A Lexicon-Based Approach to Build Reputation from Social Media

Abstract

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.