Ryuho Sekikawa | Search arXiv

arXiv2026

Supporting Perspective Acquisition and Opinion Formation on Societal Issues Through AI-Generated Japanese Rap Battle Debates

Acquiring diverse perspectives and forming informed opinions on societal issues are essential for critical thinking and informed decision-making. Although observing debates between opposing viewpoints can promote perspective acquisition, conventional debates require substantial time and human resources, limiting their accessibility. This study investigates whether brief AI-generated rap battle-style debates can support perspective acquisition and opinion formation on societal issues. Rap battles are debate-style performances in which opposing viewpoints are expressed through rhymed verses, making them engaging while preserving the structure of argumentative dialogue. To conduct this investigation, we automatically generated rap battle-style debates using GPT-5.4-mini and presented them to participants with synthesized audio through a web-based viewing interface. We evaluated the educational effectiveness of this approach through a user study involving six participants who viewed 40 debates generated from topics on societal issues used in the All Japan Junior and Senior High School Debate Championships. The results showed that watching approximately 1.5 minute rap battle-style debates nearly doubled the number of opinions and discussion points identified by participants. Furthermore, participants reconsidered or changed their stances in 52.5% of the evaluated cases. These findings demonstrate that even brief AI-generated rap battle-style debates can effectively support perspective acquisition and opinion formation on societal issues.

cs.MM↗

arXiv2025

Structural Changes and Percolation Transition in Networks after Aging Processes

In social networking services, users constantly change, and the network structure changes simultaneously. As the network structure changes, so does the word-of-mouth within it. To study how information transfer on the network changes with the aging of the network, we investigated the relation of the structure and the percolation in the aged networks. We first prepared the Bianconi-Barabási model as the initial network and observed the time evolution of its properties by repeatedly deleting and adding nodes. We introduced two tunable parameters, the deleting parameter $α$ and the adding parameter $β$, and observed the aging behavior for the various parameter sets. We found that the network did not reach its steady state depending on the parameters. We also found that when the network is stable, there is a parameter region where the degree distribution changes from power-law to exponential decay. We performed the percolation analyses and found that the behavior of the percolation probability changes simultaneously with changes in the network's structure. This study is expected to help control network structure in steady-state aged networks.

physics.soc-ph↗