Does exposure to like-minded/non-like-minded information lead to the use of political incivility? Few studies have investigated this question, and the results have been mixed. There are two conflicting possibilities: (i) if individuals are frequently exposed to like-minded political information, they reinforce their pre-existing beliefs and are, thus, more likely to use uncivil language, and (ii) if individuals are frequently exposed to non-like-minded information, they often feel negative emotions and are, therefore, more likely to use incivility. To evaluate these two competing hypotheses, I analyze Japanese Twitter data using a semi-supervised learning method. The results show that individuals who are exposed to non-like-minded information are more likely to use political incivility.