Generating appropriate emotions for responses is essential for dialog systems to provide human-like interaction in various application scenarios. Most previous dialog systems tried to achieve this goal by learning empathetic manners from anonymous conversational data. However, emotional responses generated by those methods may be inconsistent, which will decrease user engagement and service quality. Psychological findings suggest that the emotional expressions of humans are rooted in personality traits. Therefore, we propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system and further investigate a solution through the personality-affected mood transition. Specifically, we first construct a daily dialog dataset, Personality EmotionLines Dataset (PELD), with emotion and personality annotations. Subsequently, we analyze the challenges in this task, i.e., (1) heterogeneously integrating personality and emotional factors and (2) extracting multi-granularity emotional information in the dialog context. Finally, we propose to model the personality as the transition weight by simulating the mood transition process in the dialog system and solve the challenges above. We conduct extensive experiments on PELD for evaluation. Results suggest that by adopting our method, the emotion generation performance is improved by 13% in macro-F1 and 5% in weighted-F1 from the BERT-base model.

生成适当的情感响应对于对话系统在各种应用场景中提供类人交互至关重要。大多数以前的对话系统试图通过从匿名对话数据中学习同理心方式来实现这一目标。然而，这些方法产生的情绪反应可能不一致，这将降低用户参与度和服务质量。心理学研究结果表明，人类的情绪表达植根于人格特质。因此，我们提出了一个新任务，即受人格影响的情绪生成，根据赋予对话系统的人格生成情绪，并通过受人格影响的情绪转换进一步研究解决方案。具体来说，我们首先构建一个日常对话数据集，即个性情感线数据集（PELD），其中包含情感和个性注释。随后，我们分析了该任务中的挑战，即（1）异构地整合个性和情感因素；（2）在对话上下文中提取多粒度的情感信息。最后，我们建议通过模拟对话系统中的情绪转换过程来将个性建模为转换权重，并解决上述挑战。我们对 PELD 进行了广泛的实验以进行评估。结果表明，通过采用我们的方法，在基于 BERT 的模型中，宏观 F1 的情绪生成性能提高了13% ，加权 F1 的情绪生成性能提高了 5% 。