The identity resolution across social platforms is an important research aspect， which integrates the user’s information from various platforms. Most of the existing user identity resolution work is aimed at social platforms with similar types. The information between platforms is relatively symmetrical. Whether the user is the same user is determined by the similarity of user’s profile attributes， spatial location， network relations and other information on different platforms. However， in the two heterogeneous social platforms， the user information is asymmetric so that we cannot get the corresponding attribute information for user identity resolution. This paper discusses the method of user identity resolution across comment and activity platforms. To solve the problem of user information attribute asymmetry of across social platforms， the user information is organized according to three types of information： profile attribute， semantic sequence and feature word sequence. The corresponding information is extracted from their respective social platforms to establish mapping relationships， and an integrated matching algorithm integrating the three types of information is proposed. Considering the time offset phenomenon of user activities， the back propagation learning method is used to obtain the time offset weights， and a similarity measurement method between semantic sequence and feature word sequence based on back propagation learning is proposed. At the same time， an overall similarity is designed for user identity. Experimental results on real dataset show that the proposed method is effective on user identity resolution.