Search results

Recommendation systems are a fundamental tool for hotels to adopt a differentiating competitive strategy. The main purpose of this work is to use machine learning techniques to treat imbalanced data sets, not applied until now in the tourism field. These techniques have allowed the authors to analyse the influence of imbalance data on hotel recommendation models and how this phenomenon affects client dissatisfaction.

An opinion survey was conducted among hotel customers of different categories in 120 different countries. A total of 135.102 surveys were collected over eleven quarters. A longitudinal design was conducted during this period. A binary logistic model was applied using the function generalized lineal model (GLM).

Through the analysis of a representative amount of data, the authors empirically demonstrate that the imbalance phenomenon is systematically present in hotel recommendation surveys. In addition, the authors show that the imbalance exists independently of the period in which the survey is done, which means that it is intrinsic to recommendation surveys on this topic. The authors demonstrate the improvement of recommendation systems highlighting the presence of imbalance data and consequences for marketing strategies.

The main contribution of the current work is to apply to the tourism sector the framework for imbalanced data, typically used in the machine learning, improving predictive models.

The purpose of this paper is to analyze the aftermath of business failure (BF) by addressing: how the individual progressed and developed new ventures, how individuals changed business behaviors and practices in light of a failure, and what was the effect of previous failure on the individual’s decisions to embark on subsequent ventures.

The authors resort to qualitative methods to understand the aftermath of BF from a retrospective point of a successful entrepreneur. Specifically, the authors undertook semi-structured interviews to six entrepreneurs, three from the north of Europe and three from the south and use interpretative phenomenological analysis.

The authors found that previous failure impacted individuals strongly, being shaped by the individual’s experience and age, and their perception of blame for the failure. An array of moderator costs was identified, ranging from antecedents to institutions that were present in the individual’s lives. The outcomes are directly relatable to the failed experience by the individual. The authors also found that the failure had a significant effect on the individual’s career path.

While predicting the failure of healthy firms or the discovery of the main determinants that lead to such an event have received increasingly more attention in the last two decades, the focus on the consequences of BF is still lagging behind. The present study fills this gap by analyzing the aftermath of BF.

Time pressure may change how people behave. The multiplicity of options and the nature of the products, hedonic or utilitarian, might increase the complexity of the choice and alter the effects of time pressure. Combining both factors, the purpose of this paper is to verify the moderating role played by the nature of the products observing the relationship between interaction (time pressure × multiplicity of options) and choice delay.

A two-level factorial experimental design was applied (time pressure: with; without) × 2 (number of alternatives: two; six) × 2 (type of purchase: hedonic; utilitarian), with mixed design, considering the purchase delay a dependent variable.

The results signal that the nature of the products moderates the effects of the interaction between time pressure and choice overload in purchase delay. Utilitarian purchases are more susceptible to the effects of time pressure and options overload than hedonic purchases.

The interaction between time pressure and choice overload, researched in previous works, influences in different ways the purchase of utilitarian or hedonic products. This differentiation, taking into consideration the type of product, brings new perspectives on the purchase decision process and provides theoretical and practical information on the effects of information overload and time pressure over the consumer decision-making process.

This study aims to examine adolescents’ social media environment connected to unhealthy food marketing. As social media have become a ubiquitous part of young people’s everyday lives, marketers have also shifted their focus to these channels. Literature on this phenomenon is still scarce and often takes a quite narrow view of the role of marketing in social media. Furthermore, the experiences of the adolescents are seldom considered.

Using a sociocultural approach and netnographic methodology, this study presents findings from a research project conducted in Finland. The data consist of both social media material and focus group interviews with adolescents.

The findings elaborate on unhealthy food marketing to adolescents in social media from two perspectives: sociocultural representations of unhealthy foods in social media marketing and social media influencers connecting with adolescents.

The study broadens and deepens the current understanding of unhealthy food marketing to adolescents taking place in social media. The study introduces a novel perspective to the topic by looking at it as a sociocultural phenomenon.

Ensuring quality is one of the most significant challenges in microtask crowdsourcing tasks. Aggregation of the collected data from the crowd is one of the important steps to infer the correct answer, but the existing study seems to be limited to the single-step task. This study aims to look at multiple-step classification tasks and understand aggregation in such cases; hence, it is useful for assessing the classification quality.

The authors present a model to capture the information of the workflow, questions and answers for both single- and multiple-question classification tasks. They propose an adapted approach on top of the classic approach so that the model can handle tasks with several multiple-choice questions in general instead of a specific domain or any specific hierarchical classifications. They evaluate their approach with three representative tasks from existing citizen science projects in which they have the gold standard created by experts.

The results show that the approach can provide significant improvements to the overall classification accuracy. The authors’ analysis also demonstrates that all algorithms can achieve higher accuracy for the volunteer- versus paid-generated data sets for the same task. Furthermore, the authors observed interesting patterns in the relationship between the performance of different algorithms and workflow-specific factors including the number of steps and the number of available options in each step.

Due to the nature of crowdsourcing, aggregating the collected data is an important process to understand the quality of crowdsourcing results. Different inference algorithms have been studied for simple microtasks consisting of single questions with two or more answers. However, as classification tasks typically contain many questions, the proposed method can be applied to a wide range of tasks including both single- and multiple-question classification tasks.