Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may still be insufficiently helpful for users who are comparing multiple different choices. Without any contrastive information, the user may still struggle with the question, “Which one should I pick?” In this project, we aim to generate two distinctive opinion summaries and one common opinion summary from two entities which users can use to compare and contrast reviews of products. We developed a novel decoding algorithm, co-decoding. For the distinctive opinion summary generation, it emphasizes the distinctive words by contrasting the token probability distribution of the target entity against that of the counterpart entity. For the common opinion summary generation, it highlights the entity-pair specific words by aggregating token probability distributions.