Abstract: The interests and emotions of users are often varied in their real lives. On the contrary, some other features (such as the profiles) of micro-blog are always unchangeable and they cannot describe the users’ characteristics very well. Then a novel friend recommendation method merged users’ text semantics with emotions was proposed. In the model, in order to compute the similarity of friends, some text content features from users’ micro-blog are extracted and time factor was introduced. Then further consideration on the users' emotional characteristics was taken to compute the users’ similarity through analyzing the emotional words in micro-blog text. Then the final results were gotten. The results of the experiments show that the model can effectively enhance the accuracy and rationality of friend recommendation by adding text semantics and emotions analysis.

Key words: micro-blog, text semantic, emotional analysis, similarity, friend recommendation