Abstract The Threshold-based Naïve Bayes (Tb-NB) classifier is introduced as a (simple) improved version of the original classifier. Tb-NB extracts sentiment from Natural Language text corpus and allows user not only to predict how much sentence positive (negative) but also quantify with numeric value. It based on estimation single threshold value that concurs define decision rule classifies into opinion its content. One main advantage deriving possibility utilize results input post-hoc...

Abstract TV series and cinema productions are considered one of the most recent promising instruments to promote tourist destinations increase flows. However, a few papers analyze empirically their impact on choices. We contribute scarce literature by investigating successful all times: Game Thrones (GoT). The was internationally broadcasted filmed around world. focus fourteen filming locations in three different countries: Spain, Croatia Malta. To estimate how much tourism performance is...

Purpose This study aims to explore how closed factories could be transformed and provide a path for sustainable development territory. The authors focus on the case of Great Mine Serbariu, located in Carbonia (Sardinia), which used largest coal mine Italy between 1939 1964. Design/methodology/approach adopt qualitative research design based an exploratory single-case study, drawing interviews with main stakeholders, survey conducted among 5,158 visitors, administrative documentation City...

Abstract In this paper, we propose a semi-supervised method to cluster unstructured textual data called sentiment clustering on natural language texts. The aim is identify clusters homogeneous with respect the overall of texts analyzed. combines different techniques and methodologies: Sentiment Analysis, Threshold-based Naïve Bayes classifier, Network-based Semi-supervised Clustering. It involves steps. first step, text transformed into structured text, it categorized positive or negative...

Aim of this paper is to investigate the extent impact Airbnb phenomenon on tourism indicators in general and, particular, sustainable (STI). We conjecture that, notwithstanding correctness STIs construction, these measure partially, since are computed using data recorded by official statistics organisation that do not include information about flows. demonstrate offer a new point view analysis terms sustainability. Results provide evidence substantial presence guests Italy and consequent...

Abstract This paper proposes a new methodology called TOpic modeling Based Index Assessment through Sentiment (TOBIAS). method aims at the effects of topics, moods, and sentiments comments describing phenomenon upon its overall rating. TOBIAS is built combining different techniques methodologies. Firstly, Analysis identifies sentiments, emotions, Topic Modeling finds main relevant topics inside comments. Then, Partial Least Square Path estimates how they affect an rating that summarizes...

Specific and Destination Websites of UNESCO Heritage Sites (WUHS) located in France, Italy Spain are analyzed to investigate if the management is able promote heritages efficiently World Wide Web. Empirical evidence supports idea that WUHS ranking depends on type localization site quantity quality information influences time spent by a user visiting website-page. Therefore, managers could be improve role websites through: a) more efficient incisive promotion or destination; b) design based...

The Covid-19 pandemic is having an unprecedented impact on health systems, many economic sectors and the labour market. This critical situation also accompanied by social destabilisation, which has exacerbated inequalities severely affected most disadvantaged population groups, such as migrant workers. study provides insights into consequences of first wave lockdown period in Spring 2020 Romanians living Italy, using data collected International Association Italy-Romania ‘Cuore Romeno’,...

Following previous research on museum and tourism websites, this study focuses the websites created by UNESCO sites located in France, Italy, Spain to evaluate their information content how it can influence online popularity. Empirical evidence suggests following: a) heritage basically create provide general touristic information; b) use of interactive elements on-sale platforms is limited; c) relevant information, engaging contents, are necessary reach popularity, d) access usually obtained...

Abstract Semisupervised clustering extends standard methods to the semisupervised setting, in some cases considering situations when clusters are associated with a given outcome variable that acts as “noisy surrogate,” is good proxy of unknown structure. In this article, novel approach an named network‐based (NeSSC) introduced. It combines initialization, training and agglomeration phase. initialization matrix pairwise affinity instances estimated by classifier. phase transformed into...

Abstract Network-based Semi-Supervised Clustering (NeSSC) is a semi-supervised approach for clustering in the presence of an outcome variable. It uses classification or regression model on resampled versions original data to produce proximity matrix that indicates magnitude similarity between pairs observations measured with respect outcome. This transformed into complex network which community detection algorithm applied search underlying structures partition instances highly homogeneous...

Abstract In literature, several researchers have discovered that the reviews written about Airbnb accommodation tend to be extremely positive than those published on other famous platforms, consequently, many negative experiences remain untracked. Leaving underrepresented hampers hosts’ ability improve their services. To overcome this gap, we employ Small Area Estimation quantify sentiment in and relative critical topics characterize them. Our methodology involves a two-step process: first,...

To achieve a comprehensive understanding of the factors influencing tourist satisfaction, there has recently been an increasing interest in information provided by online reviews. In this regard, rather unexplored issue concerns causal relationship between topics and emotions expressed consumers written text their overall quality assessment given through rating system. This study aims to contribute filling gap investigating whether are differences coastal inland Sardinian hotels reviewers...

Abstract New forms of hospitality grew increasingly more popular and successful during the last decades. Nowadays, they are chosen for different reasons, one most important certainly being price. Understanding elements that can impact on price determination is crucial to increase profitability. We propose two indicators Airbnb accommodations, which defined in three phases using proportional odds model as a reference model. The first phase focuses probability estimation accommodations...

Aim of this paper is to investigate the extent impact Airbnb phenomenon on tourism indicators in general and, particular, sustainable (STI). We conjecture that, notwithstanding correctness STIs construction, these measure partially, since are computed using data recorded by official statistics organisation that do not include information about flows. demonstrate offer a new point view analysis terms sustainability. Results provide evidence substantial presence guests Italy and consequent...

Abstract We investigated aspects of host activities that influence and enhance performance in an effort to achieve best results terms the occupancy rate overall rating. The measures percentage reserved days with respect available days. rating identifies satisfaction level guests booked Airbnb accommodation. used proportional odds model estimate impact managerial variables characteristics accommodation on performance. Five different levels were understand which features them support move from...