Construction of Text-dialog Corpus with Emotion Tags Focusing on Facial Expression in Comics

Tokuhisa, Masato; Murakami, Jin'ichi; Ikehara, Satoru

doi:10.5715/jnlp.14.3_193

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tokuhisa et al [23] statistically analyzed the valency pattern of each sentence pattern, and proposed a method for emotion inference. Tokuhisa et al [24] constructed and evaluated the dialog corpus by annotating emotion tags focusing on facial expressions of characters from manga comics.…”

Section: English Case Pattern Predicatementioning

confidence: 99%

Utterance Emotion Estimation by Using Feature of Syntactic Pattern

Matsumoto¹

2021

Information Systems - Intelligent Information Processing Systems, Natural Language Processing, Affective Computing and Artifici

View full text Add to dashboard Cite

Emotion has been defined as basic emotions by various researchers, however, there are not many studies describing the relation between emotion and language patterns in detail based on statistical information. There are various languages all over the world, and even a language of the same country has different writing styles/expressions depending on which language media is used or who is a writer/speaker, which is thought to make it difficult to analyze the relation of emotion and language patterns. The author has been engaged in constructing and analyzing emotion corpora in some domains based on different sources. From the analysis results, emotion expressions started to become more understood that they have differences and tendencies according to the attributes of the writers and the speakers. In this chapter, I focused on the differences detected in the attributes of the writer/speaker with respect to language patterns; in usage tendencies or combinations of words, unknown expressions (slangs), sentence patterns, non-verbal expressions (emoji, emoticon, etc.) with relevant emotions, then introduce the outcome of the analytical survey on a large scale corpus obtained from a social networking service.

show abstract

Section: English Case Pattern Predicatementioning

confidence: 99%

Utterance Emotion Estimation by Using Feature of Syntactic Pattern

Matsumoto¹

2021

Information Systems - Intelligent Information Processing Systems, Natural Language Processing, Affective Computing and Artifici

View full text Add to dashboard Cite

show abstract

“…Some typical knowledge base techniques are based on the vector space method [4,5], thesauruses [6,7], ontology [8], the concept base [9], the corpus [10], and so on. Applied systems proposed so far include an ontology-based semantic retrieval system for classical texts [11] and an emotion judgment system using a concept base [12].…”

Section: Previous Studiesmentioning

confidence: 99%

Construction of an “Analects of Confucius” knowledge base including pragmatics information

Tsuchiya

Ren³

2011

Elect Comm in Japan

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose an approach to constructing a knowledge base for the Analects of Confucius, which aims to promote a correct understanding of this text. The content of the Analects has not been categorized by topic and it always contains broader meanings. Thus, it is necessary to create a framework that can be used to manage and build the knowledge base for the text. The construction of knowledge bases in the past has focused on the investigation of words and of surface meanings and explicitly communicated meanings of passages, but these cannot be used for study of deeper meanings or implicitly communicated meanings. The present paper sets up a categorization system for the Analects, which is used to create a knowledge base by using pragmatics information, based on the utterance interpretation method in pragmatics. A question answering system that makes use of the knowledge base on the Analects was used for assessment of the approach. The results showed that answers based on a combination of pragmatics information and modern text interpretation outperformed by 32.2% answers extracted only from the modern text.

show abstract