CROSA: Context‐aware cloud service ranking approach using online reviews based on sentiment analysis

Abstract

The explosion of cloud services over the Internet has raised new challenges in cloud service selection and ranking. The existence of a great variety of offered cloud services made the users think deeply about the most appropriate services that meet their needs and at the same time are adaptable to their context. Nowadays, online reviews are used for the purpose of enhancing the effectiveness of finding useful product information, having impact on the consumers' decision-making process. In this context, the current paper suggests a context-aware cloud service ranking approach using online reviews and based on sentiment analysis (CROSA). Its main objective is to ease the cloud service selection. The CROSA approach analyzes sentiments associated with service measurement index (SMI)-based service properties for each alternative cloud service. Moreover, it enhances the cloud service decision-making by supporting fuzzy sentiments through the intuitionistic fuzzy set theory and PROMETHEE II. The experimental results presented in this paper show that this approach is efficient and performing.

Parameter Reputation Model for Cloud Service Recommendation and Ranking Using Opinion Mining

“…The author also proposed four prediction models to predict the sentiment of user reviews based on existing supervised machine learning algorithms, such as Random Forest, Random Tree, Naive Bayes and K-Nearest Neighbours. Ben-Abdallah et al [37] presented a system named CROSA that can rank cloud services based on different service-based properties and context of the user. The system considers the online reviews and feedbacks to effectively find the usefulness of the service and to help consumers in the decision-making process.…”

“…Further, the weighted percentages of reviews of one product concerning one feature are calculated using fuzzy set logic and relevant weighting schemes, and according to these weights, an intuitionistic fuzzy number is assigned to each feature that represents the performance of an alternative product concerning a product feature. After analysis of above mentioned work, we find some of the limitations are as follows: (1) limited QoS parameters considered [18,20,32,38,39], (2)parameters importance and/or reputation based evaluation not considered [23,32,37,38,39], (3) consideration of both positive and negative parameters based comparison lacked [32,37,38,39]. Our proposedmodel addresses all those limitations and provides the efficient service selection and ranking solution.…”

Container description ontology for CaaS

“…More and more the enterprises are turning to the cloud computing thanks to their low costs and availability of services and data from any location, on any type of media at any time [12,15,3]. Besides its classical three service models (IaaS, PaaS, and SaaS), cloud computing has been recently empowered by a new service offering called Containersas-a-Service (CaaS) [18].…”

Personalized cloud service review analysis based on modularized ontology

“…The review structure (pros and cons, likes and dislikes) has been used in their study to fine tune the sentiment polarity classification of structured reviews. In our previous (Ben-Abdallah et al, 2019), we proposed a contextaware cloud service ranking approach using online reviews based on sentiment analysis (CROSA). The CROSA approach aims at recommending cloud services based on customers' reviews having contexts similar to that of the end-user.…”

“…However, these works are seen to be focusing on the data extraction process only. The authors in Ben-Abdallah et al (2019), Jayaratna et al (2017) for example, did an outstanding job in mining the data from the available customer's reviews; however, they did not pay attention to the semantic aspect. We believe that the extracted features should be appropriately organized according to their main categories to get a better information management system.…”