Dental Service Strategy of Hospitals in Indonesia Based on Big Data Analysis ofSocial Media Users X
- 1Master of Hospital Administration, Megarezky University, Makassar, Indonesia
- 2Department of Statistics, Nnamdi Azikiwe University, Awka, Nigeria
- 3Social Science Education Program, UIN Sayyid Ali Rahmatullah, Tulungagung, Indonesia
Abstract
This study analyzes public perception of hospital dental polyclinic services in Indonesia through big data sentiment analysis of 3,075 tweets from the X platform (January–November 2024), using keywords like “dental hospitals” and “dental poly hospitals.” Employing a descriptive design, data was crawled via Google Colab, followed by preprocessing steps: duplicate removal, non-essential character cleanup, normalization, tokenization, stopword elimination, and stemming. The Naïve Bayes Classifier algorithm classified sentiments, revealing 61.54% negative sentiment (1,571 tweets) and 38.46% positive sentiment (982 tweets), with 73% model accuracy, 0.73 negative precision, and 0.90 negative recall. Negative sentiments highlighted issues, such as long waiting times, inadequate facilities, and BPJS-related administra- tive delays, while positive sentiments praised professional staff and comprehensive facilities. Field data from tweet analysis showed frequent complaints about procedural discomfort (e.g., “pain,” “pluck”) and appreciation for competent doctors. SWOT analysis, triangulated with multi-stakeholder assessments (hospital administrators, directors, dentists), yielded an IFAS score of 7.04 and an EFAS score of 6.84, indicating strong internal capabilities but operational inefficiencies. Strategic recommendations include optimizing workflows, standardizing services, and leveraging public awareness to enhance specialized dental care, addressing public dissatisfaction for sustainable service improvement.
Related
- Periodontitis and Associated Factors Among Dental Outpatients at Tertiary Hospitals in Dhaka
- Pretreatment Attrition, Treatment Delay and Treatment Outcome in Drug-Resistant Tuberculosis: A Mixed-Methods Cohort Study in Public and Private Hospitals in Indonesia
- Status quo of change fatigue and influencing factors among nursing assistants in 21 general hospitals in Guangdong province under the "accompaniment⁃free care service" model
- The moderating role of online literacy and trust in shaping patient satisfaction through e-service quality in private hospitals
- Impact of the COVID-19 pandemic on dental care utilization in Indonesia: a critical analysis with policy implications
BibTeX
@article{istiqlaliyah2026dental,
title = {{Dental Service Strategy of Hospitals in Indonesia Based on Big Data Analysis ofSocial Media Users X}},
author = {Alfiatuz Zahro Al Istiqlaliyah and Muhammad Basir and Abd. Malik Iskandar and Muhammad Idris Paratai and Hairuddin K. and Saparuddin Latu and Chrisogonus K. Onyekwere and Yudi Krisno Wicaksono},
journal = {KEMAS: Jurnal Kesehatan Masyarakat},
year = {2026},
month = jul,
doi = {10.15294/kemas.v21i4.32631},
url = {https://doi.org/10.15294/kemas.v21i4.32631},
note = {CC BY},
}
RIS
TY - JOUR
TI - Dental Service Strategy of Hospitals in Indonesia Based on Big Data Analysis ofSocial Media Users X
AU - Alfiatuz Zahro Al Istiqlaliyah
AU - Muhammad Basir
AU - Abd. Malik Iskandar
AU - Muhammad Idris Paratai
AU - Hairuddin K.
AU - Saparuddin Latu
AU - Chrisogonus K. Onyekwere
AU - Yudi Krisno Wicaksono
PY - 2026
DA - 2026/07/01
JO - KEMAS: Jurnal Kesehatan Masyarakat
DO - 10.15294/kemas.v21i4.32631
UR - https://doi.org/10.15294/kemas.v21i4.32631
AB - This study analyzes public perception of hospital dental polyclinic services in Indonesia through big data sentiment analysis of 3,075 tweets from the X platform (January–November 2024), using keywords like “dental hospitals” and “dental poly hospitals.” Employing a descriptive design, data was crawled via Google Colab, followed by preprocessing steps: duplicate removal, non-essential character cleanup, normalization, tokenization, stopword elimination, and stemming. The Naïve Bayes Classifier algorithm classified sentiments, revealing 61.54% negative sentiment (1,571 tweets) and 38.46% positive sentiment (982 tweets), with 73% model accuracy, 0.73 negative precision, and 0.90 negative recall. Negative sentiments highlighted issues, such as long waiting times, inadequate facilities, and BPJS-related administra- tive delays, while positive sentiments praised professional staff and comprehensive facilities. Field data from tweet analysis showed frequent complaints about procedural discomfort (e.g., “pain,” “pluck”) and appreciation for competent doctors. SWOT analysis, triangulated with multi-stakeholder assessments (hospital administrators, directors, dentists), yielded an IFAS score of 7.04 and an EFAS score of 6.84, indicating strong internal capabilities but operational inefficiencies. Strategic recommendations include optimizing workflows, standardizing services, and leveraging public awareness to enhance specialized dental care, addressing public dissatisfaction for sustainable service improvement.
SN - 1858-1196
SN - 2355-3596
ER -