Disentangling consumer recommendations: Explaining and predicting airline recommendations based on online reviews

Siering, Michael; Deokar, Amit V.; Janze, Christian

doi:10.1016/j.dss.2018.01.002

Cited by 168 publications

(121 citation statements)

References 47 publications

Supporting

Mentioning

110

Contrasting

Unclassified

Order By: Relevance

“…Skytrax is an airline quality assessment website that performs an online assessment after the customer directly used each airline [1]. Skytrax has worked for over 150 airlines across the globe, from the world's largest airlines through to small domestic carriers and it is a world-recognized brand that provides professional audit and service benchmarking programs for airlines on product and service quality.…”

Section: Skytraxmentioning

confidence: 99%

See 1 more Smart Citation

Understanding Customer Experience and Satisfaction through Airline Passengers’ Online Review

Ban

Kim

2019

Sustainability

View full text Add to dashboard Cite

This study was conducted to understand customer experience and satisfaction through airline passengers' online review. To achieve the purpose of this study, the semantic network analysis was conducted qualitatively by collecting reviews in top 10 airlines selected by Skytrax (airlinequality.com). In addition, this study quantitatively identified the relationship among six evaluation factors (seat comfort, staff, food and beverage (F&B), entertainment, ground service, and value for money), customer satisfaction and recommendation. This study collected 9632 reviews from the Skytrax. Through a CONCOR (CONvergence of iterated CORrelation) analysis, keywords were grouped into six clusters (seat comfort, staff, entertainment, ground service, value for money, and airline brand). Through the linear regression analysis, all evaluation factors except 'entertainment' factor significantly had impact on customer satisfaction and recommendation. These results showed that understanding online review can provide both academic implication and practical implication to develop sustainable strategy in the airline industry.

show abstract

Section: Skytraxmentioning

confidence: 99%

“…Due to fierce competition in the airline industry, the airline company needs to focus on the passenger's experience and satisfaction [1]. Customer feedback, in particular, is critical since it is an outcome measurement for business performance [2].…”

Section: Introductionmentioning

confidence: 99%

Understanding Customer Experience and Satisfaction through Airline Passengers’ Online Review

Ban

Kim

2019

Sustainability

View full text Add to dashboard Cite

show abstract

“…Machine learning based methods utilize unsupervised and/or supervised learning techniques to extract aspects and sentiments from textual contents. For example, Siering et al [6] utilized text statistics and linguistic information to extract a variety of aspects from airline company reviews, then they trained the supervised classifiers to assign sentiments to different aspects, for the purpose of explaining and providing recommendations to (potential) customers. Additionally, Akhtar et al [7] designed an optimizer-based feature selection method to extract aspects terms from texts, then an ensemble machine learning model was trained to classify sentiments toward extracted aspects.…”

Section: Related Workmentioning

confidence: 99%

“…It is more efficient to treat both steps in a holistic fashion, to avoid separating the explicit or implicit logical/semantic connects between them. • Several prior related studies extract aspects and sentiments at word level [6,9]; while other studies rely on linguistic patterns among words [5,10]. However, it is beneficial to treat sentences as sequences (of words) to maintain the semantic meanings in them.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Toward multi-label sentiment analysis: a transfer learning based approach

2020

View full text Add to dashboard Cite

Sentiment analysis is recognized as one of the most important sub-areas in Natural Language Processing (NLP) research, where understanding implicit or explicit sentiments expressed in social media contents is valuable to customers, business owners, and other stakeholders. Researchers have recognized that the generic sentiments extracted from the textual contents are inadequate, thus, Aspect Based Sentiment Analysis (ABSA) was coined to capture aspect sentiments expressed toward specific review aspects. Existing ABSA methods not only treat the analytical problem as single-label classification that requires a fairly large amount of labelled data for model training purposes, but also underestimate the entity aspects that are independent of certain sentiments. In this study, we propose a transfer learning based approach tackling the aforementioned shortcomings of existing ABSA methods. Firstly, the proposed approach extends the ABSA methods with multi-label classification capabilities. Secondly, we propose an advanced sentiment analysis method, namely Aspect Enhanced Sentiment Analysis (AESA) to classify text into sentiment classes with consideration of the entity aspects. Thirdly, we extend two state-of-the-art transfer learning models as the analytical vehicles of multi-label ABSA and AESA tasks. We design an experiment that includes data from different domains to extensively evaluate the proposed approach. The empirical results undoubtedly exhibit that the proposed approach outperform all the baseline approaches.

show abstract

But it was supposed to be healthy! How expected and actual nutritional value affect the content and linguistic characteristics of online reviews for food products

Wang

Kuchmaner

et al. 2023

J Consum Psychol

View full text Add to dashboard Cite

Consumers are choosing to purchase food products from retailers through online channels rather than brick‐and‐mortar channels. While online reviews play a crucial role in influencing online purchases, scant work has examined how consumers write reviews for food products. We argue that the nutritional value of the food is a key aspect of product performance and apply expectation‐disconfirmation theory to examine whether pre‐purchase expectations about a food product's nutritional value and disconfirmation of these expectations have a significant effect on online review content and linguistic characteristics. Using text‐mining approaches to analyze Amazon data, we find that pre‐purchase expectations, postpurchase performance, and disconfirmation regarding nutritional value affect both review content and linguistic characteristics, including review length, diversity, readability, subjectivity, and sentiment. While research suggests that postpurchase product performance is the main influence on online review writing behavior, this research shows that the pre‐purchase phase also plays a key role.

show abstract

Disentangling consumer recommendations: Explaining and predicting airline recommendations based on online reviews

Cited by 168 publications

References 47 publications

Understanding Customer Experience and Satisfaction through Airline Passengers’ Online Review

Understanding Customer Experience and Satisfaction through Airline Passengers’ Online Review

Toward multi-label sentiment analysis: a transfer learning based approach

But it was supposed to be healthy! How expected and actual nutritional value affect the content and linguistic characteristics of online reviews for food products

Contact Info

Product

Resources

About