Social media analytics: Extracting and visualizing Hilton hotel ratings and reviews from TripAdvisor

Chang, Yung Chun; Ku, Chih Hao; Chen, Chun‐Hung

doi:10.1016/j.ijinfomgt.2017.11.001

Cited by 185 publications

(118 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning includes supervised [1], which requires a set of predefined categories or tagging labels, and unsupervised methods, which does not require data labeling. Supervised machine learning algorithms such as Naïve Bayes [17], regression analysis [52], decision trees [41], k-nearest neighbors [9], and Support Vector Machine (SVM) [5] have been used to conduct sentiment analysis and classification for online reviews and tourism research. For example, Dey et al [9] used Naïve Bayes and K-Nearest Neighbor to perform sentiment analysis of hotel and movie reviews and Chang et al [5] adopted a novel SVM approach to conduct aspect-based sentiment analysis of hotel reviews and visualize the result.…”

Section: Artificial Intelligence (Ai)mentioning

confidence: 99%

“…For example, Guo et al [15] use topic modeling -Latent Dirichlet Analysis (LDA), which combines machine learning and NLP techniques to extract dimension of customer satisfaction from 266,544 online reviews for 25,670 hotels in 16 countries. Both Chang et al [5] and Akhtar et al [2] have used more advanced NLP techniques to detect aspect-based sentiment from hotel reviews and ratings, which extract fine-grained opinions toward hotel reviews.…”

Section: Natural Language Processing (Nlp)mentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence and Visual Analytics: A Deep-Learning Approach to Analyze Hotel Reviews & Responses

Ku¹,

Chang²,

Wang³

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

With a growing number of online reviews, consumers often rely on these reviews to make purchase decisions. However, little is known about managerial responses to online hotel reviews. This paper reports on a framework to integrate visual analytics and machine learning techniques to investigate whether hotel managers respond to positive and negative reviews differently and how to use a deep-learning approach to prioritize responses. In this study, forty 4-and 5-star hotels in London with 91,051 reviews and 70,397 responses were collected and analyzed. Visual analyses and machine learning were conducted. The results indicate most hotels (72.5%) showing no preference to respond to positive and negative reviews. Our proposed deeplearning approach outperformed existing algorithms to prioritize responses.

show abstract

Section: Artificial Intelligence (Ai)mentioning

confidence: 99%

Section: Natural Language Processing (Nlp)mentioning

confidence: 99%

Artificial Intelligence and Visual Analytics: A Deep-Learning Approach to Analyze Hotel Reviews & Responses

Ku¹,

Chang²,

Wang³

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Martin-Fuentes et al created a Python-based web browser bot to extract accommodation service providers' rankings from Booking and TripAdvisor for the analysis of about 20,000 providers' (present at both platforms) customer feedbacks' similarity and veracity [15]. Yung-Chun et al, within their framework of data crawlers and visual analytics, used machine learning techniques for sentiment-sensitive tree construction, convolution tree kernel classification, aspect extraction, and category detection of The Hilton hotel brand's UGC at TripAdvisor for supporting decision makers via business intelligence [16]. Sumaronso et al analyzed TripAdvisor's impact on the actual occupancy in Surakarta (Indonesia) via manual searches and interviews with accommodation facilities' managers [17].…”

Section: Literature Reviewmentioning

confidence: 99%

Can Location-Based Social Media and Online Reservation Services Tell More about Local Accommodation Industries than Open Governmental Data?

et al. 2019

View full text Add to dashboard Cite

The paper follows-up ongoing research focusing on the potential of machine-readable data as additional knowledge in the governance of local tourism and destination management organizations (DMOs) in Slovakia. The current focus is on one classic social media (Facebook), one location-based social media (Foursquare), two hybrid travel-related platforms with partial attributes of reservation services (Google Places, TripAdvisor), and two online reservation services (Booking, Airbnb). The global aim is the usage of extracted data for the identification of additional entities with the obligation of local occupancy taxation, which is the financial backbone of Slovak (DMOs). A set of simple and globally reusable scripts constructed in Python and PostgreSQL were used to extract data on lodging providers from the Google Places application programming interface (API), the Facebook Place Search API and the Foursquare Venue API over grid overlays of districts' spatial representation. For pure scientific purposes in the case of Tripadvisor, Booking, and Airbnb, with no suitable access to open APIs, web scraping methods were used for data extraction. The pilot case was applied in the boundaries of Kosice city (Slovakia), and the aggregations of processed data were compared with official open statistics. Results indicate that the automated continuous monitoring of online platforms could help local public administrations in decreasing occupancy tax evasions and even widen knowledge about online audiences and visitors' satisfaction.

show abstract

“…It is possible to see the studies exmining the aims of the travels and features of the tourist groups by eWOM reviews. Chang et al (2017) analyzed the online reviews of the tourists to determine the travel aims of them by using sensitivity classification and combined algorithm. They found that the couple travelers were more than the others and business trips were in a low level.…”

Section: Previous Studiesmentioning

confidence: 99%

Examining eWOM Reviews of the Hotel Enterprises on Tripadvisor: The Case of Usak Province

Mazan¹,

Çatir²

2019

jotags

View full text Add to dashboard Cite

Consumers tend to tell others about their product or service experience. The transfer of these experiences about products and services is known as word of mouth (WOM) communication. With technological developments and easy accessibility of the internet, these thoughts can be published electronically and become visible to everyone. At this stage, traditional WOM is transformed into eWOM online. Since tourism products and services are experience products, consumers need to rely on others' recommendations. Consumers; hotels where they stay, restaurants they eat, shopping businesses etc. comments on online platforms. In this study, eWOM elements are evaluated by examining the electronic comments for hotel businesses in Uşak province, which is an online evaluation platform on Tripadvisor. The study was carried out in tourism licensed hotels in Usak.

show abstract

Social media analytics: Extracting and visualizing Hilton hotel ratings and reviews from TripAdvisor

Cited by 185 publications

References 26 publications

Artificial Intelligence and Visual Analytics: A Deep-Learning Approach to Analyze Hotel Reviews & Responses

Artificial Intelligence and Visual Analytics: A Deep-Learning Approach to Analyze Hotel Reviews & Responses

Can Location-Based Social Media and Online Reservation Services Tell More about Local Accommodation Industries than Open Governmental Data?

Examining eWOM Reviews of the Hotel Enterprises on Tripadvisor: The Case of Usak Province

Contact Info

Product

Resources

About