![]() | Only 14 pages are availabe for public view |
Abstract The field of Affective Computing (AC) expects to narrow the communicative gap between the highly emotional human and the emotionally challenged computer by developing computational systems that recognize and respond to the affective states of the user. Researchers have recognized the significance of affect with respect to Human-Computer Interaction (HCI), and the affective states of users can be recognized using intelligent User Interface (UI). In order to support individuals in their writing or reading activities, or groups communicating, researchers have tried to develop techniques for sensing users’ affective states. Affect-sensitive interfaces are being developed in number of domains, including gaming, mental health, and learning technologies. Emotions are part of human life. The recognition of emotion has been implemented in many kinds of media. This can be through speech, image, facial expressions, and textual data. The textual data is very popular medium, consisting of books, newspapers, and letters. Studying the relationship between natural language and affective information, and dealing with its computational treatment is becoming an important field. It is possible for people to exchange ideas, opinions, and emotions using texts through network transmissions. Recently, interest has been growing among researchers to fmd ways of detecting subjective information used in blogs and other online social media. This research addresses the task of determining emotions expressed in Arabic text at the sentence level. Based on this corpus, a moderate sized Arabic emotion lexicon for the six basic emotions is constructed based on the annotated Arabic children stories for the predefmed emotion categories. The primary consideration in the selection of data for my research was that the data should be rich in emotion expressions. |