Related Experiment Video
Updated: Nov 6, 2025
08:00
Decoding Natural Behavior from Neuroethological Embedding
Published on: October 3, 2025
193
Exploring Sources of Satisfaction and Dissatisfaction in Airbnb Accommodation Using Unsupervised and Supervised Topic
Kai Ding1, Wei Chong Choo1, Keng Yap Ng2
1Department of Management and Marketing, Faculty of Economics and Management, Universiti Putra Malaysia, Seri Kembangan, Malaysia.
Frontiers in Psychology
|May 10, 2021
Summary
Analyzing 59,766 Airbnb reviews, this study identifies key factors influencing user satisfaction and dissatisfaction. Findings reveal distinct attributes for positive and negative experiences, offering insights for improving accommodation services.
Area of Science:
- Hospitality Management
- Consumer Behavior Analysis
- Data Science in Tourism
Background:
- Online reviews are crucial for understanding customer satisfaction in the sharing economy.
- Previous research often aggregates positive and negative feedback, potentially masking important nuances.
- The Airbnb platform presents a unique case for studying user satisfaction due to its diverse offerings and shared environments.
Purpose of the Study:
- To identify and analyze key attributes influencing Airbnb user satisfaction and dissatisfaction separately.
- To explore the heterogeneity of satisfaction and dissatisfaction drivers across different Airbnb property types.
- To provide actionable managerial insights for enhancing user experience and satisfaction.
Main Methods:
- Analysis of a large corpus (59,766 reviews) from 27,980 Airbnb listings across 12 cities.
- Application of Latent Dirichlet Allocation (LDA) and supervised LDA (sLDA) for topic modeling and attribute prediction.
- Separate examination of positive and negative reviews to uncover distinct satisfaction and dissatisfaction factors.
Main Results:
- Satisfaction and dissatisfaction attributes in Airbnb accommodation are heterogeneous.
- A novel topic, 'guest conflicts,' emerged, highlighting the importance of guest interactions in shared spaces.
- Home-like experience and host assistance are strongly linked to users' revisit intention.
- Specific attributes were identified with the strongest predictive power for satisfaction and dissatisfaction.
Conclusions:
- Understanding the distinct drivers of satisfaction and dissatisfaction is crucial for Airbnb practitioners.
- The study offers methodological contributions in transforming social media data into actionable customer insights.
- Future research should investigate guest interactions within shared accommodation environments.
- Managerial strategies can be prioritized based on attributes with the highest predictive power for user satisfaction.
Keywords:
Airbnbbig datacustomer satisfactionsharing economysupervised topic modelingtext mininguser-generated contentMore Related Videos
08:12A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
Published on: March 1, 2022
2.7K
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
148
Related Concept Videos
02:16Stereotype Content Model
15.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.0K
01:11Residuals and Least-Squares Property
8.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
8.2K
02:45Self-Discrepancy Theory
18.6K
One influential perspective on what motivates people's behavior is detailed in Tory Higgin's self-discrepancy theory (Higgins, 1987). He proposed that people hold disagreeing internal representations of themselves that lead to different emotional states.
18.6K
03:00Self-Evaluation: Self-Enhancement and Self-Verification
5.5K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.5K
01:16Goodness-of-Fit Test
6.3K
The goodness-of-fit test is a type of hypothesis test which determines whether the data "fits" a particular distribution. For example, one may suspect that some anonymous data may fit a binomial distribution. A chi-square test (meaning the distribution for the hypothesis test is chi-square) can be used to determine if there is a fit. The null and alternative hypotheses may be written in sentences or stated as equations or inequalities. The test statistic for a goodness-of-fit test is given as...
6.3K
02:05Degree of Unsaturation
9.3K
The degree of unsaturation (U), or index of hydrogen deficiency (IHD), is defined as the difference in the number of pairs of hydrogen atoms between the compound and the acyclic alkane with the same number of carbon atoms. Each double bond or ring costs two hydrogen atoms compared to a saturated analog and results in one degree of unsaturation.
The degree of unsaturation for hydrocarbons is U = (2C + 2 − H) / 2, where C is the number of carbon atoms and H is the number of hydrogen atoms.
The degree of unsaturation for hydrocarbons is U = (2C + 2 − H) / 2, where C is the number of carbon atoms and H is the number of hydrogen atoms.
9.3K