Fine-Grained Sentiment Analysis on PeduliLindungi Application Users with Multinomial Naive Bayes-SMOTE

Suyuti, Imam; S, Dewi Retno Sari

doi:10.23919/eecsi56542.2022.9946469

Cited by 5 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. Technical problems is referred to as PLMA [1] Several previous studies related to PLMA, but very lack studies on PLMA user experience and user interface, previous related studies were PeduliLindungi's COVID-19 Treatment Success (Indonesian Case Study) [1], User Satisfaction Analysis of PeduliLindungi App Using EUCS Method [5], PeduliLindungi App Users Multinomial Naive Bayes-SMOTE Fine-Grained Sentiment Analysis [6], Integration and Interoperability Issues with PeduliLindungi Data and Software Architecture Refactoring [7], Aspects of the PeduliLindungi App User's Goals, Procedures, Tools, and Surroundings [8], PeduliLindungi User Satisfaction Research [9], Google Play PeduliLindungi sentiment analysis using the Random Forest Algorithm with SMOTE [10], Case Study of Jakarta University Students' Use of the PeduliLindungi App to Prevent COVID-19 [11], PeduliLindungi, an Indonesian tracking app, sheds light on an integrated model of tracking apps [12], Factors That Influence Indonesians' Plans to Use the PeduliLindungi App During COVID-19 [13], Sentiment Analysis Machine Learning Comparison PeduliLindungi Applications [14], Binary Sentiment Reviews: Support Vector Machine vs. Naive Bayes Classifier for the PeduliLindungi App [15], Support Vector Machine and Naive Bayes Algorithm-Based Particle Swarm Optimization Analysis of Google Play User Reviews for PeduliLindungi [16], and Acceleration of Pedulilindungi's Popularity Among the Public in Relation to the Corona Virus (Covid-19) [17].…”

Section: Introductionmentioning

confidence: 99%

Exploring User Experience and User Interface of Indonesian e-Health PeduliLindungi Mobile-Apps with MeCUE 2.0 Framework

2023

View full text Add to dashboard Cite

PeduliLindungi Mobile-Apps (PLMA) is a mobile-based e-Health application that was released by the Ministry of Communication and Information (KOMINFO) of the Republic of Indonesia in April 2020. Its goal is to help the government keep track of the Covid-19 Pandemic in Indonesia and stop it from spreading. PLMA is used to find Covid-19, keep track of it, warn people about it, and stop it from spreading. Reports say that more than 10,000,000 people have downloaded PLMA, and KOMINFO has told all citizens that they must use this app. But PLMA was criticized by people who used its apps because of problems like application errors, data leaks, and mistakes in user data. Also, as of September 29, 2021, 470,521 people had reviewed it on the Google Play Store, giving it an average score of 3.8. The score from the PLMA review shows that the application needs to be improved. PLMA also gets complaints about how hard it is to navigate, how features aren't clear, how there are problems with connection and performance, how personal data isn't safe, and how hard it is to get to. The purpose of the research is to investigate and evaluate PLMA which focuses on the user experience (UX) or user interface (UI) of application users. UI/UX in PLMA has been measured or evaluated in a few studies, but the numbers are still very small and limited. Minge (2020) came up with the meCUE 2.0 framework as a way to evaluate an application user experience service. It is a fairly new and comprehensive framework. The MeCUE 2.0 Framework has a questionnaire with 34 statement items. It is made up of 4 modules: Modules I and II (Perception of quality of instrumental and non-instrumental products), Module III (Emotions), Module IV (Consequences), and Module V (Overall Evaluation). In the first step of this study, the meCUE 2.0 questionnaire was translated and then given to 50 people. The results showed that the UI/UX ratings for PLMA were 3.17 for usefulness, 4 for usability, 3.33 for visual aesthetics, 3 for status, 3.67 for commitment, 3.67 for positive emotions, 2.67 for negative emotions, 3.67 for intention to use, 2.67 for product loyalty, and 3.67 for overall evaluation.(107.00). This research makes a contribution both in terms of ideas and in terms of how it can be used. For example, it tells UX designers and policymakers that they should pay attention to important factors while developing PLMAs.

show abstract