From the perspective of contrastive linguistics, this article analyses the frequency and nature of the SVO sentence structure in English and Portuguese, particularly in those cases where the subject is realised by the first person pronoun I and eu respectively or by a name.
Abstract. In this paper we propose a set of stylistic markers for automatically attributing authorship to micro-blogging messages. The proposed markers include highly personal and idiosyncratic editing options, such as 'emoticons', interjections, punctuation, abbreviations and other low-level features. We evaluate the ability of these features to help discriminate the authorship of Twitter messages among three authors. For that purpose, we train SVM classifiers to learn stylometric models for each author based on different combinations of the groups of stylistic features that we propose. Results show a relatively good-performance in attributing authorship of micro-blogging messages (F = 0.63) using this set of features, even when training the classifiers with as few as 60 examples from each author (F = 0.54). Additionally, we conclude that emoticons are the most discriminating features in these groups.
Emotion and the emotions we study today have been discussed for centuries using words and phrases that reflect the thoughts of those times, but that have also become fossilised in modern Western thought. The concepts behind these expressions vary in content according to the context in which they are used, and their translations into other languages show that their usage, or that of their cognates, in each language allows for further different interpretations of the concepts, often influenced by the culture and society in which they are used. The studies of Emotion and Language are influenced by perspectives from the disciplines of philosophy, anthropology, psychology, sociology, neuroscience, and computer science, and cover not just the spoken or written form of the core concepts of emotion, but also descriptions of the expression of emotion through facial expression, body language, and physical reactions, and even subjective language in general. This article will attempt to provide a view of some of the issues that affect the understanding of the language of emotion, and that underlie many of the problems faced by those working in opinion mining, sentiment analysis, and human<>computer interaction. It will also touch on the complex relationship between emotion and cognition, and the problems this poses. The objective is to offer some interdisciplinary background for our second article, which presents a more detailed perspective from a computational point of view.
In this paper, the second in the pair, we discuss how psychologists, linguists, and computer scientists model emotion from a computational perspective. First, we draw some parallels between the formalization of the emotions in the human body and the development of computational systems. Then we look at three influential schools for formalizing emotion in language, and we use a specific example to show that they do not have the same concerns and expressive power. We give some examples of computational resources for emotions, insisting on why the variety of languages and cultures makes it impossible to apply a monolithic universal approach. We then turn to emotion and opinion and briefly overview opinion mining and emotion generation. Instead of describing techniques and technologies and providing quantitative results, we try to present a “big picture” of emotion processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.