Table 1 - uploaded by Alireza Alaei
Content may be subject to copyright.
Source publication
Advances in technology have fundamentally changed how information is produced and consumed by all actors involved in tourism. Tourists can now access different sources of information, and they can generate their own content and share their views and experiences. Tourism content shared through social media has become a very influential information s...
Context in source publication
Context 1
... less research has focused on sentence level analysis, since it is more challenging to accurately extract polarity from a small number of words compared with paragraphs and documents (Brob, 2013;Choudhury, 2016;Höpken et al., 2016;Schmunk et al., 2014;Ribeiro et al., 2016). For a clear explanation and understanding of the different sentiment analysis methods, the relevant key terms are defined in Table I. Table 1 here ...
Similar publications
Sentiment analysis refers to the active field of Natural language processing that extracts the attitude and emotion of a human being. With the growth of social media, more people are using online platforms such as Twitter, Facebook, YouTube, etc. to express their opinions. Twitter is considered to be the purest platform to express one’s views. Most...
Sentiment analysis can be used to analyze web material from social media platforms, online products, companies, events, and personnel. Sentiment analysis employs a variety of methodologies to determine a text's or sentence's sentiment. Although gathering input is simple, deriving insights from it is still difficult. The dramatic increase in interne...
![Fig.2 Sentiment analysis process on product reviews [40] Fig. 2 shows...](profile/Akhilesh-Dwivedi-3/publication/328765294/figure/fig2/AS:946834100998145@1602754249487/Sentiment-analysis-process-on-product-reviews-40-Fig-2-shows-the-Feature-Selection_Q320.jpg)
![Fig. 4 Deployment of IoT for BDSA techniques [39]](profile/Akhilesh-Dwivedi-3/publication/328765294/figure/fig3/AS:946834101002248@1602754249514/Deployment-of-IoT-for-BDSA-techniques-39_Q320.jpg)
![Fig. 5 Layered Architecture of IOT deployment for BDSA techniques [49]](profile/Akhilesh-Dwivedi-3/publication/328765294/figure/fig4/AS:946834100994058@1602754249544/Layered-Architecture-of-IOT-deployment-for-BDSA-techniques-49_Q320.jpg)
![Fig. 6 High-Level Architecture of Hadoop [40]](profile/Akhilesh-Dwivedi-3/publication/328765294/figure/fig5/AS:946834100998154@1602754249689/High-Level-Architecture-of-Hadoop-40_Q320.jpg)
![Example images (from the Flickr images collected in [5]) for...](publication/326814837/figure/fig5/AS:941752819126313@1601542777956/Example-images-from-the-Flickr-images-collected-in-5-for-object-based-visual_Q320.jpg)
Social media sentiment analysis (also known as opinion mining) which aims to extract people’s opinions, attitudes and emotions from social networks has become a research hotspot. Conventional sentiment analysis concentrates primarily on the textual content. However, multimedia sentiment analysis has begun to receive attention since visual content s...
Citations
... However, the use of pretrained models in management and hospitality studies remains rare. Alaei et al. [3] encourage tourism researchers to discover data dynamics to gain deeper insights from different aspects of data using deep learning approaches. This study provides important implications for managerial practices. ...
User-generated content has become an essential factor influencing customer choice in the selection of hotel and bed and breakfast (BNB) accommodation. It is important for entrepreneurs to effectively analyze customer reviews. From the perspective of BNB managers, it is necessary to know customer opinions relating to specific aspects of the services they have received. Aspect-based sentiment analysis (ABSA) evaluates customer sentiments and opinions and can be used to improve services. We propose a framework for automated ABSA of reviews. The framework contains modules for data preprocessing, a multi-task Chinese aspect-based sentiment analysis module, and a Kano module. The Kano module divided service attributes into several distinct categories including must-be, one-dimensional, and attractive attributes… and so on. This module is integrated into our analytical framework to elucidate the relationships between hotel service offerings and customer attributes. The framework is used for a dataset crawled from Google Maps hotel reviews with aspect categories labeled by domain experts. The experimental results demonstrate the excellent performance of this method. We categorize customer requirements based on the aggregate consumer preferences estimated by the Kano module. The effectiveness of the proposed framework is demonstrated in an empirical evaluation and the utility of the proposed Kano module demonstrated.
... With the wide application of mobile Internet technology in the development of tourism, big data application is used as the core to enhance the modernization of the tourism industry [6][7][8][9]. Big data technology integrates data involving tourism from transportation, environmental protection, land resources, urban and rural construction, commerce, aviation, postal services, telecommunications, meteorology, and other related aspects while cooperating with major network search engines such as Baidu, Google, Taobao, and other tourism e-operators to establish tourism big data resources that unite social data and data from tourism and related sectors, which provides the characteristic culture and tourism industry with a new opportunity for development and a new driving force [10][11][12]. Accurate analysis of tourism demand is an important research topic in the field of tourism management, which helps the tourism management department to establish the expected judgment on the carrying capacity of tourism destinations and the flow of tourists and to formulate corresponding policies based on the results of the analysis, which can further improve the tourism management system and thus increase the economic returns of local tourism [13][14]. ...
As science and technology advance, the tourism industry is increasingly pivoting towards digital and intelligent transformation. The pivotal role of big data in shaping tourism trends is becoming more apparent. This study leverages big data to explore its impact on tourism development and proposes a big data-based model for this purpose. An influence mechanism model tailored to local tourism’s unique characteristics was developed to guide this analysis. Employing data mining techniques, this research utilizes the association rule model to forecast local tourism trends. Additionally, it applies heat evaluation and hotspot analysis models to examine local tourism activities. Spatial characteristics of local tourism are investigated using the nearest neighbor algorithm. An empirical study conducted in Province H illustrates these concepts in action. Here, the entertainment and leisure segment aligns most closely with the overall clustering characteristics, achieving a Z-score of -200.01. The peak hotness months in Province H are May and October, with hotness indices of 0.0438 and 0.0468, respectively. Entertainment and leisure activities make the most significant contribution to this metric, with an average value of 0.0235. Moreover, the prediction error does not exceed 5%, underscoring the validity and practical utility of this study’s methodological approach in analyzing local tourism development. This provides a robust scientific basis for harnessing data to foster local tourism growth.
... Supervised machine learning technique requires a model data called training data which assigns the polarity of data based on the context of the sentences. Data annotation can be based on manual labeling [11], [38], or based on the given rating [20]. Table 1 demonstrated the sample of manual labeling applied for some reviews in this paper. ...
The COVID-19 pandemic has enormously affected the economic situation worldwide, including in Indonesia resulting in 30 million Indonesian tumbling into penury. The Ministry of Social Affairs initiated a program to distribute social assistance aimed at the poorest households. ‘Aplikasi Cek Bansos’ is a public service application that aims to validate their status towards the social assistance program. Understanding the public sentiment and factors affecting public satisfaction levels is crucial to be performed. The goal of this study is to perform a comparative study of supervised machine learning to learn the sentiment of the public and the dominant variable resulting in public satisfaction. Support vector machine, Naïve Bayes dan K-nearest neighbor (KNN) are performed to seek the highest accuracy. This experiment discovered that the KNN algorithm produced outstanding performance where the accuracy hit 99.21%. Sentiment prediction indicated negative perception as the majority covering 83.81%. Trigrams analysis is performed to learn themes affecting satisfaction levels toward the application. Negative themes are grouped into the following categories: App instability, hope for improvement, navigation issues, and low-quality content. Some recommendations are offered for the Ministry of Social Affairs and developers, to overcome negative feedback and enhance public satisfaction level towards the application.
... Therefore, in many areas of the healthcare sector, clinical decision-making based on scanned images and laboratory samples has produced good results in classification, interpretation, and even prediction for patients [2,3]. Also, several approaches based on machine learning have been proposed for evaluating the performance in different fields such as the educational systems and assessing student performance [4,5], the sentimental analysis based on machine learning, which can be applied in a variety of fields, such as politics [6], and tourism [7]. ...
Deep learning (DL)-oriented document processing is widely used in different fields for extraction, recognition, and classification processes from raw corpus of data. The article examines the application of deep learning approaches, based on different neural network methods, including Gated Recurrent Unit (GRU), long short-term memory (LSTM), and convolutional neural networks (CNNs). The compared models were combined with two different word embedding techniques, namely: Bidirectional Encoder Representations from Transformers (BERT) and Gensim Word2Vec. The models are designed to evaluate the performance of architectures based on neural network techniques for the classification of CVs of Moroccan engineering students at ENSAK (National School of Applied Sciences of Kenitra, Ibn Tofail University). The used dataset included CVs collected from engineering students at ENSAK in 2023 for a project on the employability of Moroccan engineers in which new approaches were applied, especially machine learning, deep learning, and big data. Accordingly, 867 resumes were collected from five specialties of study (Electrical Engineering (ELE), Networks and Systems Telecommunications (NST), Computer Engineering (CE), Automotive Mechatronics Engineering (AutoMec), Industrial Engineering (Indus)). The results showed that the proposed models based on the BERT embedding approach had more accuracy compared to models based on the Gensim Word2Vec embedding approach. Accordingly, the CNN-GRU/BERT model achieved slightly better accuracy with 0.9351 compared to other hybrid models. On the other hand, single learning models also have good metrics, especially based on BERT embedding architectures, where CNN has the best accuracy with 0.9188.
... Due to the importance of text data for dynamic and complex tourism research, over the past decade, more than 400 research papers on tourism and hospitality issues based on text analysis have been published in tourism and hospitality journals. While some literature reviews related to text analysis in this field exist, they mainly focus on specific types of text data, such as online reviews (Kwok et al., 2017) and social media data (Nusair, 2020), or specific text analysis methods, such as sentiment analysis (Alaei et al., 2019;Ma et al., 2018;Mehraliyev et al., 2022 ). Consequently, a comprehensive review of text analysis research in this field is still lacking. ...
Despite numerous studies that adopt text analysis in tourism and hospitality published in the past decade, a comprehensive review of this topic is still lacking. This study endeavors to bridge this gap by conducting a systematic review of text analysis research published in the top five journals in tourism and hospitality between 2013 and 2023. From a thematic analysis perspective, this paper provides an elaborate description of how text data can be utilized for prediction and understanding purposes. Specifically, the prediction scenarios encompass hotels, destinations, and restaurants, while the understanding aspect focuses on tourists, firms, destinations, and academic researches within this domain. From a methodological perspective, this paper offers an in-depth exploration of data sources, tools or methodologies, processing procedures, and commonly utilized metrics in text analysis. The paper concludes by proposing a summary framework for text analysis research while highlighting future research trends, opportunities, and challenges in this domain.
... En el ámbito de las actividades económicas en el sector turístico, la proliferación de sitios web y redes sociales para difundir opiniones y experiencias de visitantes ha motivado el desarrollo de herramientas para analizar grandes volúmenes de CGU. Frente a ello, se destaca la pertinencia de aplicar técnicas como el análisis de sentimientos para averiguar la reputación de los destinos entre los visitantes y determinar el desempeño de las unidades que conforman el destino turístico (Alaei, Becken y Stantic, 2019). Por otro lado, Kasztelnik y Delanoy (2020) agregan que dicha técnica facilita el entendimiento del cliente, ya que se conocen sus opiniones, satisfacción de expectativas y necesidades; además, coadyuva a la identificación de áreas de mejora, lo que podría impactar favorablemente en la calidad en el servicio; y motiva el diseño de estrategias de marketing, pues se obtiene retroalimentación directa de los usuarios. ...
... Entre las técnicas comunes de PLN que se utilizan con frecuencia, el análisis de sentimientos y emociones se destaca por su capacidad de determinar la polaridad de un texto; es decir, si es positivo, negativo o neutral (Alaei, Becken y Stantic, 2019). Como señalan Alaparthi y Mishra (2021), el análisis de sentimientos puede implementarse, por un lado, de manera supervisada mediante modelos transformadores, de clasificación y de memoria de largo plazo a corto plazo (Long term short term); y por otro lado, de manera no supervisada, mediante bases de datos que permiten asignar puntuaciones de polaridad a palabras y oraciones, como SentiWordNet. ...
El objetivo de este trabajo es analizar los sentimientos y emociones de un corpus de 7543 reseñas en inglés, recabado del portal TripAdvisor, relativo a 38 establecimientos de alimentos y bebidas ubicados en Bahías de Huatulco, en el período 2013-2023. Para ello, se implementa el modelo Robustly Optimized BERT Approach, y se complementa el estudio con un análisis de las frecuencias de palabras y temáticas presentes en el corpus de reseñas. Los resultados sugieren que la mayor parte de las palabras utilizadas por los comensales poseen una connotación favorable para los establecimientos; por otro lado, el porcentaje de reseñas positivas se mantiene en un nivel cercano a 90% a lo largo del tiempo; por último, las reseñas negativas y aquellas que se asocian con emociones de tristeza y enojo, representan un bajo porcentaje y revelan variaciones reducidas en el tiempo. Las métricas de rendimiento indican un alto nivel de exactitud general en la clasificación de las reseñas (91%), aunque se destaca una baja capacidad para clasificar correctamente las reseñas neutrales. Los resultados de este trabajo son consistentes con la literatura, enfatizan la importancia de la experiencia gastronómica en en un destino turístico y proporcionan información relevante para mejorar la calidad en el servicio en establecimientos de alimentos y bebidas de Bahías de Huatulco.
... In tourism, the importance of sentiment analysis has significantly been recognized not only for its ability to detect positive or negative opinions in the text (Thelwall, 2019) but also due to tourism being a service-oriented area that heavily relies on positive customer emotions and feedback (Alaei et al., 2019). Generally, sentiment analysis is employed to understand visitors' opinions on a visited destination via online postings. ...
... For Alaei et al. (2019), 'Tourism content shared through social media has become a very influential information source that impacts tourism in terms of both reputation and performance.' (p. 1). ...
... These platforms provide a space for individual tourists to recount their experiences, and offer evaluations (Valdivia et al., 2019). With over 570 million reviews on approximately 7.3 million tourism businesses and attractions, TripAdvisor has been acclaimed for its expansive user-generated content that provides insights into tourists' opinions and behaviours (Alaei, Becken, & Stantic, 2019;Chang, Ku, & Chen, 2019;Valdivia et al., 2019), and is even a recommended site to obtain data on the tourist gaze (see Rink, 2017;Shang et al., 2022). ...
The recent closure of the Uluru climb marked a pivotal moment in Australia's tourism history. Uluru in the Northern Territory has long been a contested symbolic tourist site subject to competing narratives of its significance as a tourist icon and Aboriginal cultural landscape. This study examines tourist responses to the climb closure through a netnographic analysis of TripAdvsior content. The findings uncover enduring tensions in tourist perceptions and behaviours in relation to the climb closure. This research highlights the dynamic nature of the tourist gaze upon contested sites, such as Uluru. We conclude that despite ongoing contestation, the climb closure signifies broader societal shift towards respecting Aboriginal perspectives in tourism decision-making.
... Therefore, In many areas of the healthcare sector, clinical decision-making based on scanned images and laboratory samples has produced good results in classification, interpretation, and even prediction for patients [2,3]. Also, several approaches based on machine learning have been proposed for evaluating the performance in different fields such as the educational systems and assessing student performance [4,5], the sentimental analysis based on machine learning, which can be applied in a variety of fields, such as politics [6], and tourism [7]. Therefore, the use of machine learning can be an innovative approach to improve the employability of students, support their career prospects, and identify their skills, and weaknesses based on labor market requirements [8]. ...
... Current Memory Content (ht): This value represents the network's current state. 7 The update gate and reset gate are responsible for controlling the information flow, and their values are learned adaptively during the training process. The GRU architecture is more computationally efficient than LSTM because it has fewer parameters. ...
Deep Learning (DL) oriented document processing is widely used in different fields for extraction, recognition, and classification processes from raw corpora of data. The article examines the application of deep learning approaches, based on different neural network methods, including Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN). The compared models were combined with two different word embedding techniques, namely: Bidirectional Encoder Representations from Transformers BERT and Gensim Word2Vec. The models are designed to evaluate the performance of architectures based on neural network techniques for the classification of CVs of Moroccan engineering students at ENSAK(National School of Applied Sciences of Kenitra, Ibn Tofail University). The used dataset included resumes collected from engineering students at ENSAK in 2023 for a project on the employability of Moroccan engineers in which new approaches were applied, especially machine learning, deep learning, and big data. Accordingly, 867 resumes were collected from five specialties of study (Electrical Engineering, Networks and Systems Telecommunications, Computer Engineering, Automotive Mechatronics Engineering, Industrial Engineering). The results revealed good performance of the proposed models based on the BERT embedding approach compared to models based on the Gensim Word2Vec embedding approach. Accordingly, the CNN-GRU/Bert model achieved slightly better accuracy with 0.9251 compared to other hybrid models.
... Sentiment analysis is a text mining methodology that determines and quantifies the degree of emotion for words in a document based on an emotion vocabulary. It has been studied in a wide area of domain, such as movie reviews, teaching reviews [16][17][18], product reviews [19], e-learning [20], travellers' reviews [21], etc. Sentiment analysis may be broadly classified into machine learning emotion analysis and dictionary-based emotion analysis. Machine learning-based sentiment analysis shows higher accuracy than dictionary-based sentiment analysis when there is sufficient data, but when the amount of data is small, dictionary-based sentiment analysis shows higher accuracy. ...
The effective and successful implementation of the capstone design curriculum has been extensively researched. This study was focused on the emotions of students who participated in a capstone design course and the factors behind these emotions. An attempt was made to quantify students’ emotions through the sentiment analysis of text mining based on their review data about the capstone design. Also, a survey to identify the factors that affect these emotions was conducted with students after the course. The causal analysis indicated that, first, the statistically significant positive factor in the positive sentiment was group interaction with teaching staff, while the organisation of the course, individual rapport, need for other major’s knowledge, and students’ own enthusiasm had a negative effect. Second, the factor that increased the negative sentiment was students’ own enthusiasm, and the factor that decreased it was the learning value of the course. Lastly, on the composite sentiment, the enthusiasm and scope of the course had a negative influence, while group interaction with teaching staff - positive. The identified factors and their influence on students could inform future capstone design curricula.
