Optimizing App Review Classification with Large Language Models: A Comparative Study of Prompting Techniques

Keyphrases

• Large Language Models 100%
• App Review Classification 100%
• Small Animal Model 66%
• Model Size 66%
• App Reviews 66%
• Few-Shot Prompting 66%
• Classification Performance 33%
• Classification Model 33%
• Return on Investment 33%
• Competitive Results 33%
• Model Performance 33%
• Small Media 33%
• Zero-shot 33%
• Diminishing Returns 33%
• Mistral 33%
• Problem Reports 33%
• Prompt Design 33%

Arts and Humanities

• Review 100%
• Limitations 33%
• Mistral 33%

Computer Science

• Large Language Model 100%
• Return on Investment 33%
• Classification Performance 33%