![]() |
JOURNAL TOOLS |
Opzioni di pubblicazione |
eTOC |
Per abbonarsi |
Sottometti un articolo |
Segnala alla tua biblioteca |
ARTICLE TOOLS |
Publication history |
Estratti |
Permessi |
Per citare questo articolo |
Share |


I TUOI DATI
I TUOI ORDINI
CESTINO ACQUISTI
N. prodotti: 0
Totale ordine: € 0,00
COME ORDINARE
I TUOI ABBONAMENTI
I TUOI ARTICOLI
I TUOI EBOOK
COUPON
ACCESSIBILITÀ
ORIGINAL ARTICLE
Gazzetta Medica Italiana - Archivio per le Scienze Mediche 2021 May;180(5):166-71
DOI: 10.23736/S0393-3660.19.04199-8
Copyright © 2019 EDIZIONI MINERVA MEDICA
lingua: Inglese
Data mining framework for analyzing Twitter users’ opinion on the drug mefloquine
Esam M. ELGOHARY 1 ✉, Mohamed M. ABD-ELAZIZ 2
1 Institute of National Planning, Cairo, Egypt; 2 Department of Information Systems, Faculty of Computers and Information Sciences, University of Mansoura, Mansoura, Egypt
BACKGROUND: Nowadays, the increasing data that became available on social media supported fast growth of the healthcare sector by analyzing a wide range of personal health experiences that help healthcare professionals to improve outcomes. This paper presents a new data mining framework to identify the polarity in Twitter (Twitter, Inc., San Francisco, CA, USA) users’ sentiment by extracting data related to mefloquine as a malaria drug and analyze users’ interactions and feedback.
METHODS: The framework consists of seven stages: collecting tweets related to mefloquine use, calculating TF-IDF scores for the words used in the tweets by preparing the collected data to be processed, performing a classification process for the constructed words list to produce three categories: positive, negative and neutral, performing a network analysis process to create a model for the tweets, identifying sub-graphs for this network model, calculating the module average opinion (MAO) and user average opinion (UAO) for all modules into network and, identifying the influential users in each module by performing the information brokers stage.
RESULTS: The results showed that the positive users’ impression was 67.4% and the negative users’ impression was 25.9% while the neutral users’ opinion was 6.7%.
CONCLUSIONS: Results also showed that the users who take advice from a physician before switching to mefloquine made up most of the positive users’ opinions, while the negative opinions ranged from unavailability of the drug and the serious side effects that include long-term mental health problems and neurological side effects. It is therefore not recommended in people with a history of mental health problems or epilepsy.
KEY WORDS: Social media; Delivery of healthcare; Malaria; Mefloquine