1,721,000 research outputs found
A statistical framework for Airbnb hosts and Superhosts
Full text linkWe propose a statistical framework in order to investigate the Airbnb hosts activities. We aim to propose an extended model able rstly to comprehend which variables can impact on the hosts' activity; secondly to identify a guide that can support the hosts in the constant eort to reach the best performances
and to become a Superhost. The framework use two dierent models, the logistic model and the bivariate odds ratio model. Three groups of variables are taken into account. They are the attributes that Airbnb uses to assign the Superhost badge, the managerial aspects and the characteristics of the accommodations. The analysis is focused on the hosts operating in the Italian most visited cities. Our ndings show the capacity of the framework to identify the variables, as for instance the number of reviews, the services, and the typology of the rented accommodation, that aect the hosts' performance.
The results show how the framework can be used as a managerial support for the hosts
The impact of TV series on tourism performance: the case of Game of Thrones
Full text linkTV series and cinema productions are considered one of the most recent and promising instruments to promote tourist destinations and to increase tourist flows. However, a few papers analyze empirically their impact on tourist choices. We contribute to the scarce literature by investigating the impact of one of the most successful TV series of all times: Game of Thrones (GoT). The series was internationally broadcasted and filmed around the world. We focus on fourteen filming locations in three different countries: Spain, Croatia and Malta. To estimate how much of their recent tourism performance is due to the visibility obtained through GoT, we use county-level panel data in the years 2007–2019 and apply an event study design as methodology. We deal with the issue of treatment effect heterogeneity over time and across counties by adopting an interaction-weighted estimator which focuses on season-specific treatment effect. The results show a positive and persistent impact of GoT on tourism performance, on both new tourist arrivals and overnight stays, and are not driven by spillover effects. Overall, findings confirm the ability of TV productions to boost the tourist flows in the filming locations
Iterative Threshold-based Naïve Bayes Classifier: an efficient Tb-NB improvement
No full textWhile analyzing online reviews on Booking.com, we proposed an ad-hoc classification model (Threshold-based Naïve Bayes Classifier, Tb-NB) to evaluate Customer Satisfaction, starting from the reviews' content, and predicting them as positive/negative. The log-likelihood ratios attributed to each word included in a review are then used to estimate a numeric sentiment score. In this paper we propose an improved version of Tb-NB called "iterative" Tb-NB. It results in a second step of Tb-NB: starting from the output of Tb-NB and reclassifying reviews with a probabilistic approach, it refines iteratively the threshold value used to classify a given subset of reviews
Topic based quality indexes assessment through sentiment
Full text linkThis paper proposes a new methodology called TOpic modeling Based Index Assessment through Sentiment (TOBIAS). This method aims at modeling the effects of the topics, moods, and sentiments of the comments describing a phenomenon upon its overall rating. TOBIAS is built combining different techniques and methodologies. Firstly, Sentiment Analysis identifies sentiments, emotions, and moods, and Topic Modeling finds the main relevant topics inside comments. Then, Partial Least Square Path Modeling estimates how they affect an overall rating that summarizes the performance of the analyzed phenomenon. We carried out TOBIAS on a real case study on the university courses’ quality evaluated by the University of Cagliari (Italy) students. We found TOBIAS able to provide interpretable results on the impact of discussed topics by students with their expressed sentiments, emotions, and moods and with the overall rating
From mine industries to a place of culture, tourism, research and higher education: case study of the great mine Serbariu
No full textPurpose – This study aims to explore how closed factories could be transformed and provide a path for sustainable development for a territory. The authors focus on the case of the Great Mine Serbariu, located in Carbonia (Sardinia), which used to be the largest coal mine in Italy between 1939 and 1964.
Design/methodology/approach – The authors adopt a qualitative research design based on an exploratory single-case study, drawing on interviews with the main stakeholders, on a survey conducted among 5,158 visitors, and on administrative documentation of the City Council.
Findings – The analysis of the Great Mine Serbariu case showed that the regeneration of an exhausted mine serves a model of sustainable development, especially for the redevelopment of other urban and industrial degraded areas. The Great mine Serbariu was restored and turned into a place of culture, tourism, research and higher education, with the Italian Cultural Centre of Coal Mining (ICCCM) establishing its headquarters in the heart of the former mine. It attracted almost 220,000 visitors, generating both domestic and international tourist flows and making an industrial heritage a real resource for the area.
Originality/value – This article advances the authors’ understanding of how closed industries could become an instrument for sustainable development on the social, economic, touristic and cultural levels. This study
would help local governments with examples to enhance the historical resources to create a new identity that led to a sustainable development of an urban landscape, and to create networks with other comparable museums all over Europe to better exploit the touristic and cultural potential
From self-perception to feedback: mapping sustainability-oriented self-descriptions to Airbnb reviews
No full textUnderstanding the relationship between self-perception and online feedback is crucial for assessing behavioral consistency in sustainability-oriented consumers. This study examines whether Airbnb users who describe themselves using sustainability-related
terms reflect similar concerns in their reviews. We first filter user self-descriptions based
on sustainability-related keywords and apply topic modeling to both self-descriptions and reviews. To analyze the relationship between self-reported identity and review content, we employ a chi-squared independence test on the dominant topics of self-descriptions and reviews. Additionally, we assess the association between the dominant self-description topic and the dominant emotion expressed in reviews. Our findings provide insights into the extent to which self-declared sustainability orientations influence user-generated content, oering implications for consumer behavior analysis and sustainability communication in online platforms
Application of machine learning models to discriminate tourist landscapes using eye-tracking data
No full textOverlapping coefficient in network-based semi-supervised clustering
Full text linkNetwork-based Semi-Supervised Clustering (NeSSC) is a semi-supervised approach for clustering in the presence of an outcome variable. It uses a classification or regression model on resampled versions of the original data to produce a proximity matrix that indicates the magnitude of the similarity between pairs of observations measured with respect to the outcome. This matrix is transformed into a complex network on which a community detection algorithm is applied to search for underlying community structures which is a partition of the instances into highly homogeneous clusters to be evaluated in terms of the outcome. In this paper, we focus on the case the outcome variable to be used in NeSSC is numeric and propose an alternative selection criterion of the optimal partition based on a measure of overlapping between density curves as well as a penalization criterion which takes accounts for the number of clusters in a candidate partition. Next, we consider the performance of the proposed method for some artificial datasets and for 20 different real datasets and compare NeSSC with the other three popular methods of semi-supervised clustering with a numeric outcome. Results show that NeSSC with the overlapping criterion works particularly well when a reduced number of clusters are scattered localized
- …
