Analyzing patients satisfaction level for medical services using twitter data

Article Subjects > Engineering Europe University of Atlantic > Research > Scientific Production
Ibero-american International University > Research > Articles and books
Universidad Internacional do Cuanza > Research > Scientific Production 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 and Mujahid, Muhammad and Rustam, Furqan and Soriano Flores, Emmanuel and Vidal Mazón, Juan Luis and Díez, Isabel de la Torre and Ashraf, Imran mail UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, emmanuel.soriano@uneatlantico.es, juanluis.vidal@uneatlantico.es, UNSPECIFIED, UNSPECIFIED (2024) Analyzing patients satisfaction level for medical services using twitter data. PeerJ Computer Science, 10. e1697. ISSN 2376-5992

Text
peerj-cs-1697.pdf
Available under License Creative Commons Attribution.
Download (5MB)

Official URL: http://doi.org/10.7717/peerj-cs.1697

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.

Item Type:	Article
Uncontrolled Keywords:	Health care, Patient satisfaction, Feature selection, Machine learning
Subjects:	Subjects > Engineering
Divisions:	Europe University of Atlantic > Research > Scientific Production Ibero-american International University > Research > Articles and books Universidad Internacional do Cuanza > Research > Scientific Production
Date Deposited:	22 Jan 2024 23:30
Last Modified:	22 Jan 2024 23:30
URI:	https://repositorio.unini.edu.mx/id/eprint/10556

Actions (login required)

View Item

open

Influence of E-learning training on the acquisition of competences in basketball coaches in Cantabria

The main aim of this study was to analyse the influence of e-learning training on the acquisition of competences in basketball coaches in Cantabria. The current landscape of basketball coach training shows an increasing demand for innovative training models and emerging pedagogies, including e-learning-based methodologies. The study sample consisted of fifty students from these courses, all above 16 years of age (36 males, 14 females). Among them, 16% resided outside the autonomous community of Cantabria, 10% resided more than 50 km from the city of Santander, 36% between 10 and 50 km, 14% less than 10 km, and 24% resided within Santander city. Data were collected through a Google Forms survey distributed by the Cantabrian Basketball Federation to training course students. Participation was voluntary and anonymous. The survey, consisting of 56 questions, was validated by two sports and health doctors and two senior basketball coaches. The collected data were processed and analysed using Microsoft® Excel version 16.74, and the results were expressed in percentages. The analysis revealed that 24.60% of the students trained through the e-learning methodology considered themselves fully qualified as basketball coaches, contrasting with 10.98% of those trained via traditional face-to-face methodology. The results of the study provide insights into important characteristics that can be adjusted and improved within the investigated educational process. Moreover, the study concludes that e-learning training effectively qualifies basketball coaches in Cantabria.

Producción Científica

Josep Alemany Iturriaga mail josep.alemany@uneatlantico.es, Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Javier Jorge mail , Kamil Giglio mail ,

Alemany Iturriaga

open

Exploring body composition and somatotype profiles among youth professional soccer players

OBJECTIVE: This study aimed to analyze the body composition and somatotype of professional soccer players, investigating variations across categories and playing positions. METHODS: An observational, cross-sectional, and analytical study was conducted with 51 male professional soccer players in the U-19 and U-20 categories. Data about sex, age, height, and weight were collected between March and May 2023. Body composition analysis utilized the ISAK protocol for the restricted profile, while somatotype categorization employed the Heath and Carter formula. Statistical analysis was performed using IBM SPSS Statistics V.26, which involved the application of Mann-Whitney and Kruskal-Wallis tests to discern differences in body composition variables and proportionality based on categories and playing positions. The Dunn test further identified specific positions exhibiting significant differences. RESULTS: The study encompassed 51 players, highlighting meaningful differences in body composition. The average body mass in kg was 75.8 (±6.9) for U-20 players and 70.5 (±6.1) for U-19 players. The somatotype values were 2.6-4.6-2.3 for U-20 players and 2.5-4.3-2.8 for U-19 players, with a predominance of muscle mass in all categories, characterizing them as balanced mesomorphs. CONCLUSIONS: Body composition and somatotype findings underscore distinctions in body mass across categories and playing positions, with notably higher body mass and muscle mass predominance in elevated categories. However, the prevailing skeletal muscle development establishes a significant semblance with the recognized somatotype standard for soccer.

Producción Científica

Raynier Zambrano-Villacres mail , Evelyn Frias-Toral mail , Emily Maldonado-Ponce mail , Carlos Poveda-Loor mail , Paola Leal mail , Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Alice Leonardi mail , Bruno Trovato mail , Federico Roggio mail , Alessandro Castorina mail , Xu Wenxin mail , Giuseppe Musumeci mail ,

Zambrano-Villacres

open

Can the Functional Physical Fitness of Older People with Overweight or Obesity Be Improved through a Multicomponent Physical Exercise Program? A Chilean Population Study

The aim of the present study was to understand the effect of a multicomponent physical exercise program on the functional physical fitness of older people with overweight or obesity in Chile, and whether these effects were similar in women and men. For this purpose, a quasi-experimental study was designed with a control group to evaluate the functional physical fitness through the Senior Fitness Test battery for older people [SFT; aerobic endurance (AE), lower body strength (LBS), upper body strength (UBS), upper body flexibility (UBF), lower body flexibility (LBF), dynamic balance (DB), and hand pressure strength right (HPSR) and left (HPSL)]. Seventy older people with overweight or obesity aged between 60 and 86 years participated (M = 73.15; SD = 5.94), and were randomized into a control group (CG, n = 35) and an experimental group (EG, n = 35). The results after the intervention between the CG and EG indicated that there were statistically significant differences in the AE (p = 0.036), in the LBS (p = 0.031), and in the LBF (p = 0.017), which did not exist before the intervention (p > 0.050), except in the HPSR (0.029). Regarding the results of the EG (pre vs. post-intervention), statistically significant differences were found in all of the variables studied: AE (p < 0.001), LBS (p < 0.001), UBS (p < 0.001), LBF (p = 0.017), UBF (p < 0.001), DB (p = 0.002), HPSR (p < 0.001), and HPSL (p = 0.012) in both men and women. These improvements did not exist in any of the CG variables (p > 0.05). Based on the results obtained, we can say that a multicomponent physical exercise program applied for 6 months in older people with overweight or obesity produces improvements in functional physical fitness regardless of sex, except in lower body flexibility and left-hand dynamometry.

Producción Científica

Yazmina Pleticosic-Ramírez mail yazmina.pleticosic@doctorado.unini.edu.mx, Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es, Marcos Mecías-Calvo mail marcos.mecias@uneatlantico.es, Rubén Navarro-Patón mail ,

Pleticosic-Ramírez

open

Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence

Driving while drowsy poses significant risks, including reduced cognitive function and the potential for accidents, which can lead to severe consequences such as trauma, economic losses, injuries, or death. The use of artificial intelligence can enable effective detection of driver drowsiness, helping to prevent accidents and enhance driver performance. This research aims to address the crucial need for real-time and accurate drowsiness detection to mitigate the impact of fatigue-related accidents. Leveraging ultra-wideband radar data collected over five minutes, the dataset was segmented into one-minute chunks and transformed into grayscale images. Spatial features are retrieved from the images using a two-dimensional Convolutional Neural Network. Following that, these features were used to train and test multiple machine learning classifiers. The ensemble classifier RF-XGB-SVM, which combines Random Forest, XGBoost, and Support Vector Machine using a hard voting criterion, performed admirably with an accuracy of 96.6%. Additionally, the proposed approach was validated with a robust k-fold score of 97% and a standard deviation of 0.018, demonstrating significant results. The dataset is augmented using Generative Adversarial Networks, resulting in improved accuracies for all models. Among them, the RF-XGB-SVM model outperformed the rest with an accuracy score of 99.58%.

Producción Científica

Hafeez Ur Rehman Siddiqui mail , Ambreen Akmal mail , Muhammad Iqbal mail , Adil Ali Saleem mail , Muhammad Amjad Raza mail , Kainat Zafar mail , Aqsa Zaib mail , Sandra Dudley mail , Jon Arambarri mail jon.arambarri@uneatlantico.es, Ángel Gabriel Kuc Castilla mail , Furqan Rustam mail ,

Siddiqui

open

From by-products to new application opportunities: the enhancement of the leaves deriving from the fruit plants for new potential healthy products

In the last decades, the world population and demand for any kind of product have grown exponentially. The rhythm of production to satisfy the request of the population has become unsustainable and the concept of the linear economy, introduced after the Industrial Revolution, has been replaced by a new economic approach, the circular economy. In this new economic model, the concept of “the end of life” is substituted by the concept of restoration, providing a new life to many industrial wastes. Leaves are a by-product of several agricultural cultivations. In recent years, the scientific interest regarding leaf biochemical composition grew, recording that plant leaves may be considered an alternative source of bioactive substances. Plant leaves’ main bioactive compounds are similar to those in fruits, i.e., phenolic acids and esters, flavonols, anthocyanins, and procyanidins. Bioactive compounds can positively influence human health; in fact, it is no coincidence that the leaves were used by our ancestors as a natural remedy for various pathological conditions. Therefore, leaves can be exploited to manufacture many products in food (e.g., being incorporated in food formulations as natural antioxidants, or used to create edible coatings or films for food packaging), cosmetic and pharmaceutical industries (e.g., promising ingredients in anti-aging cosmetics such as oils, serums, dermatological creams, bath gels, and other products). This review focuses on the leaves’ main bioactive compounds and their beneficial health effects, indicating their applications until today to enhance them as a harvesting by-product and highlight their possible reuse for new potential healthy products.

Producción Científica

Lucia Regolo mail , Francesca Giampieri mail francesca.giampieri@uneatlantico.es, Maurizio Battino mail maurizio.battino@uneatlantico.es, Yasmany Armas Diaz mail , Bruno Mezzetti mail , Maria Elexpuru Zabaleta mail maria.elexpuru@uneatlantico.es, Cristina Mazas Pérez-Oleaga mail cristina.mazas@uneatlantico.es, Kilian Tutusaus mail kilian.tutusaus@uneatlantico.es, Luca Mazzoni mail ,

Regolo

Enlaces de interés

Enlaces de interés

Analyzing patients satisfaction level for medical services using twitter data

Abstract

Actions (login required)

TEMÁTICA

ACCESO

IDIOMA

Filtros