Ref | Language | Coupes | Healthcare scope | Method | Objective /findings |
---|---|---|---|---|---|
# [18] | English | NHS website | Clinical service | NLP and Topic Modeling | - Classification of patients' emotions into positive and negative categories - Identifying frequent topics in patients' comments |
# [10] | English | NHS website | Hospital's performance | ML | - Presenting a model to predict patients' views on different aspects of a hospital's performance |
# [12] | English | Breast cancer | NLP and ML | - Different experiences of the patient from the treatment process, their needs and concerns were identified | |
# [21] | English | Breast Cancer community group (Breastcancer.org) | Breast cancer | ML and Deep Learning | - The change in user satisfaction levels was measured - Changes in patients' emotions were investigated |
# [22] | English | Breast cancer | Deep Learning and topic modeling | - Identifying recurring topics - Identifying emotions over time | |
# [33] | English | Social networks, message boards, patient communities, and topical sites | Breast cancer | ML | - Understanding barriers to breast cancer treatment |
# [30] | Indonesian | Google Play Store | Service quality | ML and Fast Large-Margin classification methodology | - Classification of service quality comments into positive and negative categories - Information quality, system quality, and interaction quality affect customer satisfaction |
# [31] | Arabic | Health services | ML and Deep Learning | - Classification of opinions into positive and negative categories | |
# [32] | Spanish | COPOS (Corpus Of Patient Opinions in Spanish) | Medical attention | Semantic orientation and ML | - polarity classification |
# [34] | Persian | Database of Rajaie Cardiovascular Medical and Research Center | Hospital wards and staff members | Lexicon-based method and ML | - patients’ atisfaction analysis - Determining the different ward and staff names mentioned in patients’ messages |
Our research | Persian | Patient feedback form of the Tehran University of Medical Science Cancer Institute | Hospitalized Cancer Patient | Lexicon-based method and Topic modeling | - patients' sentiments about general services, healthcare services, and life expectancy |