User Profiling Based on Nonlinguistic Audio Data

User profiling refers to inferring people’s attributes of interest ( AoIs ) like gender and occupation, which enables various applications ranging from personalized services to collective analyses. Massive nonlinguistic audio data brings a novel opportunity for user profiling due to the prevalence of studying spontaneous face-to-face communication. Nonlinguistic audio is coarse-grained audio data without linguistic content. It is collected due to privacy concerns in private situations like doctor-patient dialogues. The opportunity facilitates optimized organizational management and personalized healthcare, especially for chronic diseases. In this article, we are the first to build a user profiling system to infer gender and personality based on nonlinguistic audio. Instead of linguistic or acoustic features that are unable to extract, we focus on conversational features that could reflect AoIs. We firstly develop an adaptive voice activity detection algorithm that could address individual differences in voice and false-positive voice activities caused by people nearby. Secondly, we propose a gender-assisted multi-task learning method to combat dynamics in human behavior by integrating gender differences and the correlation of personality traits. According to the experimental evaluation of 100 people in 273 meetings, we achieved 0.759 and 0.652 in F1-score for gender identification and personality recognition, respectively.

The Phenomenon of Value Co-Creation and Its Place in Air Transport

It is known that businesses are looking for different ways to reach customers, both technologically and through employees, in order to protect their existing customers as well as to gain new customers. However, today, due to the personable approaches of services, there is a need to create a bond between the business and the customer. In this context, value is an original understanding that people have, and businesses aim to create value together by reaching more customers through personalized services. Thus, the importance of studies aimed at understanding this phenomenon based on multilateral profit relationship is increasing day by day. In the current study, the approach of creating value together is discussed, and the understanding of the creation of value together in air transportation operating in the service sector is examined.

A Comprehensive Systematic Literature Review About Smartness in Tourism

With the rapidly developing technology, the tourism experience has started to enrich and innovative/personalized services and competitive advantage in tourism have started to gain importance. Smartness in tourism refers to tourism activities supported by technology. This study aims to classify the current literature on the subject of smartness in tourism. First of all, a qualitative research was carried out by explaining the concepts of smart tourism and smart tourism destination in the literature. Within the scope of the research, a qualitative research was conducted using systematic literature review method. In the research, 264 academic publications related to smartness in tourism were analyzed in terms of the destinations where they were applied, the scope of the journals they were published, the language of the publication, the methods and approaches, and suggestions were made for further studies.

Emphasizing the Digital Shift of Hospitality Towards Hyper-Personalization

This chapter aims to review the tech evolution in hospitality, from services to eServices, that will provide hyper-personalization in the hospitality field. In the past, the services were provided by hotels through diligent staff and supported by standardized and weak technology that was not allowed to provide personalized services by itself. Therefore, the study applied K-means and FCM clustering algorithms to cluster online travelers' reviews from TripAdvisor. The study shows that K-means clustering outperforms fuzzy c-means in this study in terms of accuracy and execution time while fuzzy c-means converge faster than K-means clustering in terms of the number of iterations. K-means achieved 93.4% accuracy, and fuzzy c-means recorded 91.3% accuracy.

OUPIP

This article aims to propose an ontological user model called OUPIP (Ontology-Based User Profile for Impairment Person), that extends existing ontologies to help designers and developers to adapt applications and devices according to the user's profile, disability and dynamic context. Besides, the approach has been applied in a typical real-life scenario in which personalized services are provided to impairment person through a mobile phone.

Effects of Customer Experience Factors on Beauty Product Satisfaction in Beauty Live Commerce: -For women in their 20s and 30s in Zhejiang Province, China-

This study was conducted from March 29th to April 25th 2021 to investigate the effect of customer experience factors on beauty product satisfaction in beauty live commerce, focusing on women in their 20s and 30s who watched Chinese beauty live commerce broadcasts and purchased beauty products. By the 25th, WeChat and WenJuanXing program were used to analyze 323 copies investigated. For data analysis, we used t-test, one-way ANOVA, Scheffe's multiple range test, Correlation Analysis, and Multiple Regression Analysis on the basis of SPSSWIN 21.0 program, and the results are as follows. The group is generally characterized as women in their 20-30's years old and unmarried. Their final educational background is a university degree, and the monthly income is less than 1 million to 2 million won. Occupation among them is highest as a profession. The average of all customer experience factors of beauty products was 3.64, and the average of the overall satisfaction with beauty products was 3.68, which was high. There are significant differences in customer experience factors and satisfaction with beauty products in different occupations. It is found that both the quantitative and qualitative services of beauty product satisfaction are significantly positively correlated with the customer experience factors of beauty products. The results confirmed that customer experience factors such as information provision services and personalized services in Beauty Live Commerce have a great impact on the satisfaction of beauty products. Proposed direction of the services provided, in order to make more effective use of Chinese women live beauty product marketing business in the future.

Personalized API Recommendations

Application Programming Interfaces (APIs) play an important role in modern software development. Developers interact with APIs on a daily basis and thus need to learn and memorize those APIs suitable for implementing the required functions. This can be a burden even for experienced developers since there exists a mass of available APIs. API recommendation techniques focus on assisting developers in selecting suitable APIs. However, existing API recommendation techniques have not taken the developers personal characteristics into account. As a result, they cannot provide developers with personalized API recommendation services. Meanwhile, they lack the support for self-defined APIs in the recommendation. To this end, we aim to propose a personalized API recommendation method that considers developers’ differences. Our API recommendation method is based on statistical language. We propose a model structure that combines the N-gram model and the long short-term memory (LSTM) neural network and train predictive models using API invoking sequences extracted from GitHub code repositories. A general language model trained on all sorts of code data is first acquired, based on which two personalized language models that recommend personalized library APIs and self-defined APIs are trained using the code data of the developer who needs personalized services. We evaluate our personalized API recommendation method on real-world developers, and the experimental results show that our approach achieves better accuracy in recommending both library APIs and self-defined APIs compared with the state-of-the-art. The experimental results also confirm the effectiveness of our hybrid model structure and the choice of the LSTM’s size.

Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network

In the era of Web 2.0, there is a huge amount of user-generated content, but the huge amount of unstructured data makes it difficult for merchants to provide personalized services and for users to extract information efficiently, so it is necessary to perform sentiment analysis for restaurant reviews. The significant advantage of Bi-GRU is the guaranteed symmetry of the hidden layer weight update, to take into account the context in online restaurant reviews and to obtain better results with fewer parameters, so we combined Word2vec, Bi-GRU, and Attention method to build a sentiment analysis model for online restaurant reviews. Restaurant reviews from Dianping.com were used to train and validate the model. With F1-score greater than 89%, we can conclude that the comprehensive performance of the Word2vec+Bi-GRU+Attention sentiment analysis model is better than the commonly used sentiment analysis models. We applied deep learning methods to review sentiment analysis in online food ordering platforms to improve the performance of sentiment analysis in the restaurant review domain.

Measuring tourist behavioral intentions after the first outbreak of COVID-19 pandemic crisis. Prima facie evidence from the Greek market

Purpose COVID-19 pandemic crisis has led the scientific community in continuous efforts to estimate its impact on tourism. UNWTO predictions indicated a decline in international tourist arrivals and the respective loss in revenues generated by tourist activity for the first year of the pandemic. Undoubtedly, such an impact may not be the same for every country, especially on a domestic level. In fact, the recovery process upon COVID-19 suggests domestic tourism as the driving force. Therefore, this paper aims to investigate the tourist behavioral intentions after the first outbreak of COVID-19 with evidence from the Greek market. Design/methodology/approach A primary survey with questionnaires distributed via online channels (email and social media) has been undertaken to focus on the travelers’ preferences when it comes to the main parts that compose the holiday travel (destination, transport mode, accommodation type). Additionally, there were questions regard to their perceptions on the international norms of health protection against the virus. Findings The results of the survey illustrate some prima facie evidence of tourist behavioral intentions of Greeks, upon a statistical analysis, which indicates preference in domestic tourism and personalized services, issues related with travel costs and health safety awareness, toward tourism recovery process and customers’ reengagement and trust to the tourism businesses and destinations. Originality/value As Greece is a popular destination that includes a plethora of tourism cities, this paper illustrates the intentions of Greeks toward tourism activity upon pandemic crisis, when it comes to their travel preferences, as well as their perceptions on health and safety protocols applied in destinations and tourism businesses.

MNCF: Prediction Method for Reliable Blockchain Services under a BaaS Environment

Blockchain is an innovative distributed ledger technology that is widely used to build next-generation applications without the support of a trusted third party. With the ceaseless evolution of the service-oriented computing (SOC) paradigm, Blockchain-as-a-Service (BaaS) has emerged, which facilitates development of blockchain-based applications. To develop a high-quality blockchain-based system, users must select highly reliable blockchain services (peers) that offer excellent quality-of-service (QoS). Since the vast number of blockchain services leading to sparse QoS data, selecting the optimal personalized services is challenging. Hence, we improve neural collaborative filtering and propose a QoS-based blockchain service reliability prediction algorithm under BaaS, named modified neural collaborative filtering (MNCF). In this model, we combine a neural network with matrix factorization to perform collaborative filtering for the latent feature vectors of users. Furthermore, multi-task learning for sharing different parameters is introduced to improve the performance of the model. Experiments based on a large-scale real-world dataset validate its superior performance compared to baselines.