CAO: A Fully Automatic Emoticon Analysis System

Abstract

This paper presents CAO, a system for affect analysis of emoticons. Emoticons are strings of symbols widely used in text-based online communication to convey emotions. It extracts emoticons from input and determines specific emotions they express. Firstly, by matching the extracted emoticons to a raw emoticon database, containing over ten thousand emoticon samples extracted from the Web and annotated automatically. The emoticons for which emotion types could not be determined using only this database, are automatically divided into semantic areas representing "mouths" or "eyes," based on the theory of kinesics. The areas are automatically annotated according to their co-occurrence in the database. The annotation is firstly based on the eye-mouth-eye triplet, and if no such triplet is found, all semantic areas are estimated separately. This provides the system coverage exceeding 3 million possibilities. The evaluation, performed on both training and test sets, confirmed the system's capability to sufficiently detect and extract any emoticon, analyze its semantic structure and estimate the potential emotion types expressed. The system achieved nearly ideal scores, outperforming existing emoticon analysis systems.

Towards Computational Fronesis

“…An example of negative-activated emotion could be "anger"; a positive-deactivated emotion is, e.g., "relief". The mapping of Nakamura's emotion types on Russell's two dimensions proposed by was proved reliable in several research (Ptaszynski, Dybala, Shi, Rzepka, & Araki, 2009b;Ptaszynski, Maciejewski, Dybala, Rzepka, & Araki, 2010). The mapping is represented in Figure 1.…”

“…Firstly, we focused on evaluation of the affect analysis procedure. Although the two affect analysis systems were evaluated separately previously (Ptaszynski, Dybala, Shi, Rzepka, & Araki, 2009a;Ptaszynski, Maciejewski, Dybala, Rzepka, & Araki, 2010), there was no overall evaluation. This corresponds to items A) and B) investigated in the questionnaire.…”

“…This provides hints about potential groups of expressed emotions giving the system coverage of over 3 million possibilities. The performance of CAO was evaluated as close to 98% (Ptaszynski, Maciejewski, Dybala, Rzepka, & Araki, 2010) which proved CAO as a reliable tool for the analysis of Japanese emoticons. In the annotation process CAO was used as a supporting procedure in ML-Ask to improve the performance of the affect annotation system and add detailed information about emoticons appearing in the text.…”