Travel Reviews Research Articles

Analyzing online reviews of foreign tourists to destination attractions in China: a novel text mining approach

ABSTRACT In recent years, China has been gradually improving its tourism services along with its economic development. Inbound tourism not only boosts the economy of China, but also creates issues and challenges for tourism administration. The purpose of this study is to develop a novel text mining approach that combines topic modeling and sentiment analysis for exploring the dynamic evolution of topic intensity of destination attractions and discovering the reasons for foreign tourists’ dissatisfactions. To this end, we propose an LDA-based topic evolution model, develop a tourism-oriented VADER dictionary and introduce an integration method for screening negative reviews. Then, the approach was used to analyze 80,546 online travel reviews from foreign tourists on TripAdvisor for 10 popular destination attractions in China from 2011 to 2019. The findings can help tourism practitioners better understand the changes and trends of the topics over time as well as develop strategies with respect to tourists’ dissatisfactions.

How Online Travel Reviews Sources Affect Travelers’ Behavioral Intentions? Analysis with Source Credibility Theory

ABSTRACT This study used Source Credibility Theory (SCT) to examine the effect of the source credibility factors (SCFs) of travelers’ electronic word of mouth (eWOM) and their adoption on tourists’ hotel booking and review sharing intention. This study used Structure Equation Modeling (SEM) and artificial neural network (ANN) approaches to validate the effect of SCFs on tourists’ behavioral intentions. The study highlighted that all three source credibility factors, such as perceived sender trust, website trust, and organizational reputation, affected functional aspects like eWOM credibility and adoption. The study finds the dual-mediating effect of eWOM credibility and adoption between source credibility factors and eWOM outcomes. This study makes a unique attempt to analyze the roles of various aspects of SCT on tourists’ eWOM behavior. This study contributes to online trust literature by examining the effect of different online credibility factors (surface credibility, presumed credibility, reputed credibility) on online tourist behavior.

OPTIMIZATION OF K-MEANS CLUSTERING USING PARTICLE SWARM OPTIMIZATION ALGORITHM FOR GROUPING TRAVELER REVIEWS DATA ON TRIPADVISOR SITES

K-Means Algorithm can be used to group tourists based on reviews on tourist destination objects. This algorithm has a weakness that is sensitive to the determination of the initial centroid. The initial centroid that is determined at random will decreasing the level accuracy, often gets stuck at the local optimum, and gets a random solution. Optimization algorithms such as PSO can overcome this by determining the optimal initial centroid. The optimal number of clusters (K) will be determined using the Elbow method by calculating the SSE value of the resulting cluster. The average Silhouette Coefficient (SC) is used to measure the quality of the clusters produced by the K-Means Algorithm with and without the PSO Algorithm. This study uses secondary data obtained from the UCI Machine Learning Repository with the name Travel Reviews Data Set which consists of 980 records and 10 attributes. The test results show that K=2 is the optimal number of clusters. The K-Means and PSO Algorithm gives an average SC value of 0.300358 which is better than without the PSO Algorithm of 0.300076. The optimal PSO hyperparameter generated is the number of particles=30, \varphi_1=2.2, and {\ \varphi}_2=3 at maximum iteration of 100.

How do online travel reviews facilitate informed purchase decisions?

ABSTRACT We analysed the attributes of online travel reviews that facilitate online travel purchasing decisions. In Study 1, we developed and validated a scale for measuring the perceived value of online travel reviews (PVOTR). The PVOTR scale has six dimentions and was based on a literature review and Fuzzy Delphi Method. It was validated with data from 69 undergraduate students and 485 travelers in Taiwan. In Study 2, we examined the impact of PVOTR on the online travel purchasing attitudes of another 469 travelers in Taiwan. PVOTR significantly affected online travel purchasing attitudes through the mediation of reduced perceived complexity.

Analisis Sentimen Wisatawan terhadap Taman Nasional Bunaken dan Top 10 Hotel Rekomendasi Tripadvisor Menggunakan Algoritma SVM dan DT berbasis CRISP-DM

It is necessary to analyze traveler sentiment towards Bunaken National Park and Tripadvisor's Top 10 Recommended Hotels to identify traveler satisfaction with the attractions, accommodation services, and transportation used. Considering this, this study uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework by testing the performance of the Decision Tree (DT) algorithm and the Support Vector Machine (SVM). CRISP-DM has six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Based on the processing of 398 Bunaken National Park destination data and 1793 review data on the top 10 hotels recommended by Tripadvisor, the SVM algorithm performed better. In the context of Bunaken National Park destination data, the performance of the SVM algorithm using the SMOTE operator can produce 100% accuracy, precision, recall, f-measure, AUC, and t-Test values. In addition, in processing the top 10 hotel datasets recommended by Tripadvisor, the SVM algorithm using the SMOTE operator provides an accuracy value of 96.42%, a precision value of 100%, a recall value of 92.83%, an f-measure value of 96.27%, an AUC value of 100%, and a t-Test value of 96.4%. The results of identifying the five words that most often appear in tourist reviews for Bunaken Marine Park tourist destinations are 164 words fish, 165 words island, 193-word dive, 230 diving, and 280 words Bunaken. This indicates the driving factor for tourist visits to Bunaken Marine Park is the beauty of underwater nature, including the diversity of marine animal species, the natural beauty of the archipelago, and diving activities. In addition, the results of identifying the five words that most often appear in traveler reviews for Tripadvisor's top 10 recommended hotels are 1170 great words, 1222 bunaken words, 1550 resort words, 1613 diving words, and 1711 dive words. This indicates that the characteristics of tourists who have the motive of traveling to Bunaken National Tourism Park have the intention to use resort accommodations around Bunaken and have mobility and facilities to support diving activities. Thus, the output of this study can be used as a recommendation for accommodation service managers to prepare supporting facilities for tourists who want to visit Bunaken National Park.

Sentiment of Chinese Tourists towards Malaysia Cultural Heritage Based on Online Travel Reviews

Analyzing the perception differences and influencing factors of cross-cultural groups in heritage tourism can help heritage sites to formulate differentiated service and improve tourist satisfaction. This research adopted the BERT model to undertake sentiment analysis of 17,555 Chinese online reviews for nine scenic spots in Melaka. Using vocabulary filtering, co-occurrence analysis, and semantic clustering technology, the emotional characteristics of Chinese outbound tourists when they visited heritage sites in Melaka were analyzed, which revealed the factors influencing their positive and negative emotions. Results showed that: 1. The BERT-based deep learning approach can obtain improved sentiment predictive performance. 2. Chinese tourists’ general emotional perceptions of Melaka were positive and they were very interested in heritage sites. 3. The most important reason for the negative emotions of Chinese tourists was a lack of cultural experience in Melaka. This research expands the application of deep learning in the field of tourism, and it helps heritage tourism destinations to improve their marketing plans for Chinese tourists and achieve long-term sustainable development of the destination.

The role of badges to spur frequent travelers to write online reviews

研究目的在线旅游评论平台已成为创新的信息系统, 这也是由于结合了复杂的游戏化元素, 例如具有视觉吸引力的徽章。本研究旨在分析升级徽章后评论的三个特征：评论长度（字数）、情绪评分和两次连续评论之间的时间段（距离撰写下一次评论的天数）。研究设计/方法/途径本研究使用数据挖掘方法分析了由 100 位常旅客和贡献者撰写的总共 77,000 条在线 TripAdvisor 评论。然后进行基于数据的敏感性分析 (DSA), 以提供对数据挖掘训练模型的理解。研究发现结果表明, 具有自我自豪感（“徽章护照”）和同行认可（“徽章有帮助”）的徽章在在线评论的整个生命周期中具有显着影响, 而仅通过计算贡献来授予徽章几乎没有影响。研究原创性本研究首次分析了经验丰富的旅行者在获得徽章和积分时受到的影响。奖励标准贡献徽章的内在动机因素几乎不会影响用户行为。需要设计徽章来奖励那些并非微不足道且不完全取决于用户的成就。

Topic modeling of the quality of guest’s experience using latent Dirichlet allocation: western versus eastern perspectives

PurposeThis study aims to understand the satisfaction and needs of eastern and western travelers as hotel guest, based on their experiences as seen in guest reviews and review topics.Design/methodology/approachConsidering 2,965 and 1,035 western and eastern traveler reviews, respectively, from 47 countries, obtained from TripAdvisor listed-hotel in Phnom Penh and Siem Reap city in Cambodia, this study investigates the differences in hotel guest satisfaction and needs by using topic modeling (i.e. latent Dirichlet allocation [LDA]).FindingsThe results reveal differences in the online preferences, experiences, expectations and behaviors of hotel guests from different cultural backgrounds. Though western and eastern travelers appear to place similar emphasis on service, location, room and destination. The westerners more likely focus on meal and online reservation, whereas the easterners focus on hotel facility.Research limitations/implicationsReviews were obtained from only two cities in Cambodia, which is not an adequate representation of the diverse travelers visiting the country.Practical implicationsThe comparison highlighting the similarities and dissimilarities between western and eastern traveler perspectives enable hoteliers to understand guests’ preferences and their hidden changes in (dis)satisfaction and leverage it to improve hotel service quality, increase occupancy and, thereby, maximize profits.Originality/valueThis study contributes to the literature on hotel guests’ experiences by presenting the difference in perceptions of service experience of western and eastern travelers, through topic modeling.

Reconstructing the microbrewery taproom experiencescape through narratives in online travel reviews: A case from Houston, Texas USA

The number of craft breweries on the American landscape has grown exponentially over the past several decades. The literature on craft beer and beer tourism has grown accordingly. Yet, visitors’ experience of the craft brewery taproom remains an under-examined aspect of this literature. O’Dell (2005 ) proposed the idea of examining the landscapes of experiences, or experiencescapes, including the physical and social spaces that allow for the co-creation of experiences. The concept has increasingly been used to examine culinary, gastronomic, and wine tourism experiences. Thus, this exploratory study begins to address the gap in the craft beer and beer tourism literature by reconstructing the experiencescape of craft brewery taprooms from visitor narratives in online travel reviews for microbreweries and taproom breweries in Houston, Texas (USA). The study employs thematic narrative analysis to identify the components of the physical and social environments of the brewery taproom that comprise the experiencescape and contribute to positive, memorable experiences. Findings indicate that consuming the craft beer product is only one part of the taproom experiencescape; breweries must consider the taproom experience holistically. Opportunities exist to facilitate a more conscious experiencescape design to engage visitors’ senses for more immersive and memorable experiences.

A Comparative Study of Collaborative Filtering and Content-Based Approaches for Improving the Accuracy of Travel Recommender Systems for Malayalam Language

In this paper, we present a personalized travel recommender system in the Malayalam language using artificial intelligence techniques. The study focuses on the use of travelogues and travel reviews written by travellers on social media as the primary source of data. A dataset of 11000 posts from 6444 travellers was collected from Facebook and other online platforms during 2020-2023. The data was pre-processed to extract relevant information such as travel mode, type of travel, location visited, and climate. Two approaches were used to build the recommender system: collaborative filtering-based K-means clustering and content-based hierarchical agglomerative clustering. The results of the study showed that the clustering approach significantly improved the efficiency and accuracy of the recommender system. K-means clustering achieved an accuracy of 91% and an F1 score of 85%, while the agglomerative hierarchical clustering approach achieved an accuracy of 85% and an F1 score of 84.25%. The results of this study demonstrate the potential of using travelogues and travel reviews to construct a personalized travel recommender system in regional languages.

Detecting Novelty Seeking From Online Travel Reviews: A Deep Learning Approach

Travel online reviews is important experience related information for understanding an inherent personality trait, novelty seeking (NS), which influences tourism motivation and the choice of tourism destinations. Manual classification of these reviews is challenging due to their high volume and unstructured nature. This paper aims to develop a classification framework and deep learning model to overcome these limitations. A multi-dimensional classification framework was created for NS personality trait that includes four dimensions synthesized from prior literature: relaxation seeking, experience seeking, arousal seeking and boredom alleviation. Based on 30 000 reviews from TripAdvisor we propose a deep learning model using Bidirectional Encoder Representations from Transformers (BERT)- Bidirectional Gated Recurrent Unit (BiGRU) to recognize NS automatically from the reviews. The classifier based on BERT-BiGRU and NS multi-dimensional scales achieved precision and F1 scores of 93.4% and 93.3% respectively, showing that NS personality trait can be relatively accurately recognized. This study also demonstrates that the classifier based on multi-dimensional NS scales can produce satisfactory results using the deep learning model. The findings also indicate that the BERT- BiGRU model achieves the best effect compared to the same kind of deep learning models. Moreover, it proves that personality traits can be automatically identified from travel reviews based on computational techniques. For practical purposes, this study provides a comprehensive classification framework for NS, which can be used in marketing and recommendation systems operating in the tourism industry.

Investigating the credibility of online travel reviews adoption in trip planning intention among Indian travellers

Travelers evaluate online travel reviews usage through their argument quality and credibility of the source. As a result, travel marketers such as hoteliers, destination marketers and travel agency websites managers should set up mechanisms to assess tourists' concern to avoid unfavorable experience from social media reviews. Accordingly, this study aims to develop a scale and validate the modified Information Adoption Model (IAM) in the tourism context, while studying the impact of online review usefulness on its adoption. Secondly, the mediation role of travelers' attitude toward online reviews between review usefulness and its adoption is determined. Further, the credibility of online travel review adoption on the behavioral intentions of travelers has been assessed. This paper adapts the modified IAM given by Abedi et al. (2019) to develop scale and provide a comprehensive model in the tourism context. The study used 284 travelers who use online travel reviews from social media for their trip planning to evaluate the proposed model through SmartPLS software. The results show that online travel review usefulness significantly affects online travel review adoption. Secondly, the relationship between online review usefulness and its adoption is fully mediated by the mediating variable (attitude towards online travel reviews). Hence, this empirical paper intends to add to the research on online travel review adoption by travelers for their trip planning, considering the forwarding of information as one of the behavioral intentions along with purchase intentions, which depicts the novelty of this paper.

Opinion Mining from Online Travel Reviews: An Exploratory Investigation on Pakistan Major Online Travel Services Using Natural Language Processing

Online tourism evaluations are a valuable origin of data for traveler organizations, defining as they could be excellently recognized critically prompting traveler opinion-designing using opinion mining. As technology advanced, online review forums of any organization become an attractive source of communication with them, where people can share their views in the form of comments. The main determination of this research article is to recognize normal topics and connect them to contrasts in web-based travel reviews. Online millions of reviews, got from two significant web-based travel organizations (Uber, and Careem) in Pakistan, and a semantic affiliation examination was utilized to extract thematic words and construct a semantic affiliation organization. In the Python programming language, we use natural language processing (NLP), which includes data cleansing and tokenization. The results of network visualization are able to evidently recognize main topics and thematic words with social network associations. The proposed logical system extends our grip on the strategic complications and gives new points of view on the best way to dig popular assessments to assist vacationers, inns, and travel industry organizations.

Measuring the Difference Between Pictures From Controlled and Uncontrolled Sources to Promote a Destination. A Deep Learning Approach

Promoting a destination is a major task for Destination Marketing Organizations (DMOs). Although DMOs control, to some extent, the information presented to travelers (controlled sources), there are other different sources of information (uncontrolled sources) that could project an unfavorable image of the destination. Measuring differences between information sources would help design strategies to mitigate negative factors. In this way, we propose a deep learning-based approach to automatically measure the changes between images from controlled and uncontrolled information sources. Our approach exempts experts from the time-consuming task of assessing enormous quantities of pictures to track changes. To our best knowledge, this work is the first work that focuses on this issue using technological paradigms. Notwithstanding this, our approach paves novel pathways to acquire strategic insights that can be harnessed for the augmentation of destination development, the refinement of recommendation systems, the analysis of online travel reviews, and myriad other pertinent domains.

Big data to assess genre-specific features of the machine translation output of online travel reviews in Spanish

Big data analysis such as user-generated content and specifically online consumer reviews has attracted considerable attention in recent years due to its numerous research opportunities and commercial applications in almost all fields of knowledge. The origin of this digital genre in the oral tradition highlights the spontaneous features of the spoken language that are reflected in the written text that has its own characteristics depending on the user’s culture and language. By comparing a corpus of 2,000 reviews, this paper proposes the identification and analysis of the unique characteristics of this new digital genre to determine the behavior of machine translation of users' reviews into Spanish. Thus, the aim of this work is to study the tourism reviews translated into Spanish and identify how MT handles the main characteristics that confer naturalness and credibility to this genre.

The impact of destination online review content characteristics on travel intention: experiments based on psychological distance perspectives

PurposeThis study aims to explore the relationship between the content characteristics of destination online reviews and travel intention under three individual circumstances: temporal distance, social distance and experiential distance.Design/methodology/approachBased on construal-level theory (CLT), this study divides online travel reviews into concrete and abstract reviews. Three experiments were conducted to test the moderating effects of temporal distance, social distance and experiential distance on the influence of review content characteristics on tourists' travel intentions.FindingsThe results show that abstract reviews would lead to higher travel intentions than concrete reviews. Furthermore, tourists' travel intentions differed depending on social distance and were significantly affected by reviews posted by reviewers similar to review recipients. In addition, the study contributes by discovering that the moderating effects of temporal distance, social distance and experiential distance were not significant, which differs from most of the previous research conclusions.Originality/valueThis study focused on review content characteristics, which provided a novel perspective for constructing online travel reviews. Furthermore, this research defined the concept of experiential distance in the context of online travel and expanded the research on psychological distance.

Infusing new insights: How do review novelty and inconsistency shape the usefulness of online travel reviews?

Review usefulness represents a vital indicator for evaluating the quality of online reviews in the tourism industry, and various heuristic cues have been recognized as determinants of this indicator. This study constructs a comprehensive conceptual framework based on the heuristic-systematic model to observe how two systematic cues, namely, review novelty and inconsistency, shape the perceived usefulness of reviews. Through an empirical analysis based on 1,744,693 reviews of 62,543 restaurants in the United States, we unveil a positive effect of review novelty on review usefulness but a negative effect of review inconsistency. We also underscore the moderating effects of several heuristic cues in the model, including review valence, reviewer expertise, and restaurant popularity. These results indicate that systematic and heuristic cues simultaneously and interactively determine review usefulness. The findings present theoretical implications to the literature and practical implications to hospitality professionals and designers/managers of review platforms.

패키지 여행상품에서 관광객이 평가하는 여행 가이드의 역할에 대한 의미 고찰

The purpose of this paper is to find and examine the meaning of the role of a tour guide from travel reviews. What is noteworthy from the results is that, first, it was found that the 'tour guide's role' in package tours was mostly focused on effectively adjusting the travel schedule or maintaining a pleasant and pleasant group atmosphere. Second, the role of the tour guide was found to be working in the process of resolving the 'hard and arduous process' of the package, including tight schedules, traffic congestion, weather changes, and conflicts. It can be inferred that, through performing this role, tourists can trust the tour guide and gain 'unforgettable impressions and memories'.

Exploring the effect of the knowledge redundancy of online reviews on tourism consumer purchase behaviour: based on the knowledge network perspective

ABSTRACT Online reviews often contain considerable information redundancy. Understanding how to mine and identify valuable information is an important research topic. Based on knowledge-based theory and social network theory, this study discusses the impact of knowledge redundancy in online travel reviews on consumer purchase behaviour from the perspective of knowledge networks. By crawling 943,516 online reviews of 609 tourism products from Trip and Tuniu, we conduct an empirical analysis of the relationships among knowledge redundancy, knowledge diversity and consumer purchase behaviour. The results show that there is a U-shaped relationship between knowledge redundancy in online tourism reviews and consumer purchase behaviour, and knowledge diversity plays an intermediary role in the relationship between knowledge redundancy and consumer purchase behaviour. The results provide valuable and timely insights for the development of the online tourism industry.

An Effective ELECTRA-Based Pipeline for Sentiment Analysis of Tourist Attraction Reviews

In the era of information explosion, it is difficult for people to decide on a tourist destination quickly. Online travel review texts provide valuable references and suggestions to assist in decision making. However, tourist attraction reviews are primarily informal and noisy. Most works in this field focus on shallow machine learning models or non-pretrained deep learning models. These approaches struggle to generate satisfactory classification results. To solve this issue, the paper proposes a pipeline model. In the first step of this paper, we preprocess tourist attraction reviews by performing stopword removal, special character removal, redundancy deletion and negation substitution to reduce noise. Then, we propose an ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) classifier for sentiment analysis of tourist attraction review. Finally, we compare our pipeline model with several representative deep text classification models. Extensive experiments have demonstrated the effectiveness of our approach to sentiment analysis of tourist attraction reviews. We not only provide one high-quality dataset for tourist attraction reviews, but our work can also expand and promote the development of sentiment analysis in other domains.