The latent knowledge in the emotions and the opinions of the individuals that are manifested via social networks are crucial to numerous applications including social management, dynamical processes, and public security. Accordingly, affective computing as an interdisciplinary research field, linking the domains from artificial intelligence to cognitive inference, is capable to exploit emotion-oriented knowledge from brief contents. The textual contents convey hidden information such as personality and cognition about corresponding authors that can determine the correlations and variations between users. Emotion recognition from brief contents should embrace the differences between authors where the differences in personality and cognition can be traced within emotional expressions. To tackle this challenge, we devise an effective framework that, on the one hand, infers latent individual aspects, the personality factors, from brief contents and, on the other hand, presents a novel ensemble classifier equipped with dynamic dropout convnets that extract emotions from textual context. To categorize short text contents, our proposed method conjointly leverages cognitive factors and exploits hidden information. Furthermore, we develop a novel embedding model that utilizes the outcome vectors to foster emotion-pertinent features that are collectively assembled by lexicon inductions. Experimental results show that compared to other competitors, our proposed model can achieve a higher performance in recognizing emotion from noisy contents.

• Index Terms—Affective Computing, Cognitive Factors, Personality, Emotion recognition, Ensemble learning

We compute the propriety of individuals to fulfill a job aooprtunity by using the cognitive factors...The article is under review