Abstract
BACKGROUND: In the healthcare service industry, patient complaints serve not only as a critical metric for assessing hospital service quality but also as a fundamental driver of high-quality hospital development. Through a systematic analysis of patients' perceptions, opinions, and emotional responses to hospital management within the complaint-handling process. METHODS: Therefore, this paper aims to develop a hospital complaint-handling analysis model to enhance public satisfaction with greater precision. First, complaint data from hospitals spanning January to December 2022-2024 was preprocessed using data cleaning, mechanical compression, word segmentation, and stop-word filtering techniques. Second, the DISC behavioral language model was employed to analyze key indicators, including hospital compensation frequency, total compensation amounts, patient appeal rates, complainants' satisfaction with the resolution process, and their overall satisfaction with complaint outcomes. Finally, a sentiment analysis model and an improved KANN-DBSCAN clustering model were applied to complaint data to precisely identify sentiment-related keywords and assess the intensity of negative emotions, providing hospitals with targeted improvement recommendations. RESULTS: This study applied the DISC behavioral model to medical complaints. DISC-based text analysis enabled tailored responses. Among 334 intervention and 341 control cases, satisfaction 93.39%, was higher in the intervention group 83.24%, indicating improved complaint resolution through behavior-informed communication strategies. CONCLUSIONS: By analyzing patients' psychological needs and expectations, this study aims to minimize financial compensation and reduce patient appeals while enhancing overall complaint resolution satisfaction, which provides medical institutions with a more comprehensive, effective, and personalized complaint-handling strategy while simultaneously improving patients' healthcare experiences.