Consumer recommendation prediction in online reviews using Cuckoo optimized machine learning models. (October 2021)

• Record Type: Journal Article
• Authors: Jain, Praphula Kumar; Yekun, Ephrem Admasu; Pamula, Rajendra; Srivastava, Gautam
• Is Part Of: Computers & electrical engineering. Volume 95(2021)
• Publication Date: 2021-10
• Subjects: Online reviews -- Cuckoo Search -- Machine learning -- Sentiment analysis -- Recommendation prediction -- Extreme gradient boosting; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107397
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Digital technology and social media have delivered many advantages in understanding human psychology, which is essential to industrial growth. Skytrax is an online social media platform for travellers to write reviews on airlines. In online reviews, consumer recommendations are critical indicators for service providers to improve their consumer policies as well as service quality. It is also helpful for future customers to help get information on future purchases prior to making them. Therefore, previous consumer recommendations based on online reviews play a vital role in airline recommendations. Our main goal is to use our proposed cuckoo optimized machine learning model to predict airline recommendations. Experimental analysis was implemented using data scraped from the website https://www.airlinequality.com . Our results show that the proposed eXtreme gradient boosting classifier optimized by Cuckoo Search (CS-XGB) outperforms other state-of-the-art techniques. Graphical abstract: Highlights: Propose a consumer recommendation prediction system using online review. Acquired consumer online reviews and ratings from Skytrax. Applied various pre-processing schemes to input data and feed it to the model. Create a Cuckoo Search (CS) based parameter optimization model. Proposed CS-XGB outperforms the other state-of-the-art techniques.