The intelligent chatbot takes dialogue sentiment prediction as the core, and it has to tackle long dialogue sentiment prediction problems in many real-world applications. Current state-of-the-art methods usually employ attention-based dialogue sentiment prediction models. However, as the conversation progresses, more topics are involved and the changes in sentiments become more frequent, which leads to a sharp decline in the accuracy and efficiency of the current methods. Therefore, we propose a Multi-round Long Dialogue Sentiment Prediction based on Multidimensional Attention (MLDSP-MA), which can focus on different topics. In particular, MLSDP-MA leverages a sliding window to capture different topics and traverses all historical dialogues. In each sliding window, the contextual dependency, sentiment persistence, and sentiment infectivity are characterized, and local attention cross fusion is performed. To learn dialogue sentiment globally, global attention is proposed to iteratively learn comprehensive sentiments from historical dialogues, and finally integrate with local attention. We conducted extensive experimental research on publicly available dialogue datasets. The experimental results show that, compared to the current state-of-the-art methods, our model improves by 3.5% in accuracy and 5.7% in Micro-F1 score.