A generalizable sentiment analysis method for creating a hotel dictionary: using big data on TripAdvisor hotel reviews

Bagherzadeh, Sayeh; Shokouhyar, Sajjad; Jahani, Hamed; Σιγάλα, Μαριάννα

doi:10.1108/jhtt-02-2020-0034

Cited by 29 publications

(22 citation statements)

References 76 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Available technical and software tools allow processing text reviews left by visitors on various platforms (Chang el al., 2020). A methodology is being developed to create robust lexicons that can be used to analyse big data to understand and predict customer sentiment (Bagherzadeh, 2021). Much attention is paid to the reliability of the data obtained and verification of the identified patterns (Han, 2021).…”

Section: Methodsmentioning

confidence: 99%

Geographical and component analysis of the perception of the tourism and recreational space of the perm region

Сафарян

Konyshev

2022

B SERBIAN GEOGRAPHIC

View full text Add to dashboard Cite

The relevance of this study lies the reassessment of the role that an information plays in the functioning and perception of tourism and recreational space. Tourism and recreational space perceive as global but it has a complex structure, represented in the form of territorial tourism and recreational systems. In a post-industrial society the importance of information for the development of tourism and recreational space is constantly increasing. Oftentimes tourists base on other tourist's information and reviews posted on the Internet, recorded in the form of digital footprints on specialized portals to make a decision to travel. The consumer perceives the tourism and recreational space of the region as a set of reviews and ratings the content of which may be different from the actual parameters of the space. These feedbacks last as a basis for the expectations and impressions formation. The purpose of this study is a component and geographical analysis of the perception of the tourism and recreational space of the Perm region using the method of text analysis of big data. The textual analysis of 5,668 reviews that have posted on the Tripadvisor website was carried out on the PolyAnalyst platform and included the calculation of the sentiment index, the extraction of keywords and the determination of the relationship of terms to define the key attributes of the tourist and recreational space perception. The component analysis of the Perm region's tourism and recreational space perception showed the uneven perception of its individual components and made it possible to identify the most topical problem areas. The assessment of the perception of tourist and recreational space by consumers from different places of residence, as well as the assessment of the territorial features of the perception of individual cities of the Perm region, was carried out using geographical analysis. Additionally, the sentiment index change from 2014 to 2021 was assessed. An analysis of this change made it possible to identify the incipient negative trends at the deterioration of the region's tourism and recreational space perception. The results of the study will be useful for the development of strategic documents on territorial planning and tourism management, improvement of regional tourism products and the image of the region.

show abstract

Section: Methodsmentioning

confidence: 99%

Geographical and component analysis of the perception of the tourism and recreational space of the perm region

Сафарян

Konyshev

2022

B SERBIAN GEOGRAPHIC

View full text Add to dashboard Cite

show abstract

“…It has been verified to outperform general dictionaries. The JHTT 14,2 words or terms used in domain-specific dictionaries may not have the same meaning in two different topics and/or contexts (Bagherzadeh et al, 2021). For example, a dictionary created in restaurants may give much worse results in the area of hotels than in the area of relatively similar books.…”

Section: Aspect Based Sentiment Analysis (Absa) Technique Used In Our...mentioning

confidence: 99%

Aspect-based sentiment analysis on online customer reviews: a case study of technology-supported hotels

Özen¹,

Katlav

2023

JHTT

View full text Add to dashboard Cite

Purpose The purpose of this study is to determine the satisfaction of the guests who stay at hotels offering technology-supported products and services related to the services and products they receive by using the opinion mining technique. Design/methodology/approach In this research, 12,396 customer reviews on booking.com related to ten hotels belonging to a hotel chain using technology-supported products were evaluated with aspect-based sentiment analysis techniques. Findings As a result of this study, it has been determined that using technology in hotel businesses creates a positive impression on customer satisfaction. It has been determined that the enrichment of standard hotel business products such as beds and room lighting with technology, in a way that will not be very costly, affects the guests. In addition, it is interesting that technological features such as robots and room service robots, which are called “High & Technology” in this study, are evaluated by customers in the service process. Practical implications The hotel managements have the opportunity to evaluate the services we offer by analyzing their online comments and to see their own image from the eyes of the guests. Hotel businesses must learn about customer expectations for technologies with high investment costs. This study, which analyzes online customer reviews, enables tourism businesses that offer technology-supported products and services and invest in technology in service delivery, to understand how customers evaluate the service. Originality/value In this study, customer reviews of a hotel group operating in many countries belonging to a hotel group that enriches its standard products with technology and provides service with the concept of a “smart hotel” were examined. This study contributes to the understanding of customers' experience of using technological products in hotel businesses. This study contributes to the literature on customers' satisfaction with technological hotel products and services and the decision of hotels to invest in technology.

show abstract

“…It should be noted that most of the lexicon-based approaches are built upon, so-called, general-purpose lexicons (Avdić and Bagić Babac, 2021). Bagherzadeh et al (2021) developed two specific lexicons, namely weighted and manually selected lexicons, which were tested and validated by applying classification accuracy metrics to the TripAdvisor data. Their approach outperformed a SentiWords lexicon-based method and a Naïve Bayes machine-learning algorithm in classifying sentiment.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting sentiment and rating of tourist reviews using machine learning

Puh

Babac

2022

JHTI

View full text Add to dashboard Cite

PurposeAs the tourism industry becomes more vital for the success of many economies around the world, the importance of technology in tourism grows daily. Alongside increasing tourism importance and popularity, the amount of significant data grows, too. On daily basis, millions of people write their opinions, suggestions and views about accommodation, services, and much more on various websites. Well-processed and filtered data can provide a lot of useful information that can be used for making tourists' experiences much better and help us decide when selecting a hotel or a restaurant. Thus, the purpose of this study is to explore machine and deep learning models for predicting sentiment and rating from tourist reviews.Design/methodology/approachThis paper used machine learning models such as Naïve Bayes, support vector machines (SVM), convolutional neural network (CNN), long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) for extracting sentiment and ratings from tourist reviews. These models were trained to classify reviews into positive, negative, or neutral sentiment, and into one to five grades or stars. Data used for training the models were gathered from TripAdvisor, the world's largest travel platform. The models based on multinomial Naïve Bayes (MNB) and SVM were trained using the term frequency-inverse document frequency (TF-IDF) for word representations while deep learning models were trained using global vectors (GloVe) for word representation. The results from testing these models are presented, compared and discussed.FindingsThe performance of machine and learning models achieved high accuracy in predicting positive, negative, or neutral sentiments and ratings from tourist reviews. The optimal model architecture for both classification tasks was a deep learning model based on BiLSTM. The study’s results confirmed that deep learning models are more efficient and accurate than machine learning algorithms.Practical implicationsThe proposed models allow for forecasting the number of tourist arrivals and expenditure, gaining insights into the tourists' profiles, improving overall customer experience, and upgrading marketing strategies. Different service sectors can use the implemented models to get insights into customer satisfaction with the products and services as well as to predict the opinions given a particular context.Originality/valueThis study developed and compared different machine learning models for classifying customer reviews as positive, negative, or neutral, as well as predicting ratings with one to five stars based on a TripAdvisor hotel reviews dataset that contains 20,491 unique hotel reviews.

show abstract

A generalizable sentiment analysis method for creating a hotel dictionary: using big data on TripAdvisor hotel reviews

Cited by 29 publications

References 76 publications

Geographical and component analysis of the perception of the tourism and recreational space of the perm region

Geographical and component analysis of the perception of the tourism and recreational space of the perm region

Aspect-based sentiment analysis on online customer reviews: a case study of technology-supported hotels

Predicting sentiment and rating of tourist reviews using machine learning

Contact Info

Product

Resources

About