Customers' conversations on social media could shed light into their experience, opinions, feelings, and concerns. To gain valuable knowledge about customers, it becomes increasingly important for businesses to collect, monitor, analyze, summarize, and visualize user-generated data on social media. However, analyzing social media data is challenging due to the vast increase of social media data. In this paper, we present a workflow approach of using established natural language preprocessing, text mining and sentiment analysis techniques to analyze social media data. Then we conducted two experiments to verify the effectiveness of our workflow approach by mining online movie reviews. The results show that our workflow approach is effective in analyzing social media data.