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.

Nowadays, many social media platforms are widely used to express people’s opinions about their daily experiences and interests. These platforms encourage people to exchange and share information about a particular brand, company or even a political point of view. Consequently, huge amount of data which can be extracted and analyzed to obtain some useful knowledge are available. In this paper, we propose to build a reputation of a given service provider (i.e. brand, product or service) from the collected social media data. To do so, we have developed a lexicon as a basic component for sentiment polarity in Arabic idioms. That is, the lexicon is used to classify words extracted from “Tweets” into either a positive or negative word. We use beta probability density functions to combine feedback from the lexicon to derive reputation scores. The experimental results show that our proposed approach is consistent with sentiment analysis approach results.