Citizen Satisfaction in e-Health Services: A Social Media Analysis of T¨urkiye’s Centralized Doctor Appointment System

National e-appointment systems play a critical role in access to healthcare, while users’ experiences with these systems are increasingly reflected in public online discourse. This study examines social media content related to T¨urkiye’s Centralized Doctor Appointment System (CDAS) to characterize sentiment patterns, temporal changes, and prominent themes in online user discourse. Publicly available comments posted on X (Twitter), Facebook, and YouTube between 1 January 2023 and 21 September 2025 were collected (N = 47,699), of which 34,827 were retained after preprocessing. A Turkish BERT-based sentiment analysis model was used to identify overall sentiment orientations. To evaluate the model’s classification performance on the current CDAS dataset, a random sample of 400 comments was manually labeled and compared with model predictions. This domain-specific validation yielded 85.5% accuracy and Cohen’s κ = 0.776. To examine changes in sentiment over time, change-point analysis was performed on monthly mean sentiment scores, and the pre- and post-break periods were compared using the Mann–Whitney U test and effect-size measures. Overall, 50.2% of comments were classified as positive, 29.4% as negative, and 20.4% as neutral, with a mean sentiment score of 0.19. A structural break was identified around November 2023; the mean sentiment score increased from 0.131 before the break to 0.215 after the break (U = 35, p = .00184), accompanied by a large effect. Finally, BERTopic was applied separately to positive and negative comments to identify the topics shaping favorable and unfavorable discourse. Negative discourse was dominated by appointment unavailability and cancellation problems (86.29%), whereas positive discourse mainly concerned smooth appointment booking and system usability (64.95%) and institutional guidance and standard feedback messages (24.40%). The findings show that social media analytics can serve as a complementary data source for monitoring temporal and thematic patterns in public discourse surrounding national digital appointment services and can provide meaningful indicators for service improvement processes.

Authors

Institutions

Publication Details

Journal
Sakarya University Journal of Computer and Information Sciences
Published
2026-10-27
DOI
https://doi.org/10.35377/saucis...1911035
Primary Topic
Sentiment Analysis and Opinion Mining
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Citizen Satisfaction in e-Health Services: A Social Media Analysis of T¨urkiye’s Centralized Doctor Appointment System

Merve Aksu
2 links
Sakarya University Journal of Computer and Information Sciences
Sentiment Analysis and Opinion Mining
article

Citizen Satisfaction in e-Health Services: A Social Media Analysis of T¨urkiye’s Centralized Doctor Appointment System

Merve Aksu
article en

Abstract

National e-appointment systems play a critical role in access to healthcare, while users’ experiences with these systems are increasingly reflected in public online discourse. This study examines social media content related to T¨urkiye’s Centralized Doctor Appointment System (CDAS) to characterize sentiment patterns, temporal changes, and prominent themes in online user discourse. Publicly available comments posted on X (Twitter), Facebook, and YouTube between 1 January 2023 and 21 September 2025 were collected (N = 47,699), of which 34,827 were retained after preprocessing. A Turkish BERT-based sentiment analysis model was used to identify overall sentiment orientations. To evaluate the model’s classification performance on the current CDAS dataset, a random sample of 400 comments was manually labeled and compared with model predictions. This domain-specific validation yielded 85.5% accuracy and Cohen’s κ = 0.776. To examine changes in sentiment over time, change-point analysis was performed on monthly mean sentiment scores, and the pre- and post-break periods were compared using the Mann–Whitney U test and effect-size measures. Overall, 50.2% of comments were classified as positive, 29.4% as negative, and 20.4% as neutral, with a mean sentiment score of 0.19. A structural break was identified around November 2023; the mean sentiment score increased from 0.131 before the break to 0.215 after the break (U = 35, p = .00184), accompanied by a large effect. Finally, BERTopic was applied separately to positive and negative comments to identify the topics shaping favorable and unfavorable discourse. Negative discourse was dominated by appointment unavailability and cancellation problems (86.29%), whereas positive discourse mainly concerned smooth appointment booking and system usability (64.95%) and institutional guidance and standard feedback messages (24.40%). The findings show that social media analytics can serve as a complementary data source for monitoring temporal and thematic patterns in public discourse surrounding national digital appointment services and can provide meaningful indicators for service improvement processes.

Sakarya University Journal of Computer and Information Sciences(Advanced Online Publication)
Artvin Coruh University (TR)
Good health and well-being
Openalex Percentile: Top 13%
Sentiment Analysis and Opinion Mining
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon