Most of existing cross-domain sentiment classification methods are not expressive enough to capture rich representation of texts, and class noise accumulated during transfer process would lead to negative transfer which could adversely affect performance. To address these issues, the authors propose a method combining textual representation learning and transfer learning algorithm for cross-domain sentiment classification. This method first builds a hierarchical attention network to generate document representations with local semantic information. Afterwards, the authors utilize the class-noise estimation algorithm to detect the negative transfer samples in transferred samples and remove them. Finally, the sentiment classifier is trained on the expanded dataset from samples in target domain and transferred ones in source domain. Compared with the baselines, two experiments on large-scale product review datasets show that the proposed method is able to effectively reduce RMSE of crossdomain sentiment classification by 1.5% and 1.0% respectively.