Joint user-interest and social-influence emotion prediction for individuals

Emotions are playing significant roles in daily life, making emotion prediction important. Since emotions are highly subjective for users, we focus on emotion prediction for individuals instead of for the masses. Existing works on emotion prediction for individuals either focus on media content or social-influence alone, which are incomprehensive in predicting users' emotions. In this paper, we design a joint user-interest and social-influence emotion prediction framework for individuals, in which user-interest in multimodal media content and social-influence in social relations are both considered. To address the issue that for different users, the impacts of these two factors are different, a probabilistic graphical model is proposed to combine these two factors together, where a set of parameters are used to measure their importance in influencing the user's emotions, and they are learnt from the user's historical behaviors. We conduct experiments using real social media network to verify our algorithm and evaluate its performance. The results demonstrate the effectiveness of our approach and show that our approach can substantially improve the emotion prediction performance.