The success of Web 2.0 applications has made on line social media websites tremendous assets for supporting critical business intelligence applications. The knowledge gained from social media can potentially lead to the development of novel services that are better tailored to users’ needs and at the same time meet the objectives of businesses offering them. Online consumer reviews are one of the critical social media contents. Proper analysis of consumer reviews not only provides valuable information to facilitate the purchase decisions of customers but also helps merchants or product manufacturers better understand general responses of customers on their products for marketing campaign improvement. This study aims at d esigning an approach for supporting the effective analysis of the huge volume of online consumer reviews and, at the same time, settling the major limitations of existing approaches. Specifically, the proposed rule-based sentiment analysis (R-SA) technique employs the class association rule mining algorithm to automatically discover interesting and effective rules capable of extracting product features or opinion sentences for a specific product feature interested. According to our preliminary evaluation results, the R-SA technique performs well in comparison with its benchmark technique.