More and more studies begin to focus on emotional conversation generation. However, the existing studies tend to focus only on emotional factors and ignore the relevance and diversity of topics in dialogues, as well as the emotional tendency closely related to topics, which may lead to the quality decline of generated responses. Therefore, a topic-expanded emotional conversation generation model that integrated topic information and emotional factors was proposed. Firstly, the conversation context was globally-encoded, the topic model was introduced to obtain the global topic words, and the external affective dictionary was used to obtain the global affective words in this model. Secondly, the topic words were expanded by semantic similarity and the topic-related affective words were extracted by dependency syntax analysis in the fusion module. Finally, the context, topic words and affective words were input into a decoder based on the attention mechanism to prompt the decoder to generate topic-related emotional responses. Experimental results show that the model can generate rich and emotion-related responses. Compared with the model Topic-Enhanced Emotional Conversation Generation(TE-ECG), the proposed model has an average increase of 16.3% and 15.4% in unigram diversity(distinct-1) and bigram diversity(distinct-2); and compared with Seq2SeqA(Sequence to Sequence model with Attention), the proposed model has an average increase of 26.7% and 28.7% in unigram diversity(distinct-1) and bigram diversity(distinct-2).

Aiming at the problems of data sparseness and cold start in social network recommendation systems, a hybrid social network recommendation algorithm based on feature Transform and Probabilistic Matrix Factorization (TPMF) was proposed. Using Probability Matrix Factorization (PMF) method as recommendation framework, trust network, the relationship between the recommended items, user-item score matrix and adaptive weight were combined to balance the impact of individual and social potential characteristics on users. The trust feature transfer was introduced into the recommendation system as valid basis for recommendation. Compared to the User-Based Collaborative Filtering (UBCF), TidalTrust, PMF and SoRec, the experimental results show that the Mean Absolute Error (MAE) of TPMF was decreased by 4.1% to 20.8%, and the Root Mean Square Error (RMSE) of TPMF was decreased by 3.3% to 18.5%. Compared with the above four algorithms, for the cold start problem, the Mean Absolute Error was decreased by 1.6 to 14.7%, and the RMSE was decreased by 1.2% to 9.7%, which verifies TPMF effectively alleviates cold start problem and improves the robustness of the algorithm.