eprintid: 10556 rev_number: 8 eprint_status: archive userid: 2 dir: disk0/00/01/05/56 datestamp: 2024-01-22 23:30:10 lastmod: 2024-01-22 23:30:12 status_changed: 2024-01-22 23:30:10 type: article metadata_visibility: show creators_name: Usman, Muhammad creators_name: Mujahid, Muhammad creators_name: Rustam, Furqan creators_name: Soriano Flores, Emmanuel creators_name: Vidal Mazón, Juan Luis creators_name: Díez, Isabel de la Torre creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: emmanuel.soriano@uneatlantico.es creators_id: juanluis.vidal@uneatlantico.es creators_id: creators_id: title: Analyzing patients satisfaction level for medical services using twitter data ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: unic_produccion_cientifica full_text_status: public keywords: Health care, Patient satisfaction, Feature selection, Machine learning abstract: Public concern regarding health systems has experienced a rapid surge during the last two years due to the COVID-19 outbreak. Accordingly, medical professionals and health-related institutions reach out to patients and seek feedback to analyze, monitor, and uplift medical services. Such views and perceptions are often shared on social media platforms like Facebook, Instagram, Twitter, etc. Twitter is the most popular and commonly used by the researcher as an online platform for instant access to real-time news, opinions, and discussion. Its trending hashtags (#) and viral content make it an ideal hub for monitoring public opinion on a variety of topics. The tweets are extracted using three hashtags #healthcare, #healthcare services, and #medical facilities. Also, location and tweet sentiment analysis are considered in this study. Several recent studies deployed Twitter datasets using ML and DL models, but the results show lower accuracy. In addition, the studies did not perform extensive comparative analysis and lack validation. This study addresses two research questions: first, what are the sentiments of people toward medical services worldwide? and second, how effective are the machine learning and deep learning approaches for the classification of sentiment on healthcare tweets? Experiments are performed using several well-known machine learning models including support vector machine, logistic regression, Gaussian naive Bayes, extra tree classifier, k nearest neighbor, random forest, decision tree, and AdaBoost. In addition, this study proposes a transfer learning-based LSTM-ETC model that effectively predicts the customer’s satisfaction level from the healthcare dataset. Results indicate that despite the best performance by the ETC model with an 0.88 accuracy score, the proposed model outperforms with a 0.95 accuracy score. Predominantly, the people are happy about the provided medical services as the ratio of the positive sentiments is substantially higher than the negative sentiments. The sentiments, either positive or negative, play a crucial role in making important decisions through customer feedback and enhancing quality. date: 2024-01 publication: PeerJ Computer Science volume: 10 pagerange: e1697 id_number: doi:10.7717/peerj-cs.1697 refereed: TRUE issn: 2376-5992 official_url: http://doi.org/10.7717/peerj-cs.1697 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Abierto Inglés Public concern regarding health systems has experienced a rapid surge during the last two years due to the COVID-19 outbreak. Accordingly, medical professionals and health-related institutions reach out to patients and seek feedback to analyze, monitor, and uplift medical services. Such views and perceptions are often shared on social media platforms like Facebook, Instagram, Twitter, etc. Twitter is the most popular and commonly used by the researcher as an online platform for instant access to real-time news, opinions, and discussion. Its trending hashtags (#) and viral content make it an ideal hub for monitoring public opinion on a variety of topics. The tweets are extracted using three hashtags #healthcare, #healthcare services, and #medical facilities. Also, location and tweet sentiment analysis are considered in this study. Several recent studies deployed Twitter datasets using ML and DL models, but the results show lower accuracy. In addition, the studies did not perform extensive comparative analysis and lack validation. This study addresses two research questions: first, what are the sentiments of people toward medical services worldwide? and second, how effective are the machine learning and deep learning approaches for the classification of sentiment on healthcare tweets? Experiments are performed using several well-known machine learning models including support vector machine, logistic regression, Gaussian naive Bayes, extra tree classifier, k nearest neighbor, random forest, decision tree, and AdaBoost. In addition, this study proposes a transfer learning-based LSTM-ETC model that effectively predicts the customer’s satisfaction level from the healthcare dataset. Results indicate that despite the best performance by the ETC model with an 0.88 accuracy score, the proposed model outperforms with a 0.95 accuracy score. Predominantly, the people are happy about the provided medical services as the ratio of the positive sentiments is substantially higher than the negative sentiments. The sentiments, either positive or negative, play a crucial role in making important decisions through customer feedback and enhancing quality. metadata Usman, Muhammad; Mujahid, Muhammad; Rustam, Furqan; Soriano Flores, Emmanuel; Vidal Mazón, Juan Luis; Díez, Isabel de la Torre y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, emmanuel.soriano@uneatlantico.es, juanluis.vidal@uneatlantico.es, SIN ESPECIFICAR, SIN ESPECIFICAR (2024) Analyzing patients satisfaction level for medical services using twitter data. PeerJ Computer Science, 10. e1697. ISSN 2376-5992 document_url: http://repositorio.unini.edu.mx/id/eprint/10556/1/peerj-cs-1697.pdf