Multilingual Semantic Networks for Kansei Study

Abstract

Words are communication media to share a concept in a community. A word involving ambiguity represents multiple concepts depending on contexts. Such ambiguity causes misunderstanding between people having different contexts. On the other hands, a community uses words to obtain responses from target population, such as customers and participants. The word ambiguity causes misunderstanding between a community and a target population due to different contexts. A community dealing with multiple languages (e.g. multinationals) has a difficulty in translation if there are no words in a second language, all meanings of which do not correspond to all meanings of a word one wishes to translate. To deal with word ambiguity, I proposed a multilingual semantic networks (MLSN) framework. The MLSN is a graph where multiple language words, as nodes, are semantically linked through concepts. I implemented WordNet of English, Japanese, and French into a graph database as a MLSN. I applied MLSN to following two analysis. In the first analysis, I investigated the meanings of ambiguous words such as “kansei”, and their semantic relations with relevant words in the three languages. I found that there are no words corresponding to all meanings of those words in second languages. In the second analysis, I discussed how MLSN supports to select and translate a set of words used as evaluation descriptors. I analyzed ten positive emotion words from Geneva Emotion Wheel and their translation. I demonstrated how MLSN automatically finds translation mismatches and semantic independence between emotion descriptors.