An Aspect-Based Review Analysis Using ChatGPT for the Exploration of Hotel Service Failures
Abstract
:1. Introduction
2. Related Works
2.1. Aspect-Based Sentiment Analysis
2.2. Aspect-Based Text Summarization
2.3. Natural Language Processing Using Large Language Model
3. Methodology
3.1. Data Collection
- Ratings—Detailed ratings are provided, covering overall satisfaction and specific areas like cleanliness, location, rooms, service, sleep quality, and value, with ratings ranging from 0 to 5;
- Review Title and Text—Each review has a title and a detailed description of the customer’s experience;
- Author Information—This includes the user’s name, the number of cities they have visited, the number of helpful votes they have received, the total number of reviews they have written, and the types of reviews;
- Hotel and Review Identifiers—Each hotel and review has its own unique identifier;
- Location—The physical location of the hotel;
- Helpful Votes—The number of helpful votes a review has received.
3.2. Determination of Hotel Service Aspects
- Cleanliness—Evaluating the overall cleanliness of a hotel, including its rooms, bathrooms, common areas, and dining facilities;
- Room Quality—Assessing factors like room size, comfort of beds, in-room amenities, soundproofing (noise level), air conditioning, and maintenance;
- Service Quality—Reviewing the professionalism, friendliness, and responsiveness of the hotel staff, including reception, housekeeping, and other staff members;
- Food and Dining—Analyzing the quality, variety, and pricing of food and beverages offered in a hotel’s dining areas;
- Location—Considering the convenience of a hotel’s location in relation to attractions, transport, and business areas;
- Shared Facilities—The quality of shared facilities such as swimming pools, fitness centers, spas, business centers, elevators and parking;
- Check-in/Check-out—Assessing the efficiency and ease of the check-in and check-out processes;
- Safety and Security—Evaluating concerns related to personal safety, security measures at the hotel, and the safety of the area;
- Internet Connectivity—Analyzing the quality and reliability of Wi-Fi or other internet services;
- Décor and Design—Reviewing guests’ perceptions of a hotel’s design, decor, and overall atmosphere, which contribute to its character and mood.
3.3. Design of Prompt Template for ChatGPT
3.3.1. Context
3.3.2. Instruction
- “Classify this complaint into the appropriate category and provide keywords or a reason for your classification with a concise single sentence”: This prompt directly instructs ChatGPT to focus on relevant hotel review criteria and summarize the reasoning behind its categorization, thus aiding in aspect-based summarization.
- “Categorization should not be overlapped”: This instruction directs ChatGPT to classify aspects in a MECE (Mutually Exclusive, Collectively Exhaustive) manner, ensuring that each category is distinct and that there is no redundancy in the responses.
- “Sentence also should be U.S. English if it is not”: Recognizing that TripAdvisor is a multilingual platform, this instruction allowed us to include reviews in various languages by translating non-English reviews into English.
- “Do not include other categories except defined above”: This instruction helped in minimizing response variation, ensuring ChatGPT adhered closely to our specified instructions and stayed aligned with this study’s objectives.
- “Do not include positive comments”: Our research concentrates on analyzing negative comments for each hotel attribute. This instruction directs ChatGPT to specifically focus on negative feedback, reducing the chance of irrelevant or off-topic responses and sharpening the precision of our sentiment analysis.
3.3.3. Output Indicator
3.3.4. Input Data
3.4. Refining ChatGPT-Generated Result
3.5. Analytical Strategy
3.5.1. Complaint Frequency Analysis
3.5.2. Topic Modelling
4. Analysis Result
4.1. Aspect-Based Summarization Result Obtained Using ChatGPT
4.2. Service Failure Frequency Analysis
4.3. Topic Analysis accross Hotel Aspects
5. Discussion
5.1. Service Failure Frequency Analysis
5.2. Topic Modelling Analysis
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A. Topic Keywords and Topic Frequency Distribution for Hotel Aspects
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 1739 | room, small, rooms, bed, bathroom, uncomfortable, tiny, beds, space, size | Room Size and Comfort: Complaints about small rooms and uncomfortable beds. |
1 | 654 | smell, room, bed, dirty, smoke, small, bugs, smoking, sheets, bathroom | Cleanliness and Odor: Issues with bad smells, unclean rooms, smoke, and pests. |
2 | 312 | air, conditioning, ac, room, noisy, unit, hot, conditioner, cold, working | Air Conditioning: Noisy or ineffective air-conditioning units. |
3 | 272 | noise, sleep, noisy, soundproofing, street, walls, room, loud, rooms, difficult | Noise Levels: Disturbances from construction, street, and adjacent rooms. |
4 | 164 | water, shower, hot, pressure, temperature, drain, bathroom, cold, room, bathtub | Water and Shower: Inconsistent shower temperature and pressure, lack of hot water. |
5 | 115 | tv, channels, television, work, working, room, remote, reception, broken, old | TV and Entertainment: TV malfunctions, poor reception, and broken remotes. |
6 | 78 | lock, door, window, close, broken, locks, doors, open, windows, hole | Locks and Security: Concerns regarding the functionality and safety of locks. |
7 | 37 | walls, paper, peeling, wallpaper, paint, room, ceiling, dirty, tiny, small | Wall Maintenance: Walls in need of repair and repainting. |
8 | 19 | toilet, flush, blocked, overflowed, backed, unpleasant, smelly, smelled, carpet, water | Toilet Functionality: Toilet-flushing issues and unpleasant odors. |
9 | 15 | old, outdated, rickety, dirty, musty, worn, avoid, antique, dated, means | Furniture and Fixtures: Old, dirty, or worn-out furniture and fixtures. |
10 | 12 | decor, outdated, dated, cheesy, leaky, roof, slightly, fashioned, fit, place | Decor and Aesthetics: Outdated or tacky decor giving a poorly maintained impression. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
Topic 0 | 1904 | desk, staff, rude, unhelpful, unprofessional, unfriendly, check, reception, unresponsive, receptionist | Front Desk Staff: Reports of rudeness and unprofessionalism. |
Topic 1 | 827 | hotel, room, staff, did, guests, noise, service, guest, provide, unresponsive | Room Service: Issues with staff responsiveness and assistance. |
Topic 2 | 188 | service, customer, poor, terrible, lack, horrible, bad, staff, mediocre, check | Overall Customer Service: General dissatisfaction with service quality. |
Topic 3 | 144 | luggage, bags, bellman, assistance, doorman, assist, help, bell, did, taxi | Luggage Assistance: Inadequate help from bellhops/doormen. |
Topic 4 | 130 | towels, housekeeping, maid, clean, room, service, days, toilet, day, sheets | Housekeeping: Infrequent maid service and lack of cleanliness. |
Topic 5 | 113 | reservation, refund, management, manager, reservations, refused, response, email, compensation, complaint | Reservations and Management: Problems with bookings, refunds, and complaint handling. |
Topic 6 | 89 | breakfast, bar, restaurant, service, bartender, drinks, waitress, slow, poor, waiter | Food and Beverage: Poor service in breakfast, bar, and restaurant areas. |
Topic 7 | 28 | smoking, non, smell, room, smoke, floor, guarantee, strong, condition, window | Room Assignments: Issues with smoking in non-smoking rooms. |
Topic 8 | 28 | key, remote, work, tv, room, phone, keys, working, safe, floor | Operational Inconveniences: Non-functional key cards and TV remotes. |
Topic 9 | 21 | card, credit, charged, unauthorized, charges, overcharged, charge, double, refund, called | Billing Disputes: Unauthorized or incorrect credit card charges. |
Topic 10 | 14 | concierge, reservations, transportation, airport, restaurant, information, did, incorrect, provided, recommendations | Concierge Services: Inadequate information and transportation arrangements. |
Topic 11 | 14 | guard, security, harassed, behavior, manager, duty, treated, situation, lobby, intrusion | Security Personnel: Reports of harassment and aggressive behavior. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 719 | room, dirty, carpet, bed, bathroom, stains, carpets, rooms, stained, filthy | Overall Cleanliness: Frequent mentions of dirty rooms and bathrooms. |
1 | 469 | hotel, dirty, cleanliness, room, bathroom, rooms, clean, sheets, poor, overall | Bathroom Condition: Complaints about mold, peeling paint, and shabbiness. |
2 | 158 | dirty, bathroom, mold, walls, room, peeling, shower, filthy, carpet, wallpaper | Room Odor: Reports of smoke smell and stale odors in rooms. |
3 | 74 | smell, smoke, room, odor, cigarette, smelled, unpleasant, stale, strong, smelly | Bed Bug Issues: Guest experiences with bed bug infestations. |
4 | 64 | bed, bugs, bug, bites, infestation, room, infested, blood, causing, sheets | Carpet Cleanliness: Dirty and stained carpets noted. |
5 | 50 | carpet, carpets, dirty, stained, stains, room, rugs, filthy, furniture, replaced | General Room Condition: Rooms described as smelly, filthy, and old. |
6 | 37 | smelly, dirty, filthy, old, dump, disgusting, horrible, extremely, dusty, property | Lobby Cleanliness: Dirtiness in lobby areas, affected by construction. |
7 | 24 | lobby, dirty, construction, filthy, mess, plastic, carpet, sticky, rooms, trash | Bathroom Hygiene: Finding hairs in bathrooms, showing cleaning lapses. |
8 | 13 | hair, hairs, bathroom, shower, dust, floor, tub, pillow, previous, left | Window Cleanliness: Dusty and dirty windows indicating poor maintenance. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 452 | room, hotel, check, process, inefficient, reservation, guest, rooms, ready, wait | Check-In Process: Reports of inefficient check-in process, including room readiness and reservation issues. |
1 | 357 | check, inefficient, process, processes, long, difficult, efficient, wait, time, reception | Overall Inefficiency: General inefficiency in both check-in and check-out processes. |
2 | 106 | desk, rude, staff, receptionist, unhelpful, long, manager, check, process, did | Front Desk Staff Behavior: Rude and unhelpful reception staff impacting the check-in experience. |
3 | 97 | charged, card, credit, billing, issue, charge, rate, charges, incorrect, payment | Billing and Charges: Credit card charge issues and billing problems during check-out. |
4 | 68 | luggage, bags, airport, assistance, check, process, service, doorman, long, leave | Luggage Assistance: Difficulties with luggage handling, leading to delays and property loss. |
5 | 51 | key, keys, room, work, working, locked, door, cards, lock, card | Room Key Issues: Inconvenience caused by non-functional room keys. |
6 | 18 | elevator, long, slow, wait, working, minutes, level, lift, accessing, waits | Elevator Service: Long waits and slow elevators, particularly during peak times. |
7 | 17 | [refund, office, refusal, money, calls, refused, customer, multiple, despite, service] | Refund Challenges: Difficulties in obtaining refunds, with management being unresponsive. |
8 | 13 | hair, hairs, bathroom, shower, dust, floor, tub, pillow, previous, left | Hot Water Availability: Inconsistencies in hot water supply, affecting guest convenience. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 417 | elevators, elevator, slow, long, wait, lifts, causing, lift, times, time | Elevators: Guests express frustration with slow elevators and long waiting times. |
1 | 201 | noise, shared, noisy, rooms, room, bathroom, loud, floor, shower, dirty | Noise Levels: Common complaints about noise from various sources impacting guest comfort. |
2 | 187 | gym, fitness, hotel, lobby, amenities, room, bar, center, facilities, restaurant | Gym/Fitness Facilities: Disappointment in the quality and availability of fitness amenities. |
3 | 52 | pool, rooftop, closed, area, advertised, water, open, hotel, stay, facilities | Pool Area: Criticisms of pool facilities not meeting expectations or having restrictive access. |
4 | 30 | ice, machine, machines, working, floor, multiple, floors, broken, drinks, quality | Ice Machines: Issues with ice machines being non-functional or empty. |
5 | 18 | car, expensive, charged, 30, extra, new, required, service, inconvenient, hotel | Parking Services: Complaints about the high cost and inconvenience of parking. |
6 | 17 | luggage, storage, pay, lack, inconvenient, door, carts, cab, 50, process | Luggage Storage: Concerns over the inconvenience and lack of security in luggage storage. |
7 | 14 | business, center, internet, work, access, available, machine, did, room, worst | Business Center: Dissatisfaction with inadequate business facilities and lack of privacy. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 244 | breakfast, continental, options, limited, coffee, poor, overpriced, quality, included, free | Breakfast Variety: Dissatisfaction with limited breakfast options and late weekend start times. |
1 | 154 | hotel, restaurant, did, breakfast, guests, does, food, dining, bar, closed | Hotel Restaurant Accessibility: Complaints about restaurant closures and restricted access to areas like rooftops. |
2 | 117 | buffet, food, overpriced, expensive, breakfast, mediocre, quality, cold, good, price | Buffet Value: Negative feedback on overpriced, uninspired buffet offerings and service issues. |
3 | 80 | service, restaurant, room, food, dirty, poor, bar, hour, dining, slow | Room Service and Restaurant Quality: Reports of poor quality and slow service in room service and restaurants. |
4 | 33 | room, service, menu, overpriced, costing, 00, night, cost, expensive, prices | Room Service Pricing: Concerns about the high cost of items on the room service menu. |
5 | 32 | bar, wine, overpriced, drinks, pricing, prices, mini, bottle, minibar, drink | Bar Pricing: High prices for drinks, especially wine, and chaotic bar atmosphere noted. |
6 | 27 | coffee, maker, machine, room, provided, rooms, tea, facilities, making, lack | Coffee Facilities: Frustration over the lack of in-room coffee-making amenities and poor coffee quality. |
7 | 22 | overpriced, rip, priced, rates, expensive, prices, worth, total, tickets, broad way | Overall Pricing Concerns: General impression of overpricing across various hotel services. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 549 | decor, room, lobby, rooms, outdated, dark, old, dirty, need, carpet | Room Decor and Comfort: Negative remarks about outdated, uncomfortable room decor and layout. |
1 | 515 | hotel, atmosphere, design, did, overall, expectations, meet, need, decor, outdated | Hotel Atmosphere: Discontent regarding the overall ambiance and design failing to meet guest expectations. |
2 | 100 | atmosphere, unpleasant, character, lack, disappointing, creepy, disgusting, overall, uncomfortable, poor | Lack of Character: Criticisms of a bland, characterless atmosphere leading to an unsatisfactory stay. |
3 | 31 | run, tired, appearance, shabby, dated, right, worn, feel, unattractive, trendy | Maintenance Issues: Observations of the hotel appearing run-down and poorly maintained. |
4 | 19 | pictures, website, misleading, photos, actual, picture, compared, does, look, like | Marketing Accuracy: Complaints about misleading promotional materials not matching the hotels reality. |
5 | 15 | service, customer, attention, lack, issues, access, going, completely, manager, corporate | Service Quality: Reports of subpar customer service, including inattentiveness and unresponsiveness. |
6 | 11 | dump, place, nasty, clean, feel, lacked, overall | Cleanliness and Overall Appeal: Negative views on the hotel’s cleanliness, with some likening it to a “dump.” |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 822 | hotel, location, convenient, square, times, noise, located, area, attractions, street | Hotel Location and Convenience: Discussions about the hotel’s location, proximity to attractions, and issues with noise and accessibility. |
1 | 239 | inconvenient, location, worth, good, attractions, great, business, price, stay, positive | Inconvenient Location: Negative feedback on the hotel being distant from key areas, affecting its suitability for business travel and overall stay value. |
2 | 41 | subway, taxis, taxi, cab, station, far, difficulty, difficult, getting, away | Subway and Taxi Access: Complaints regarding challenges in accessing public transport, including subway and taxi services. |
3 | 18 | view, park, street, room, views, construction, told, disappointing, central, floor | Room View Concerns: Discontent with room views, highlighting obstructed scenes and the questionable value of paying extra for city views. |
4 | 18 | convenient, short, recommended, convenience | Short Stay Convenience: Criticisms indicating that the hotel’s location is inconvenient, even for brief visits or specific needs. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 196 | room, internet, access, rooms, wireless, did, phone, available | Room Internet Access: Issues with limited internet access, confined mainly to areas like the lobby. |
1 | 86 | internet, slow, connection, connectivity, service, access, mention, speed, poor, issue | Internet Speed and Connectivity: Frustration over slow internet speeds and unreliable connectivity. |
2 | 78 | pay, internet, free, day, expensive, Wi-Fi, paid, room, additional, minutes | Internet Costs: Discontent with additional charges for internet usage in the hotel. |
3 | 52 | Wi-Fi, wireless, unreliable, work, worked, signal, service, works | Wi-Fi Reliability: Concerns about inconsistent Wi-Fi service and signal strength. |
4 | 22 | tv, channels, reception, cable, clear, poor, movies, fix, problems, bit | Television Service Quality: Complaints regarding inadequate TV services, including limited channels and poor reception. |
Topic | Count | Representative Keywords | Interpretation |
---|---|---|---|
0 | 556 | hotel, security, safety, concerns, room, lack, unsafe, personal, guest, guests | Hotel Security and Safety: Issues regarding insufficient security measures, emergency preparedness, and overall safety protocols in hotels. |
1 | 34 | room, presence, raises, saw, safety, hygiene, cleanliness, concerns, discovered, hotel | Room Cleanliness and Pest Presence: Concerns about hygiene and cleanliness due to pests like mice and rats in hotel rooms, affecting guest perceptions of safety. |
2 | 69 | presence, safety, concerns, room, cleanliness, personal, hygiene, hotel, guest, concern | Personal Safety and Pest Infestations: Specific focus on personal safety issues arising from pest infestations, including cockroaches and bed bugs, highlighting broader implications for hotel hygiene standards. |
References
- Koc, E. Service Failures and Recovery in Hospitality and Tourism: A Review of Literature and Recommendations for Future Research. J. Hosp. Mark. Manag. 2019, 28, 513–537. [Google Scholar] [CrossRef]
- Mattila, A.S. An Examination of Factors Affecting Service Recovery in a Restaurant Setting. J. Hosp. Tour. Res. 1999, 23, 284–298. [Google Scholar] [CrossRef]
- Ayyildiz, T.; Ayyildiz, A.Y.; Koc, E. Illusion of Control in Service Failure Situations: Customer Satisfaction/Dissatisfaction, Complaints, and Behavioural Intentions. Curr. Psychol. 2023, 43, 515–530. [Google Scholar] [CrossRef]
- Wang, K.-Y.; Hsu, L.-C.; Chih, W.-H. Retaining Customers after Service Failure Recoveries: A Contingency Model. Manag. Serv. Qual. 2014, 24, 318–338. [Google Scholar] [CrossRef]
- Leung, D.; Law, R.; Van Hoof, H.; Buhalis, D. Social Media in Tourism and Hospitality: A Literature Review. J. Travel Tour. Mark. 2013, 30, 3–22. [Google Scholar] [CrossRef]
- Bulchand-Gidumal, J.; Melián-González, S.; González López-Valcárcel, B. Improving Hotel Ratings by Offering Free Wi-Fi. J. Hosp. Tour. Technol. 2011, 2, 235–245. [Google Scholar] [CrossRef]
- Prasad, K.; Wirtz, P.W.; Yu, L. Measuring Hotel Guest Satisfaction by Using an Online Quality Management System. J. Hosp. Mark. Manag. 2014, 23, 445–463. [Google Scholar] [CrossRef]
- Sparks, B.A.; Browning, V. The Impact of Online Reviews on Hotel Booking Intentions and Perception of Trust. Tour. Manag. 2011, 32, 1310–1323. [Google Scholar] [CrossRef]
- Stringam, B.B.; Gerdes, J. An Analysis of Word-of-Mouse Ratings and Guest Comments of Online Hotel Distribution Sites. J. Hosp. Mark. Manag. 2010, 19, 773–796. [Google Scholar] [CrossRef]
- Chow, C.S.F.; Zhang, L.L.; Chow, C.S.; Zhang, L.L. Measuring consumer satisfaction and dissatisfaction intensities to identify satisfiers and dissatisfiers. J. Consum. Satisf. Dissatisfaction Complain. Behav. 2008, 21, 66–79. [Google Scholar]
- Ye, Q.; Law, R.; Gu, B.; Chen, W. The Influence of User-Generated Content on Traveler Behavior: An Empirical Investigation on the Effects of e-Word-of-Mouth to Hotel Online Bookings. Comput. Hum. Behav. 2011, 27, 634–639. [Google Scholar] [CrossRef]
- Manickas, P.A.; Shea, L.J. Hotel Complaint Behavior and Resolution: A Content Analysis. J. Travel Res. 1997, 36, 68–73. [Google Scholar] [CrossRef]
- Levy, S.E.; Duan, W.; Boo, S. An Analysis of One-Star Online Reviews and Responses in the Washington, D.C., Lodging Market. Cornell Hosp. Q. 2013, 54, 49–63. [Google Scholar] [CrossRef]
- Zhou, L.; Ye, S.; Pearce, P.L.; Wu, M.-Y. Refreshing Hotel Satisfaction Studies by Reconfiguring Customer Review Data. Int. J. Hosp. Manag. 2014, 38, 1–10. [Google Scholar] [CrossRef]
- Álvarez-Carmona, M.Á.; Aranda, R.; Rodríguez-Gonzalez, A.Y.; Fajardo-Delgado, D.; Sánchez, M.G.; Pérez-Espinosa, H.; Martínez-Miranda, J.; Guerrero-Rodríguez, R.; Bustio-Martínez, L.; Díaz-Pacheco, Á. Natural Language Processing Applied to Tourism Research: A Systematic Review and Future Research Directions. J. King Saud Univ.-Comput. Inf. Sci. 2022, 34, 10125–10144. [Google Scholar] [CrossRef]
- Ravi, K.; Ravi, V. A Survey on Opinion Mining and Sentiment Analysis: Tasks, Approaches and Applications. Knowl.-Based Syst. 2015, 89, 14–46. [Google Scholar] [CrossRef]
- Al-Smadi, M.; Al-Ayyoub, M.; Jararweh, Y.; Qawasmeh, O. Enhancing Aspect-Based Sentiment Analysis of Arabic Hotels’ Reviews Using Morphological, Syntactic and Semantic Features. Inf. Process. Manag. 2019, 56, 308–319. [Google Scholar] [CrossRef]
- Sann, R.; Lai, P.-C. Understanding Homophily of Service Failure within the Hotel Guest Cycle: Applying NLP-Aspect-Based Sentiment Analysis to the Hospitality Industry. Int. J. Hosp. Manag. 2020, 91, 102678. [Google Scholar] [CrossRef]
- Tsai, C.-F.; Chen, K.; Hu, Y.-H.; Chen, W.-K. Improving Text Summarization of Online Hotel Reviews with Review Helpfulness and Sentiment. Tour. Manag. 2020, 80, 104122. [Google Scholar] [CrossRef]
- Schuckert, M.; Liu, X.; Law, R. Hospitality and Tourism Online Reviews: Recent Trends and Future Directions. J. Travel Tour. Mark. 2015, 32, 608–621. [Google Scholar] [CrossRef]
- Pan, B.; Chenguang Wu, D.; Song, H. Forecasting Hotel Room Demand Using Search Engine Data. J. Hosp. Tour. Technol. 2012, 3, 196–210. [Google Scholar] [CrossRef]
- Kocoń, J.; Cichecki, I.; Kaszyca, O.; Kochanek, M.; Szydło, D.; Baran, J.; Bielaniewicz, J.; Gruza, M.; Janz, A.; Kanclerz, K.; et al. ChatGPT: Jack of All Trades, Master of None. Inf. Fusion 2023, 99, 101861. [Google Scholar] [CrossRef]
- Koc, E.; Hatipoglu, S.; Kivrak, O.; Celik, C.; Koc, K. Houston, We Have a Problem!: The Use of ChatGPT in Responding to Customer Complaints. Technol. Soc. 2023, 74, 102333. [Google Scholar] [CrossRef]
- Koubaa, A.; Boulila, W.; Ghouti, L.; Alzahem, A.; Latif, S. Exploring ChatGPT Capabilities and Limitations: A Critical Review of the NLP Game Changer. Math. Comput. Sci. 2023, preprint. [Google Scholar]
- Cho, H.; Kim, S.; Lee, J.; Lee, J.-S. Data-Driven Integration of Multiple Sentiment Dictionaries for Lexicon-Based Sentiment Classification of Product Reviews. Knowl.-Based Syst. 2014, 71, 61–71. [Google Scholar] [CrossRef]
- Blei, D.M. Latent Dirichlet Allocation. J. Mach. Learn. Res. 2003, 3, 993–1022. [Google Scholar]
- Shams, M.; Baraani-Dastjerdi, A. Enriched LDA (ELDA): Combination of Latent Dirichlet Allocation with Word Co-Occurrence Analysis for Aspect Extraction. Expert Syst. Appl. 2017, 80, 136–146. [Google Scholar] [CrossRef]
- Ray, B.; Garain, A.; Sarkar, R. An Ensemble-Based Hotel Recommender System Using Sentiment Analysis and Aspect Categorization of Hotel Reviews. Appl. Soft Comput. 2021, 98, 106935. [Google Scholar] [CrossRef]
- Akhtar, N.; Zubair, N.; Kumar, A.; Ahmad, T. Aspect Based Sentiment Oriented Summarization of Hotel Reviews. Procedia Comput. Sci. 2017, 115, 563–571. [Google Scholar] [CrossRef]
- Hegde, R.; Seema, S. Aspect Based Feature Extraction and Sentiment Classification of Review Data Sets Using Incremental Machine Learning Algorithm. In Proceedings of the 2017 Third International Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics (AEEICB), Chennai, India, 27–28 February 2017; IEEE: Chennai, India; pp. 122–125. [Google Scholar]
- Srivastava, R.; Singh, P.; Rana, K.P.S.; Kumar, V. A Topic Modeled Unsupervised Approach to Single Document Extractive Text Summarization. Knowl.-Based Syst. 2022, 246, 108636. [Google Scholar] [CrossRef]
- Ma, Y.; Li, Q. A Weakly-Supervised Extractive Framework for Sentiment-Preserving Document Summarization. World Wide Web 2019, 22, 1401–1425. [Google Scholar] [CrossRef]
- Abdi, A.; Shamsuddin, S.M.; Hasan, S.; Piran, J. Machine Learning-Based Multi-Documents Sentiment-Oriented Summarization Using Linguistic Treatment. Expert Syst. Appl. 2018, 109, 66–85. [Google Scholar] [CrossRef]
- Amplayo, R.K.; Song, M. An Adaptable Fine-Grained Sentiment Analysis for Summarization of Multiple Short Online Reviews. Data Knowl. Eng. 2017, 110, 54–67. [Google Scholar] [CrossRef]
- Hu, Y.-H.; Chen, Y.-L.; Chou, H.-L. Opinion Mining from Online Hotel Reviews—A Text Summarization Approach. Inf. Process. Manag. 2017, 53, 436–449. [Google Scholar] [CrossRef]
- Tan, J.; Kotov, A.; Pir Mohammadiani, R.; Huo, Y. Sentence Retrieval with Sentiment-Specific Topical Anchoring for Review Summarization. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore, 6 November 2017; ACM: Singapore, 2017; pp. 2323–2326. [Google Scholar]
- Li, J.; Li, H.; Zong, C. Towards Personalized Review Summarization via User-Aware Sequence Network. AAAI 2019, 33, 6690–6697. [Google Scholar] [CrossRef]
- Zhong, Q.; Ding, L.; Liu, J.; Du, B.; Tao, D. Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-Tuned BERT. arXiv 2023, arXiv:2302.10198. [Google Scholar]
- Yang, X.; Li, Y.; Zhang, X.; Chen, H.; Cheng, W. Exploring the Limits of ChatGPT for Query or Aspect-Based Text Summarization. arXiv 2023, arXiv:2302.08081. [Google Scholar]
- Wei, X.; Cui, X.; Cheng, N.; Wang, X.; Zhang, X.; Huang, S.; Xie, P.; Xu, J.; Chen, Y.; Zhang, M.; et al. Zero-Shot Information Extraction via Chatting with ChatGPT. arXiv 2023, arXiv:2302.10205. [Google Scholar]
- Törnberg, P. How to Use LLMs for Text Analysis. arXiv 2023, arXiv:2307.13106. [Google Scholar]
- Qin, C.; Zhang, A.; Zhang, Z.; Chen, J.; Yasunaga, M.; Yang, D. Is ChatGPT a General-Purpose Natural Language Processing Task Solver? arXiv 2023, arXiv:2302.06476. [Google Scholar]
- Han, R.; Peng, T.; Yang, C.; Wang, B.; Liu, L.; Wan, X. Is Information Extraction Solved by ChatGPT? An Analysis of Performance, Evaluation Criteria, Robustness and Errors. arXiv 2023, arXiv:2305.14450. [Google Scholar]
- Hotel Review Datasetes. Available online: https://www.cs.cmu.edu/~jiweil/html/hotel-review.html (accessed on 29 December 2023).
- Guo, Y.; Barnes, S.J.; Jia, Q. Mining Meaning from Online Ratings and Reviews: Tourist Satisfaction Analysis Using Latent Dirichlet Allocation. Tour. Manag. 2017, 59, 467–483. [Google Scholar] [CrossRef]
- Gerdt, S.-O.; Wagner, E.; Schewe, G. The Relationship between Sustainability and Customer Satisfaction in Hospitality: An Explorative Investigation Using eWOM as a Data Source. Tour. Manag. 2019, 74, 155–172. [Google Scholar] [CrossRef]
- Hu, N.; Zhang, T.; Gao, B.; Bose, I. What Do Hotel Customers Complain about? Text Analysis Using Structural Topic Model. Tour. Manag. 2019, 72, 417–426. [Google Scholar] [CrossRef]
- Akbik, A.; Bergmann, T.; Blythe, D.; Rasul, K.; Schweter, S.; Vollgraf, R. FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), Minneapolis, MN, USA, 2–7 June 2019. [Google Scholar]
- Grootendorst, M. BERTopic: Neural Topic Modeling with a Class-Based TF-IDF Procedure. arXiv 2022, arXiv:2203.05794. [Google Scholar]
- Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. arXiv 2018, arXiv:1810.04805. [Google Scholar]
- Li, H.; Ye, Q.; Law, R. Determinants of Customer Satisfaction in the Hotel Industry: An Application of Online Review Analysis. Asia Pac. J. Tour. Res. 2013, 18, 784–802. [Google Scholar] [CrossRef]
- Berezina, K.; Bilgihan, A.; Cobanoglu, C.; Okumus, F. Understanding Satisfied and Dissatisfied Hotel Customers: Text Mining of Online Hotel Reviews. J. Hosp. Mark. Manag. 2016, 25, 1–24. [Google Scholar] [CrossRef]
- Xu, X.; Li, Y. The Antecedents of Customer Satisfaction and Dissatisfaction toward Various Types of Hotels: A Text Mining Approach. Int. J. Hosp. Manag. 2016, 55, 57–69. [Google Scholar] [CrossRef]
- Büschken, J.; Allenby, G.M. Sentence-Based Text Analysis for Customer Reviews. Mark. Sci. 2016, 35, 953–975. [Google Scholar] [CrossRef]
- Mankad, S.; Han, H.S.; Goh, J.; Gavirneni, S. Understanding Online Hotel Reviews through Automated Text Analysis. Serv. Sci. 2016, 8, 124–138. [Google Scholar] [CrossRef]
Feature | Previous Works | This Study |
---|---|---|
Aspect identification | Various methods ranging from frequency-based to unsupervised learning like LDA [16,26,27]. | Automated detection using ChatGPT, enhancing precision and reducing subjectivity. |
Sentiment identification | Primarily relies on manual coding or machine learning models, facing challenges regarding scalability and subjectivity [17,25]. | Automated detection via ChatGPT combined with BERT for negative sentiment filtering, offering a comprehensive and nuanced sentiment analysis. |
Text summarization | Both extractive and abstractive methods, limited by their reliance on manual input for effectiveness [19,32,33,34,35,36,37]. | Automated summarization through ChatGPT, offering a novel approach to creating concise, meaningful summaries from extensive review data. |
Topic modelling | LDA and other traditional methods for topic detection, often limited by the need for extensive manual tuning [26,27]. | Advanced modeling with Bertopic, leveraging deep learning to uncover nuanced insights and trends in customer feedback, surpassing traditional LDA’s capabilities. |
Topic | Aspect-Based Summarization Result produced by ChatGPT |
---|---|
We stayed at the CP during our recent trip to NYC. The location is great and most of the people working there were very helpful and polite. (the lone exception was the balding guy with glasses at the information desk). But if you are going to stay here, be prepared for the rooms to be average at best. Worn furniture and carpet, not overly clean, and run down in general. We had a great time and used the room only at night, so if the room is not that big of a deal this hotel is OK, but if you are looking for nice, go elsewhere. | -room_quality: worn furniture and carpet, not overly clean, and run down in general |
This place was tiny, run down and dirty. The staff was rude and it was close to nothing that was pen late night. It was better than Motel 6 but not much. oh and the elevator broke down. | -location: close to nothing that was open late night -room_quality: tiny, run down |
Pulled up...valet came out to greet me. Turns out he was the valet AND the bellhop. After the 10 min it took to get luggage to the room, he went downstairs to presumably park the car. About 10 min later got a call that my car had been hit by a truck (which was under vontract to the hotel to remove laundry). No apology was made for the incident, no offer for compensation given. Later, after dealing with the front desk and on-call manager, neother of whom made any effort to make my stay better, I was given the General Managers number. He made the call to compensate me for my room, albeit reluctantly. Additionally, folks above me were playing music and throwing stuff off their patio at at 4 AM. If you are teir on the weekend have to fight through a velvet rope to get back to your room amongst the desperate ho hos that skank around its first floor club. | -service_quality: Unprofessional and unresponsive staff, no apology or compensation for car incident -location: Inconvenience of fighting through a velvet rope to access rooms -room_quality: Noise disturbance from guests above and lack of security in the hotel |
Stayed 26–28 December 2005. A modest hotel on the upper West side, the rate of $330 this time for 3 people in a “suite” came too close to better hotels mid-town. Staff were great as usual, and the room is large by NYC standards. But the old HVAC system, which worked on a whim, soured the stay as the room temp alternately went from very cold to too hot.\nThe ajoining resturant, where Lucerne provides a 20% breakfast discount, still suffers from very poor service. Marybeth’s, one block away, is far superior. | -room_quality: The old HVAC system, which worked on a whim, soured the stay as the room temp alternately went from very cold to too hot. -food_dining: The adjoining restaurant, where Lucerne provides a 20 breakfast discount, still suffers from very poor service. |
Stayed in the Wellington Hotel for two nights only, thankfully…Took ages to check in, there was a queue a mile long with two persons on the desk. Whilst I was checking in, two groups approached the reception desk to make complaints. The room we were allocated was small, carpet was filthy, there were chips gone out of furniture and the air conditioning units outside the windows were awfully noisy. We refused to stay in this room, and all that was available seemingly was a smaller room, however it was much cleaner so we agreed to stay there. We were only in new york for two days and most certainly did not want to have to go searching for another hotel!!! The only thing going for this hotel is it’s location, it’s just a couple of mins away from central park/carnegie hall/time square! | -check-in/check-out: long wait to check in with complaints from other guests -room_quality: small room with noisy air conditioning units |
Hotel Aspect | Budget Hotels | Mid-Range Hotels | Luxury Hotels |
---|---|---|---|
Room Quality | Concerns about size, comfort, and cleanliness. | Air conditioning and noise levels are problematic. | High standards for size and comfort are prioritized. |
Service Quality | Front desk interactions are the most problematic. | Similar concerns, with emphasis on staff responsiveness. | High expectations for staff interaction and responsiveness. |
Cleanliness | Issues with mold, peeling paint, and odor are prominent. | General cleanliness concerns, with odor issues noted. | Highest concern for room and bathroom cleanliness. |
Check-in/Check-out | Inefficiencies in processes; rude staff. | Similar issues, with slightly lower emphasis. | Slightly higher percentages of check-in process issues. |
Shared Facilities | Noise disturbances; elevator service issues are prominent. | Elevator speed and wait times are major concerns. | Expectations for high-quality gym and pool facilities. |
Food and Dining | Limited breakfast options are a primary issue. | Concerns about value and unexpected closures of restaurants. | Overpriced food and dissatisfaction with service quality. |
Décor and Design | Focus on room decor and comfort; hotel atmosphere issues. | Equal dissatisfaction with room decor and hotel atmosphere. | Dissatisfaction with atmosphere surpasses room decor concerns. |
Location | Inconvenience of location in relation to attractions noted. | Highest emphasis on location convenience and proximity. | Proximity to attractions/business centers is crucial. |
Internet Connectivity | Internet speed and access are critical, with moderate concerns. | Highest amount of scrutiny directed toward internet access and speed. | Costs associated with internet services are a standout issue. |
Safety and Security | General safety and security concerns are significant. | Similar emphasis on safety, slightly less than that for luxury hotels. | Safety and security are the paramount concerns. |
Related Study | Data Source | Methods | Findings |
---|---|---|---|
Manickas and Shea (1997) [12] | 220 complaints | Frequency-based methods | ● Customers generally complained about fundamental service failures, such as declined service quality and rude employees. |
H. Li et al. (2013) [51] | 42,668 online reviews | Frequency-based methods | ● Customers complained frequently about beds, reception services, and room size and decoration. |
Berezina et al. (2016) [52] | 2510 online reviews | Frequency-based methods | ● Complaints were about tangible aspects such as facility-related issues and cleanliness. |
Hu et al. (2019) [45] | 27,864 online reviews | Topic Modelling (STM) | ● High-end Hotels: Complaints were focused on intangible service issues and perceived value for the amount of money paid. ● Low-end Hotels: Complaints were about tangible aspects such as facility-related issues and cleanliness. |
Xu and Lee (2016) [53] | 3480 online reviews | Topic Modelling (LSA) | ● Full-Service Hotels: Wi-Fi quality, staff helpfulness, facilities’ condition, parking, and bathroom cleanliness are major dissatisfaction points. ● Limited-Service Hotels: Noise is the main dissatisfaction factor, along with smoking, Wi-Fi, and vending machine issues. ● Suite Hotels with F&B: The cleanliness of rooms is a significant complaint, followed by issues with restaurants, parking, swimming pools, and air conditioning. ● Suite Hotels without F&B: Dissatisfaction stems from smoking/polluted air, noise, dirty bathrooms, slow Wi-Fi, and outdated facilities. |
Guo et al. (2017) [46] | 266,544 online reviews | Topic Modelling (LDA) | ● One-Star Hotels: Room experience and communication are prevalent complaints. ● Mid-Range Hotels: Focus on basic aspects like parking, check-in/out process, staff service, bathroom facilities, and price. ● Four/Four-and-a-Half-Star Hotels: Emphasis on the quality of hotel and resort facilities, food, room size, and decoration. ● Five-Star Hotels: Homeliness, event management, pet friendliness, and luxury differentiation are key attributes. |
Büschken and Allenby (2016) [54] | 4467 online reviews of hotels in New York | Topic Modelling (LDA) | ● Upscale Hotels in Manhattan: Check-in problems, room issues, noise, Wi-Fi charges, and inadequate amenities are dissatisfaction drivers. Positive factors include staff friendliness and willingness to return. ● Midscale Hotels near JFK International Airport: Complaints focus on noise, unpleasant odors, front desk service, and carpet cleanliness. Positive aspects are good service responses and proximity to JFK International Airport. |
Mankad et al. (2016) [55] | 5830 online reviews of 57 hotels in Moscow, Russia | Topic Modelling (LDA) | ● Reviews mentioning location and experience are associated with higher ratings. Reviews discussing transactions and value are associated with lower ratings. ● Amenities are less influential on ratings when sentiment is factored in, implying a more objective viewpoint on this aspect. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jeong, N.; Lee, J. An Aspect-Based Review Analysis Using ChatGPT for the Exploration of Hotel Service Failures. Sustainability 2024, 16, 1640. https://doi.org/10.3390/su16041640
Jeong N, Lee J. An Aspect-Based Review Analysis Using ChatGPT for the Exploration of Hotel Service Failures. Sustainability. 2024; 16(4):1640. https://doi.org/10.3390/su16041640
Chicago/Turabian StyleJeong, Nayoung, and Jihwan Lee. 2024. "An Aspect-Based Review Analysis Using ChatGPT for the Exploration of Hotel Service Failures" Sustainability 16, no. 4: 1640. https://doi.org/10.3390/su16041640
APA StyleJeong, N., & Lee, J. (2024). An Aspect-Based Review Analysis Using ChatGPT for the Exploration of Hotel Service Failures. Sustainability, 16(4), 1640. https://doi.org/10.3390/su16041640