In this paper, we present multiple approaches to improve sentiment analysis on Twitter data. We first establish a state-of-the-art baseline with a rich feature set. Then we build a topic-based sentiment mixture model with topic-specific data in a semi-supervised training framework. The topic information is generated through topic modeling based on an efficient implementation of Latent Dirichlet Allocation (LDA). The proposed sentiment model outperforms the top system in the task of Sentiment Analysis in Twitter in SemEval-2013 in terms of averaged F scores. © 2014 Association for Computational Linguistics.