The benefits of social learning have been recognized by existing research. To explore knowledge distribution in social learning and its effects on learning achievement, we developed a social learning platform and explored students' behaviors of peer interactions by the proposed algorithms based on social network analysis. An empirical study was also conducted on a college course to investigate the correlation between peer interaction and learning achievement. The experiment results show that the students who tended to actively contribute knowledge to peers on the social learning platform had better learning achievements than the students who were used to the passive reception of knowledge. Besides, the knowledge transmitters and intermediaries performed better in learning achievement as well, and the knowledge contributors had closer interactions with their peers. The implications derived from the findings can inspire instructors/researchers to facilitate effective social learning, and provide suggestions to develop effective algorithms to analyze social interaction behaviors.