A personalized recommender system for SaaS services

Afify, Yasmine M.; Moawad, Ibrahim F.; Badr, Nagwa L.; Tolba, Mohamed F.

doi:10.1002/cpe.3877

Cited by 12 publications

(2 citation statements)

References 37 publications

(98 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many other features of the SaaS model such as customization should be studied, too. Afify et al (2017) introduced a new approach to the service reputation calculation from the customer reactions. SaaS Recommender (SaaSRec) addresses many challenges met by the generic recommender systems.…”

Section: Business Applications In Cloud Environmentsmentioning

confidence: 99%

Towards techniques, challenges and efforts of software as a service layer based on business applications in cloud environments

Fardinpour

Milani

Norouzi

2020

View full text Add to dashboard Cite

Purpose Cloud computing is qualified to present proper limitless storage and computation resources to users as services throughout the internet. Software as a service (SaaS) layer is the key paradigm perspective in the software layer of the cloud computing. SaaS is connected by business applications to access consumers on existing public, private and hybrid cloud models. This purpose of this paper is to present a discussion and analysis on the SaaS layer based on business applications in the cloud environment in form of a classical taxonomy to recognize the existing techniques, challenges and efforts. Design/methodology/approach Existing techniques, challenges and efforts are classified into four categories: platform-dependent, application-dependent, data-dependent and security-dependent mechanisms. The SaaS layer mechanisms are compared with each other according to the important factors such as the structural properties, quality of service metrics, applied algorithms and measurement tools. Findings The benefits and weaknesses of each research study are analyzed. In the comparison results, the authors observed that the application-based method, the non-heuristic algorithms, the business process method have the highest percentage of the usage in this literature. Originality/value The SaaS layer mechanisms based on business applications have some main features such as high accessibility, compatibility, reusability and collaboration to provide activated application and operation services for user with help of Web browsers. A comprehensive analysis was presented as originality on the SaaS layer mechanisms based on business applications for high level of the cloud environment that 46 peer-reviewed studies were considered.

show abstract

Section: Business Applications In Cloud Environmentsmentioning

confidence: 99%

Towards techniques, challenges and efforts of software as a service layer based on business applications in cloud environments

Fardinpour

Milani

Norouzi

2020

View full text Add to dashboard Cite

show abstract

“…This type of system is called a feedback-based reputation system [4]. One main obstacle for feedback-based reputation models is sparsity of ratings [2], [3], [19]. That is, there is insufficient data to build the reputation score.…”

Section: Introductionmentioning

confidence: 99%

A Lexicon-based Approach to Build Service Provider Reputation from Arabic Tweets in Twitter

Al-Hussaini¹,

Al-Dossari²

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Nowadays Social media has become a popular communication tool among Internet users. Many users share opinions and experiences on different service providers everyday through the social media platforms. Thus, these platforms become valuable sources of data which can be exploited and used efficiently to support decision-making. However, finding and monitoring customers' opinions on the social media is difficult task due to the fast growth of the content. This work focus on using Twitter for the task of building service providers' reputation. Particularly, service provider's reputation is calculated from the collected Saudi tweets in Twitter. To do so, a Saudi dialect lexicon has been developed as a basic component for sentiment polarity to classify words extracted from Twitter into either a positive or negative word. Then, beta probability density functions have been used to combine feedback from the lexicon to derive reputation scores. Experimental evaluations show that the proposed approach were consistent with the results of Qaym, a website that calculates restaurants' rankings based on consumer ratings and comments.

show abstract