Search results

The COVID-19 pandemic severely impacted tourism, and the hotel and restaurant industry was the most affected sector, which faced issues related to business uncertainty and unemployment during the crisis. The analysis of recovery time and the influence factors is significant to support policymakers in developing an effective response and mitigating the risks associated with the tourism crisis. This study aims to investigate numerous factors affecting the recovery time of the hotel and restaurant sector after the COVID-19 crisis by using survival analysis.

This study uses the quarterly value added with the observation time from quarter 1 in 2020 to quarter 1 in 2023 to measure the recovery status. The recovery time refers to the number of quarters needed for the hotel and restaurant sector to get value added equal to or exceed the value added before the crisis. This study applies survival models, including lognormal regression, Weibull regression, and Cox regression, to investigate the effect of numerous factors on the hazard ratio of recovery time of hotels and restaurants after the COVID-19 crisis. This model accommodates all cases, including “recovered” and “not recovered yet” areas.

The empirical findings represented that the Cox regression model stratified by the area type fit the data well. The priority tourism areas had a longer recovery time than the non-priority areas, but they had a higher probability of recovery from a crisis of the same magnitude. The size of the regional gross domestic product, decentralization funds, multiplier effect, recovery time of transportation, and recovery time of the service sector had a significant impact on the probability of recovery.

This study contributes to the literature by examining the recovery time of the hotel and restaurant sector across Indonesian provinces after the COVID-19 crisis. Employing survival analysis, this study identifies the pivotal factors affecting the probability of recovery. Moreover, this study stands as a pioneer in investigating the multiplier effect of the regional tourism and its impact on the speed of recovery.

The tourism multiplier effect (TME) is the total economic impact of tourism demand, representing the linkages between tourism and other businesses in an area. However, study about it is limited in Indonesia, especially at the provincial level and after the COVID-19 crisis. This study aims to estimate the TME in all provinces of Indonesia, test its differences in priority and non-priority areas before and after the COVID-19 crisis, analyze its spatial distribution and examine the determinant factor of TME

This study applies an input-output model to measure the TME of all provinces in Indonesia, an independent sample t-test to examine the similarity of TME in priority and nonpriority areas, a paired sample t-test to examine the similarity of it before and after the COVID-19 crisis, and spatial analysis to check its spatial relationship.

The result shows that regional TME ranges from 1.25 to 2.05 in 2019, which changed slightly over time. The empirical result shows the TME difference before and after the COVID-19 crisis, and there is a spatial correlation in terms of TME with the hot spots are clustered in the eastern region of Indonesia, However, there was a slight change in the position of hot spots during the COVID-19 crisis. Moreover, the spatial model shows that value-added and employment in agriculture, manufacturing, trade and transportation affect the size of TME.

This study contributes to the academic literature by providing the first estimate of the TME at the provincial level in Indonesia, comparing the it in priority and non-priority areas before and after the COVID-19 crisis, and mapping its spatial distribution.

Tourism is an essential industry in Indonesia, and understanding its inter-sectoral and inter-regional connections is critical for policy development. This study examines the economic impact of regional tourism in Indonesia and the connections between different tourism-related regions and industries.

This study uses a non-survey method to estimate the inter-regional input-output table (IRIOT) in 2019, backward and forward linkage to identify the role of tourism in the economy, and the structural path analysis (SPA) to identify the inter-sectoral and inter-regional flow of tourism effect. The benchmark IRIOT 2016 published by Badan Pusat Statistik (BPS) serves as the primary data source.

The findings indicate that tourism has a relatively high impact on the overall national economy and plays an essential role in nine provinces. However, this study uses four provinces to represent Indonesian tourism: Jakarta, Jawa Timur, Bali, and Kepulauan Riau. The SPA result captures that Kepulauan Riau Province has the highest tourism multiplier effect and Jawa Timur has the highest coverage value. Moreover, the manufacturing sector receives the most benefit from the tourism effect, followed by trade, construction, agriculture, transportation, and electricity-gas. From a spatial perspective, tourism connections are not solely based on geographical proximity. Instead, they are established through an intricate supply chain network of manufactured goods. This emphasizes the significance of considering supply chain dynamics when investigating inter-regional relationships in the tourism sector.

This research contributes to the literature by estimating the IRIOT in 2019, disaggregating tourism activities from related economic sectors, constructing tourism-extended IRIOT, and identifying the critical path of tourism effect in numerous provinces with different economic structures. This novel approach offers valuable insights into the full spectrum of tourism’s economic impact, which has not been previously explored in this depth. This study is useful for policymaking, investment insight, and disaster mitigation.

The purpose of this paper is to develop a reliable model that would predict the compressive strength of slurry infiltrated fiber concrete (SIFCON) modified with various supplementary cementitious materials (SCMs) using artificial intelligence approach.

This study engaged the artificial intelligence to predict the compressive strength of SIFCON through deep neural networks (DNN), artificial neural networks, linear regression, regression trees, support vector machine, ensemble trees, Gaussian process regression and neural networks (NN). A thorough data set of 387 samples was gathered from relevant studies. Eleven variables (cement, silica fume, fly ash, metakaolin, steel slag, fine aggregates, steel fiber fraction, steel fiber aspect ratio, superplasticizer, water to binder ratio and curing ages) were taken as input to predict the output (compressive strength). The accuracy and reliability of the developed models were assessed using a variety of performance metrics.

The results showed that the DNN (11-20-20-20-1) predicted the compressive strength of SIFCON better than the other algorithms with R² and mean square error yielding 95.89% and 8.07. The sensitivity analysis revealed that steel fiber, cement, silica fume, steel fiber aspect ratio and superplasticizer are the most vital variables in estimating the compressive strength of SIFCON. Steel fiber contributed the highest value to the SIFCON’s compressive strength with 16.90% impact.

This is a novel technique in predicting the compressive strength of SIFCON optimized with different SCMs using supervised learning algorithms, improving its quality and performance.

Highlights in academic papers serve as condensed summaries of the author’s key work, allowing readers to quickly grasp the paper’s focus. However, many journals do not currently offer highlights for their articles. To address this gap, some scholars have explored using supervised learning methods to extract highlights from academic papers. A significant challenge in this approach is the need for substantial amounts of training data.

This study examines the effectiveness of prompt-based learning for generating highlights. We develop task-specific prompt templates, populate them with paper abstracts and use them as input for language models. We employ both locally inferable pre-trained models, such as GPT-2 and T5, and the ChatGPT model accessed via API.

By evaluating the model’s performance across three datasets, we find that the ChatGPT model performed comparably to traditional supervised learning methods, even in the absence of training samples. Introducing a small number of training samples further enhanced the model’s performance. We also investigate the impact of prompt template content on model performance, revealing that ChatGPT’s effectiveness on specific tasks is highly contingent on the information embedded in the prompts.

This study advances the field of automatic highlights generation by pioneering the application of prompt learning. We employ several mainstream pre-trained language models, including the widely used ChatGPT, to facilitate text generation. A key advantage of our method is its ability to generate highlights without the need for training on domain-specific corpora, thereby broadening its applicability.