Ryota Higuchi, Ryosuke Yamanishi, Mitsunori Matsushita: Analyzing Textual Sources Attributes of Comics Based on Word Frequency and Meaning, The 5th International Workshop on coMics ANalysis, Processing and Understanding, 2022年8月

The purpose of this research is to analyze the textual source attributes of explanations and review sentences about comics. Comics are difficult to process in terms of the intended story because they are primarily composed of pictures and text. One of the processing methods is to analyze comics text on the Web, particularly the description of characters and review sentences including the reader’s impression about the comic. Sources of textual information, such as explanations or reviews, are selected according to the application of the study. However, differences among textual sources regarding comics are not taken into consideration in the analysis. This paper classifies words appearing frequently in the text semantically, with results showing that explanations include words that express the story, for example, the family structure, physical information, and sex of the characters for describing the characters. Conversely, the review frequently uses words that provide meta-information about comics, such as illustrations and style. The proposed method revealed that explanations of comics are more useful as textual sources for analyzing story information than reviews.