Chollakorn Nimpattanavong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chollakorn Nimpattanavong has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ibrahim Khan
Ritsumeikan University, Japan
2 shared publications - Ruck Thawonmas
Ritsumeikan University
2 shared publications - Thai Van Nguyen
Ritsumeikan University, Japan
2 shared publications - Jun Tanabe
Ritsumeikan University, Japan
1 shared publication - Kingkarn Sookhanaphibarn
Center of Specialty Innovation, Bangkok University, Pathum Thani 12120, Thailand
1 shared publication - Pittawat Taveekitworachai
Ritsumeikan University
1 shared publication
Latest Publications
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Adaptive Background Music According to the Player’s Arousal for DareFightingICE
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.
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessAdaptive Background Music According to the Player’s Arousal for DareFightingICE
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.
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Am I Fighting Well? Fighting Game Commentary Generation With ChatGPT
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
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessAm I Fighting Well? Fighting Game Commentary Generation With ChatGPT
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.