MACVTL: Improving Efficiency of Mood Analysis from Text & Facial Cues Using Cross Validation and Transfer Learning.

Accurate analysis of a person’s mood can assist medical psychiatry personnel to assist and improve personal well-being. In order to determine a person’s mood a wide variety of inputs can be used, these inputs include but are not limited to, the person’s social media patterns, facial patterns, ecommerce buying patterns, etc. Analysis of these patterns individually can assist in development of a moderate accuracy psycho-analysis system. Thus, to improve the accuracy and efficiency of mood analysis, this text proposes a deep learning model based on transfer learning, that combines training information from social media activity, and visual actions in order to analyze the person’s state-of-mind. The proposed model is compared with individual algorithms that detect person’s mood, and an accuracy improvement of 12% was achieved. The model is also compared with similar hybrid algorithms that combine multiple psychiatric ques, and it is observed that the proposed model is 8% more effective than these systems due to incorporation of cross validation and transfer learning. [ABSTRACT FROM AUTHOR]