Classification and Pattern Discovery of Mood in

Abstract. Automatic data-driven analysis of mood from text is an emerging problem with many potential applications. Unlike generic text categorization, mood classification based on textual features is compli-cated by various factors, including its context- and user-sensitive nature. We present a comprehensive study of different feature selection schemes in machine learning for the problem of mood classification in weblogs. Notably, we introduce the novel use of a feature set based on the affective norms for English words (ANEW) lexicon studied in psychology. This fea-ture set has the advantage of being computationally efficient while main-taining accuracy comparable to other state-of-the-art feature sets exper-imented with. In addition, we present results of data-driven clustering on a dataset of over 17 million blog posts with mood groundtruth. Our analysis reveals an interesting, and readily interpreted, structure to the linguistic expression of emotion, one that comprises valuable empirical evidence in support of existing psychological models of emotion, and in particular the dipoles pleasure–displeasure and activation–deactivation.