EmotionLens: Interactive visual exploration of the circumplex emotion space in literary works via affective word clouds

Emotion (e.g., valence and arousal) is an important factor in literature (e.g., poetry and prose), and has rich values for plotting the life and knowledge of historical figures and appreciating the aesthetics of literary works. Currently, digital humanities and computational literature apply data statistics extensively in emotion analysis but lack visual analytics for efficient exploration. To fill the gap, we propose a user-centric approach that integrates advanced machine learning models and intuitive visualization for emotion analysis in literature. We make three main contributions. First, we consolidate a new emotion dataset of literary works in different periods, literary genres, and language contexts, augmented with fine-grained valence and arousal labels. Next, we design an interactive visual analytic system named EmotionLens, which allows users to perform multi-granularity (e.g., individual, group, society) and multi-faceted (e.g., distribution, chronology, correlation) analyses of literary emotions, supporting both exploratory and confirmatory approaches in digital humanities. Specifically, we introduce a novel affective word cloud with augmented word weight, position, and color, to facilitate literary text analysis from an emotional perspective. To validate the usability and effectiveness of EmotionLens, we provide two consecutive case studies, two user studies, and interviews with experts from different domains. Our results show that EmotionLens bridges literary text, emotion, and various other attributes, enables efficient knowledge discovery in massive data, and facilitates raising and validating domain-specific hypotheses in literature.