Twitter is an online social networking (OSN) service that enables users to send and read short messages called “tweets”. As of December 2014, Twitter has more than 500 million users, out of which more than 284 million are active users and about 500 million tweets are posted every day. Tweet sentiment analysis (TSA) identifies a valuable platform for the OSN study which provides insights into the opinion of the public about culture, products and political agendas and thereby is able to predict the trends in specific domains. In order to execute efficient TSA on a particular topic or domain, a TSA approach with unified tool, UnB TSA, is proposed consisting of four steps: tweets collection, refinement (excluding noisy tweets), sentiment lexicon creation and sentiment analysis. As a key part, the lexicon is domain-specific that incorporates expressions whose sentiment varies from one domain to another. Four algorithms including expanding limited hashtags into a larger and more complete set to collect tweets have been implemented. Experiments on the `iPhone 6' domain which obtains convincing results in all of the four phases, showing the superiority of the domain-specific TSA approach over a generic one.