Figure 5 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Source publication
Emotion classification is often formulated as the task to categorize texts into a predefined set of emotion classes. So far, this task has been the recognition of the emotion of writers and readers, as well as that of entities mentioned in the text. We argue that a classification setup for emotion analysis should be performed in an integrated manne...
Contexts in source publication
Context 1
... to emotions, we are interested in the relation between appraisals across different entities: if one perceives, for instance, self responsibility for an event, what is the appraisal of the other experiencer? Results are in Figure 5. For each (writerother entity) pair in a text, we retrieve the scores of all appraisal pairs, where one element is the (averaged, see Section 4.3.) ...
Context 2
... assigned to the writer and the other is given to the mentioned entity. Hence, we calculate Spearman's correlation for such appraisal combinations corresponding to the cells of Figure 5. Appraisals holding for the writers are positively correlated with the same dimensions for other entities (see diagonal). ...
Similar publications
This article focuses on the question answering type of automatic scoring system for large-scale spoken English examinations and scores using a method called multifeature fusion. Three types of features are extracted to score using speech recognition text as the research object. The three types of features are similarity, syntactic, and phonetic. Th...
