Incorporating Emotion and Personality-Based Analysis in User-Centered Modelling

摘要

Understanding complex user behaviour under various conditions, scenarios andjourneys can be fundamental to the improvement of the user-experience for agiven system. Predictive models of user reactions, responses -- and inparticular, emotions -- can aid in the design of more intuitive and usablesystems. Building on this theme, the preliminary research presented in thispaper correlates events and interactions in an online social network againstuser behaviour, focusing on personality traits. Emotional context and tone isanalysed and modelled based on varying types of sentiments that users expressin their language using the IBM Watson Developer Cloud tools. The datacollected in this study thus provides further evidence towards supporting thehypothesis that analysing and modelling emotions, sentiments and personalitytraits provides valuable insight into improving the user experience of complexsocial computer systems.