Design of multilingual participatory gaming simulations with a communication support agent

Abstract

People communicating through machine translators cannot tell what the purpose of their communication is or what other people are thinking because of the poor quality of translation services. If they are able to share their understanding within a "common ground" like a communicative or behavioral protocol, they can overcome their difficulties in communication, and we can improve information systems to help them improve mutual understanding. We designed a multilingual participatory gaming simulation, and conducted multilingual gaming experiments with Japanese and Korean participants. We extracted the protocol for conversation with mistranslations from the game logs and designed an agent to support conversation. Then, Japanese and Chinese played it and we observed and analyzed the behaviors of agents and the interaction between players and agents. Consequently, we obtained two main sets of results: (1) an agent function that notified players of the time that had elapsed since the conversation had broken down effectively speeded up their negotiations and achieved more active communications. (2) Tagging by participants was difficult and ineffective in leading to specific protocols and conversations when mistranslations occurred.

Multilingual Case Method System for Cross-Cultural Analysis

“…In the analysis of the chat discussion logs, we divided chat discussion logs into two threads, 'source' and 'translated' [11]. 'Source thread' means original statement, e.g., Japanese statement is described as source thread and Korean statement is translated into Japanese.…”

Analysis of self-tagging during conversational chat in multilingual gaming simulation

“…Also, this game logs the conversation data with these conversation tags, which enables context protocols to be extracted. However, we need to manage the participants motivation to encourage them to do conversational tagging because manual tagging done by participants does not motivate participants to assign conversation tags very much [2], [4].…”

“…A gaming simulation is often used for conversational analysis [2]. This enables us to develop a concrete support system, such as by implementing an agent through analysis of the interaction between humans or artifacts.…”

“…This enables us to develop a concrete support system, such as by implementing an agent through analysis of the interaction between humans or artifacts. Tsunoda [2], [4] determined participant behaviors and developed a communication model. He designed a supporting agent to prevent communication breakdown that may occur in CMC in a multilingual gaming simulation after he revealed their existence.…”

“…Manual tagging by analyst is very accurate but has large cost about time to assign tags [5]. Manual tagging by participants is also accurate, but it is difficult for participants to get motivated to assign tags [2], [4]. Automatic tagging is very fast, but it is not accurate [14].…”