and predicting foreign tourists' demand is a crucial research topic in the tourism industry because it profoundly influences establishing and planning tourism policies. Since foreign tourist data is influenced by various external factors, it has a characteristic that there are many subtle changes over time. Therefore, in recent years, research is being conducted to design a prediction model by reflecting various external factors such as economic variables to predict the demand for tourists inbound. However, the regression analysis model and the recurrent neural network model, mainly used for time series prediction, did not show good performance in time series prediction reflecting various variables. Therefore, we design a foreign tourist demand prediction model that complements these limitations using a convolutional neural network. In this paper, we propose a model that predicts foreign tourists' demand by designing a one-dimensional convolutional neural network that reflects foreign tourist data for the past ten years provided by the Korea Tourism Organization and additionally collected external factors as input variables.

• Journal of Agricultural Extension & Community Development
• /
• v.20 no.2
• /
• pp.511-533
• /
• 2013

The study used a seasonal ARIMA model to forecast the number of tourists to Kyeongju foreign in a uni-variable time series. Time series monthly data for the investigation were collected ranging from 1995 to 2010. A total of 192 observations were used for data analysis. The date showed that a big difference existed between on-season and off-season of the number of foreign tourists in Kyeongju. In the forecast multiplicative seasonal ARIMA(1,1,0) $(4,0,0)_{12}$ model was found the most appropriate model. Results show that the number of tourists was 694 thousands in 2011, 715 thousands in 2012, 725 thousands in 2013, 738 thousands in 2014, and 884 thousands in 2015. It was suggested that the grasping of the Kyeongju forecast model was very important in respect of how experts in tourism development, policy makers or planners would establish marketing strategies to allocate services in Kyeongju as a tourist destination and provide tourism facilities efficiently.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.187-201
• /
• 2022

Online reviews written by tourists provide important information for the management and operation of the tourism industry. The star rating of online reviews is a simple quantitative evaluation of a product or service, but it is difficult to reflect the sincere attitude of tourists. There is also an issue; the star rating and review content are not matched. In this study, a star rating prediction model based on online review content was proposed to solve the discrepancy problem. We compared the differences in star ratings and sentiment by continent through sentiment analysis on tourist attractions and hotels written by foreign tourists who visited Korea. Variables were selected through TF-IDF vectorization and sentiment analysis results. Logit, artificial neural network, and SVM(Support Vector Machine) were used for the classification model, and artificial neural network and SVR(Support Vector regression) were applied for the rating prediction model. The online review rating prediction model proposed in this study could solve inconsistency problems and also could be applied even if when there is no star rating.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.473-474
• /
• 2023

본 연구는 코로나-19 이후로 증가할 것으로 보이는 방한 외국인 관광객의 지역별 소비 경향을 카드 소비 데이터를 데이터베이스화하여 다각적인 방면에서 분석하고 정보를 만들었다. 코로나 이전 'K-pop'과 'K-drama'의 영향으로 계속해서 증가하던 방한 외국인의 수는 코로나의 영향으로 50%가량 감소했다. 하지만 '위드 코로나'로 접어든 지금, 다시금 외국인 관광객을 유치하기 위해선 각 관광객의 니즈에 맞는 서비스를 제공해야 한다. 또한, 각 지자체에서는 외국인 관광객이 선호하는 서비스를 파악하고 각 국적별 관광객에게 맞는 서비스를 제공하는 노력을 통해 지역경제를 활성화시킬 수 있을 것이다. 현재 많은 기업에서 지역별, 업종별로 맞춤 서비스를 제공하는 것처럼, 지자체가 구체적인 데이터를 사용하여 맞춤 서비스를 제공한다면 코로나로 어려운 시기를 슬기롭게 극복할 수 있다고 생각한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.477-478
• /
• 2021

관광관련 광고, 상품판매 촉진, 추천 등을 위해 제주도 관광객의 관심 정보에 있어 기후요소가 끼치는 영향을 분석하고 이를 토대로 예측모델을 개발한다. 예측모델은 입력으로 기온, 강수량, 풍속, 습도, 일사량 및 전운량, 출력으로 가장 관심도가 높은 관광지 유형을 가지며 TMAP의 검색순위 이력 데이터와 기상청의 기후이력 데이터를 다운로드하여 학습패턴을 생성한다. 예측모델은 Sklearn 인공신경망 라이브러리를 이용하여 구현하였으며, 81.8 %의 정확도를 보인다.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.725-732
• /
• 2016

This study analyzes the number of Jeju-bound tourists according to travellers' purposes. We classify the travellers' purposes into three categories: "Rest and Sightseeing", "Leisure and Sport", and "Conference and Business". To see an impact of MERS outbreak occurred in May 2015 on the number of tourists, we fit seasonal ARIMA-Intervention model to the monthly arrivals data from January 2005 to March 2016. The estimation results show that the number of tourists for "Leisure and Sport" and "Conference and Business" were significantly affected by MERS outbreak whereas arrivals for "Rest and Sightseeing" were little influenced. Using the fitted models, we predict the number of Jeju-bound tourists.

• Journal of Navigation and Port Research
• /
• v.33 no.10
• /
• pp.757-769
• /
• 2009

This paper is intended to forecast the demand for tourism of fishing regions and find the public policies to activate it. The paper focuses on the east coast regions in Gangwon-do. The analysis was conducted through time series analyses and surveys of the tourists in the regions. The results of analyses showed that, while the number of tourists(both domestic and foreign) to the regions has increased, the regions have not been able to accommodate them enough to help improve economies of the regions. It was forecasted that the number of tourists will significantly increase in the future. However, that rates of increase, especially the rates of increase of foreign tourists, cannot be evaluated positively compared to those of the past. These results suggested a few local governmental policies to activate tourism in the regions.

• Korean Journal of Environment and Ecology
• /
• v.23 no.5
• /
• pp.460-470
• /
• 2009

The purpose of this research is to suggest appropriate directions for the desirable ecotourist attraction management through the investigation of the tourist's satisfaction with ecotourism in case of Geumgang birdwatching destination. This research focus on the identification of the determinants of the ecotourist's satisfaction and the estimated regression model. The results of this study for the tourist's satisfaction with the ecotourism are summarized as follows. First, as a result of the factor analysis of the tourist's satisfaction variables, five factors like 'knowledge information', 'experience', 'ecological value', 'guide service', 'facilities environment' are deduced. Second, as a result of the test of significance, the difference of the satisfaction with ecotourism in aspect of the tourist's demographic characteristics like age and academic background is confirmed to be statistically significant except sex. Third, the tourist's satisfaction with ecotourism appears to be positively correlative with the tourist's overall satisfaction.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.27 no.1
• /
• pp.15-22
• /
• 2019

This study analyzed the correlation between generation of municipal solid waste (MSW), number of tourists, and area of accommodation facilities of small island such as Shin, Si, Mo and Jangbong island in Ongjin county, Incheon for use as basic data for estimation of MSW generation. An analysis of statistics data from september in 2012 to august in 2018 showed MSW generation was steadily increasing, and MSW generation in 2018 was increased by about 3.98 times compared to 2012. In summer, which is the tourist season, MSW generation was 2.43~9.39 times higher than in winter. MSW generation was influenced by the number of tourists. As of August 2018, generation rate of per capita of MSW was $0.839kg/cap{\cdot}day$, which was about 3.71 times higher than August 2013. Area of accommodation increased continuously from 2008 to 2017, increasing by about 8.32 times. The coefficient of determination between the area of accommodation and the number of tourists was 0.8418. Also coefficient of determination between area of accommodation and MSW generation were 0.9370 and 0.6025 before and after August in 2015, respectively. Accommodation was lacked due to increase of tourists. Although accommodation was scarce because of increase in the number of tourists since 2015, the coefficient of determination decreased due to the increase in waste generation.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.93-101
• /
• 2017

This study investigate the effect of each type of search volume on the number of Facebook fans and the number of tourists. According to the hierarchy effect model, the effect of communication appears to be the sequentiality of cognition-attitude-behavior. Applying this theory, this study predicted that when consumers who have higher involvement and knowledge on specific cities through search behavior, they will be more active in information search through Facebook fan page subscription and will lead to direct tourism behavior. To verify the prediction, we examined the influences among search volume of Seoul shown in Google Trend, the number of fans of official facebook page named 'Seoul Korea', and the number of foreign tourists. As a result, the type of search keyword was divided into four categories: tourism attraction keyword, natural environment keyword, symbolic keyword, and accessibility keyword. The regression analysis showed that tourism attraction keyword and symbolic keyword have influence on Facebook fanpage 'Like'. In addition, facebook fanpage fan size have mediation effect between search volume and number of tourists. All in all, it would be useful to appeal to foreign tourists with a message that emphasizes tourism attraction and Korea-related contents.