Chollakorn Nimpattanavong

Chollakorn Nimpattanavong

Auto-generated profile, based on publicly available information

Chollakorn Nimpattanavong

Ritsumeikan University, Japan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 December 2023
Verified
Conference Paper
Open access
CNChollakorn Nimpattanavong
Chollakorn Nimpattanavong
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
IKIbrahim Khan
Ibrahim Khan
TNThai Van Nguyen
Thai Van Nguyen
RTRuck Thawonmas
Ruck Thawonmas
KSKingkarn Sookhanaphibarn
Kingkarn Sookhanaphibarn
This paper presents a new approach for leveraging ChatGPT in fighting game commentary generation task. Commentary generation often relies on deep learning techniques, which typically demand extensive data to achieve effectiveness. Large language models (LLMs) have become essential due to their remarkable ability to process data efficiently, thanks to their extensive training on vast datasets. Our proposed approach integrates the use of LLMs, specifically the GPT-3.5 model, for generating commentaries through the utilization of various prompts with data from the open-source fighting game, DareFightingICE. Four prompt variants are employed to assess the effectiveness of each prompt components. Objective evaluation using natural language metrics reveals that different prompt components significantly affect the generated commentaries. Additionally, subjective evaluation through a questionnaire reveals that prompts without parameter definitions received the highest preference from human evaluators. These results suggest that LLMs exhibit versatility in generating fighting game commentaries and hold promise for broader applications.

6 December 2023
Verified
Conference Paper
Open access
JTJun Tanabe
Jun Tanabe
IKIbrahim Khan
Ibrahim Khan
TNThai Van Nguyen
Thai Van Nguyen
CNChollakorn Nimpattanavong
Chollakorn Nimpattanavong
RTRuck Thawonmas
Ruck Thawonmas
This paper presents a system that adapts the background music of a fighting game according to the player’s arousal. The system uses a model to estimate the player’s arousal based on events in the game and accordingly changes the pitch, tempo, and volume of the music. The system does not use AI music generation or arrangement but modifies existing music in real time. We experiment to evaluate the impact of different arousal durations on the player’s immersion and music preference. The results show that a duration of 10 seconds is the most suitable for fighting games, as it increases the immersion and matches the music with the game situation.