User Applications Research Articles

Mediation of customer satisfaction: E-service quality, brand trust, and reuse intention

The purpose of this study is to explain the role of customer satisfaction in mediating e-service quality and brand trust on reuse intention in the Traveloka application. The theories used are the Techlonogy Acceptance Model (TAM) and Expectancy Disconfirmation Theory (EDT). This research is a type of quantitative research that is associative in nature. The population in this study are all Traveloka application users who have transacted at least three (3) times in one year. The sampling technique used purposive sampling with a total sample member of 205 respondents. Respondent data collection was carried out by distributing questionnaires. The data analysis technique in this study used PLS-based SEM. The results showed that all variables had a positive and significant effect. Customer satisfaction acts as a partial mediation in mediating the effect of e-service quality and brand trust on reuse intention on the Traveloka application. The results of this study can provide an empirical contribution about the relationship between the variables of e-service quality, brand trust, customer satisfaction, and reuse intention for the development of the Technology Acceptance Model (TAM) and Expectancy Disconfirmation Theory (EDT). Traveloka management can implement a marketing strategy that emphasizes service quality and information accuracy to increase customer intention to reuse the Traveloka application.

Pengaruh Word of Mouth dan Harga terhadap Kepuasan Konsumen pada Aplikasi Maxim

The number of online transportation companies in Indonesia is growing due to advances in technology that enable everything to be done online. This study used quantitative methods to determine the impact of word of mouth and price variables on consumer satisfaction with the Maxim application. A questionnaire was distributed to 115 users of the Maxim online transportation application, and the data was processed using SSPS with multiple linear regression analysis, T-test, r-test, R2 test, Validity test, and Reliability test. The results showed that word of mouth and price had a positive effect on consumer satisfaction with the Maxim application. A number 78.3% of consumer satisfaction was influenced by the independent variables, namely word of mouth (X2) and price (X2) while the remaining 21.7% is influenced by other variables in this research.

Ubrogepant users' real-world experience: Patients on ubrogepant, characteristics and outcomes (UNIVERSE) study.

To assess the real-world effectiveness of ubrogepant by evaluating self-reported satisfaction with pain relief, ability to think clearly, and return to normal function in individuals who had used ubrogepant to treat a migraine episode within the preceding 14 days. Ubrogepant is an oral calcitonin gene-related peptide receptor antagonist approved for the acute treatment of migraine in adults. Few studies have evaluated the real-world effectiveness of ubrogepant. The UNIVERSE study was an observational, cross-sectional survey conducted between February 2021 and April 2021 in US adult Migraine Buddy application (app) users currently treated with ubrogepant. Individuals who were 18 years of age or older and reported at least one dose of ubrogepant in the previous 14 days completed a 30-question survey in the app. The survey assessed respondent demographics, migraine history, acute treatment patterns, and treatment satisfaction with ubrogepant. Respondents also reported prior acute medication use and reasons for switching to ubrogepant. Of the 1303 ubrogepant users contacted, 302 (23.2%; 50 mg, 120 participants; 100 mg, 182 participants) were included in this study. The mean (standard deviation) age was 41.9 (11.2) years, and 90.1% (272/302) were female. Satisfaction with migraine relief at 2, 4, and 24 h post-dose was reported by 75.8% (229/302), 83.4% (252/302), and 78.5% (237/302) of participants, respectively. Satisfaction with the ability to think clearly after taking ubrogepant was reported by 85.1% (257/302) of participants, and 83.8% (253/302) were satisfied with their ability to return to normal function. Furthermore, 90.7% (274/302) of participants reported that they were likely to continue using ubrogepant to treat their migraine. Most participants (n = 264 [87%]) reported switching to ubrogepant due to inadequate treatment response with their previous treatment. In this subgroup, comparable outcomes were observed with respect to satisfaction with migraine relief, ability to think clearly, and return to normal function. Ubrogepant demonstrated real-world effectiveness in the acute treatment of migraine, as evidenced by high levels of treatment satisfaction and a strong indication of their intent to continue using the medication.

Assessment of Medication Adherence Using Mobile Applications in Chronic Obstructive Pulmonary Disease: A Scoping Review.

Chronic obstructive pulmonary disease (COPD) is a condition that significantly impacts both patients and healthcare systems. The management of COPD involves various pharmacological intervention strategies, and addressing the issue of low adherence to these strategies has become a subject of significant interest. In response to this concern, there has been a shift toward utilizing telemedicine and mobile applications. The primary objective of this scoping review is to delineate the usage of mobile applications to enhance medication adherence in adult patients with COPD. This study involved a search of databases such as Medline, Google Scholar, Cochrane, and ClinicalTrial.gov, focusing on the literature published in English and Spanish over the last decade. The selected studies assessed interventions involving mobile applications (mobile apps) designed to improve medication adherence. Four digital aids were identified and available on online platforms, mobile apps, or both: m-PAC, myCOPD, Wellinks mHealth, and Propeller Health. Propeller Health, in particular, is an app that directly measures medication adherence through electronic medication monitors attached to participants' inhalers. Opening the app was associated with higher odds of using control medications compared to participants who did not open the app. The findings suggest that these digital interventions serve as valuable tools to enhance patient adherence to treatment. Future research should focus on evaluating the effectiveness of different digital devices, such as digital inhalers and mobile applications, that directly measure medication adherence.

Study path analyses for quality assurance and support of study planning

AbstractUtilizing student lifecycle data provided by campus management systems yields the opportunity to conduct study path analyses. Methods of artificial intelligence (AI) and data science can be used to analyze study paths, identify indicators for success, and gain insights into problems and issues of student cohorts following different study paths. Meanwhile, AI can also be used to support students through informed study planning. This article presents the project AIStudyBuddy with its focus on utilizing rule-based AI and process mining to support study planning and cohort monitoring. The concept of a reference architecture and data model for study path analytics as well as details on the development of the two user applications, StudyBuddy for students and BuddyAnalytics for study program designers, are presented. By exploring how AI and process mining can be applied in the scope of the two applications, the article addresses the question of how AI can be used for quality assurance in study planning and student cohort monitoring.

Oncology Clinicians' Perspectives of a Remote Patient Monitoring Program: A Multi-Modal Case Study Approach.

Remote patient monitoring (RPM) aims to improve patient access to care and communication with clinical providers. Overall, understanding the usability of RPM applications and their influence on clinical care workflows is limited from the perspectives of clinician end users at a cancer center in the Northeast, United States. Explore the usability and functionality of RPM and elicit the perceptions and experiences of oncology clinicians using RPM for oncology patients after hospital discharge. The sample included 30 of 98 clinicians (31% response rate) managing at least five patients in the RPM program and responding to the m-Health Usability between March 2021- October 2021. Overall, clinicians responded positively to the survey. Item responses with the highest proportion of disagreement were explored further. A nested sample of five clinicians who responded to the study survey (30% response rate) participated in interview sessions conducted from November 2021 to February 2022, and averaged 60 minutes each. Survey responses highlighted that RPM was easy to use and learn and verified symptom alerts during follow-up phone calls. Areas to improve identified practice changes from reporting RPM alerts through digital portals and its influence on clinicians' workload burden. Interview sessions revealed three main themes: clinician understanding and usability constraints, patient constraints, and suggestions for improving the program. Subthemes for each theme were explored, characterizing technical and functional limitations that could be addressed to enhance efficiency, workflow, and user experience. Clinicians support the value of RPM for improving symptom management and engaging with providers. Functional changes to enhance the program's utility, such as input from patients about temporal changes in their symptoms and technical resources for home monitoring devices.

Analysis of Public Sentiment Towards Celebrity Endorsment On Social Media Using Support Vector Machine

Analysis of public sentiment towards celebrity endorsements on social media is very important to understand the public's response to promotional campaigns involving celebrities. In this study, we combine the VADER labeling method with the Support Vector Machine (SVM) method to analyze public sentiment toward celebrity endorsements on social media. Data is taken from various social media sources such as Twitter, Instagram, and Facebook. The data is pre-processed to ensure data accuracy and relevance and then labeled with the VADER method to determine the positive, negative, or neutral sentiment of the text. The labeled data is then extracted for features and used to train the SVM model. The trained SVM model is then validated using test data to measure its accuracy and performance. The results of the analysis provide useful insight into public sentiment towards celebrity endorsements on social media and can provide recommendations for stakeholders regarding this matter. Overall, combining the VADER labeling method with SVM in analyzing public sentiment towards celebrity endorsements on social media shows more accurate results and can provide practical benefits in marketing and promotional strategies. The results shown using the Support Vector Machine method with a ratio of 80:20 can provide average precision results of 77%, recall of 100%, f1-score of 87%, and accuracy of 76.92%. Twitter application user sentiment shows that 77% (338 data) of Twitter user reviews provide positive sentiment and 23% (119 data) provide negative sentiment reviews from a total of 517 data. Suggestions from researchers are that in future research they can add more data to make modeling easier to provide higher accuracy values. Using other classification and performance evaluation methods, such as Naive Bayes, Decision Tree, Fuzzy, or Deep Learning. Use other data processing tools, such as RapidMiner, Jupyter Notebook, RStudio, or others.

The Usability and Feasibility of a Dietary Intake Self-Monitoring Application in a Population with Varying Literacy Levels.

Our aim was to study how hemodialysis patients with varying levels of literacy would use a diet and fluid intake monitoring mobile application (DIMA-P) and what would be its impact on their dietary behaviors. We developed a mobile application using user-centered methods and informed by the Integrated Theory of Health Behavior Change (ITHBC). Eight hemodialysis patients were recruited to use the application to record and monitor their diet and fluid intakes for a 6-week study. Overall, the participants had low literacy, numeracy, and technical skills. We collected the data on application usage and administered usability and context-of-use questionnaires to gain insights into the participants' interaction with the application. The participants' portion estimation skills and dietary self-regulation self-efficacy were assessed using various tests. In addition, interdialytic weight gain data were collected to assess the impact of app usage on the participants' health outcomes. The application usage patterns varied, with a general trend towards frequent use (n = 5) correlating with engagement in self-monitoring. The participants gave high comprehensibility, user-friendliness, satisfaction, and usefulness ratings, suggesting that the app was well designed and the target users could easily navigate and interact with the features. While the participants improved in estimating portion sizes, the impact on measuring skills was variable. There was also an improvement in the participants' dietary self-regulation self-efficacy post-study. The interdialytic weight gain trends indicated a slight improvement in fluid and diet management. People with different literacy skills can effectively use icon-based interfaces for portion size estimation and develop personalized usage patterns to self-regulate their fluid and dietary intakes. Moreover, they can experience an enhancement in their dietary self-efficacy skills by using a mobile application aimed at providing nutritional feedback. Furthermore, this research shows that the constructs of the ITHBC are effective in promoting dietary behavior change in a population with varying literacy skills. The target users can benefit from explicitly visualizing the relationship between their health outcomes and the factors influencing those outcomes. These user ambitions could be supported by developing machine learning models. Future research should also focus on enhancing the mechanisms by which technology can further enhance each component of the ITHBC framework.

Factors influencing the acceptance and use of a South African data-free job search application

Background: Despite the rise of digital job search tools, many South Africans remain excluded due to connectivity and financial barriers. The digital divide, particularly among youth and low-income groups, limits access to job opportunities, exacerbated by data costs and limited digital skills.Objectives: This study investigates the factors influencing the acceptance and use of a data-free job search application, focusing on challenges related to connectivity, data costs, and digital skills.Method: A qualitative approach is employed, analysing Google Play Store reviews through thematic analysis. The Unified Theory of Acceptance and Use of Technology (UTAUT) framework is applied to explore the influence of performance expectancy, effort expectancy, social influence, and facilitating conditions on user adoption.Results: Performance expectancy, effort expectancy, and facilitating conditions are key drivers of application usage. Positive user experiences with these factors enhance engagement, while negative perceptions of usability and technical issues limit consistent use.Conclusion: Addressing connectivity and usability issues is essential to improving the acceptance and use of data-free job search applications in South Africa. Enhancing performance expectancy, effort expectancy, social influence, and facilitating conditions can significantly increase user engagement.Contribution: The study offers practical insights for developers and policymakers to enhance the accessibility and usability of data-free job search tools, promoting more equitable access to job opportunities for disadvantaged groups.

Penerimaan Aplikasi Loklok Menggunakan Metode Technology Acceptance Model (TAM) oleh Masyarakat Jakarta

Nowadays, the development of communication and information technology has brought major chages in various aspect of life, one of them is in entertainment aspects. For example video streaming technology. Video streaming technology has been part of modern society. Loklok is of video streaming technology application which is popular in Indonesia. The purpose of this research is to analyze the acceptance video streaming technology on Loklok application and find out whether it can be generally acceptance by the people of Jakarta. This research was done for loklok application users. Loklok is an application or platform that provides video streaming services with many varieties of genres such Korean dramas, western films and animations. The conceptual model of technology acceptance assessment is based on the Technology Acceptance Model (TAM), which is a research model that analyzes the factors that influence the acceptance of computer technology. The statistical analysis used is the partial least squares structural equation model. This research uses quantitative methods with data collection techniques in the form of filling out online questionnaires through Google Forms with the number of respondents determined by the Slovin formula and sampling techniques using simple random sampling. This study uses PLS-SEM data analys with SmartPLS tools with a sample size of 100. The results of this study indicate that the variables Perceived Usefulness -> Attitude of use, Perceived ease of use -> Attitude of use, Attitude of use - > Behavioral Intention Of Use and Behavioral Intention Of Use -> Actually System Use are positive which means that the LokLok application is well received by the Jakarta Community.

An efficient beam sweeping scheme with backup paging occasions in NR-Unlicensed Spectrum

With the increasing demand of user applications and the shortage of cellular spectrum, New Radio (NR) access to Unlicensed Spectrum (NR-U) is getting significant attention. Listen Before Talk (LBT) procedure is used to sense unlicensed channel availability prior to transmission. The transmissions are subjected to LBT procedure failure, which brings extra delay as they are postponed to the next available transmission opportunity. This excess delay also affects time-critical procedures, such as paging. The directional communication in NR requires beamforming, which further complicates paging procedure as additional paging message transmissions are needed to cover all the beams. In this work, we propose an NR-U paging mechanism (called FF_BP) consisting of Full and Fast Paging Cycles with Backup Paging Occasions (POs). Full Paging uses a normal NR-U paging cycle and broadcasts a paging message on all the beams. On the other hand, Fast Paging, which targets delay-sensitive mobile users, uses a shorter paging cycle and broadcasts a paging message on selected beams only. The Backup POs deal with LBT procedure failure impairments while paging broadcast on selective beams reduces paging resource usage. We analyze FF_BP using a discrete-time semi-Markov chain model and validate the model by extensive simulations. The simulation results show that FF_BP outperforms several baseline mechanisms in terms of average paging delay and paging resource usage.

The Role of Lifestyle, Advertising, and Discount on Impulsive Buying (Survey of Tokopedia Application Users in Kuningan Regency)

The intent of this study is to assess the impact of lifestyle, advertising, and discounts on impulsive purchases among Tokopedia application users in Kuningan Regency. The study methodology used in this research is descriptive and verification research methods with a data-driven survey approach. The demographic of the study composed of all people in Kuningan Regency who use the Tokopedia application. The sample size is 100 respondents, selected using purposive sampling techniques. The criteria for respondents include those who have used the Tokopedia application at least twice. The data used in obtained through surveys distributed to respondents who met the specified criteria. The results of the study show that lifestyle, advertising, and discounts have a positive and significant effect on impulsive buying. Advertising in particular, exerts a substantial positive and significant impact on impulsive buying.

German mHealth App Usability Questionnaire (G-MAUQ) and short version (G-MAUQ-S): Translation and validation study

BackgroundThe use of mobile health applications is increasingly common among the general public and in healthcare systems. With such apps percolating into the classic healthcare sector, the necessity of sound and standardized evaluation grows. The mHealth App Usability Questionnaire (MAUQ) provides a novel and custom-tailored psychometrically validated instrument to capture users’ perception of the usefulness and usability of an mHealth application. So far, this questionnaire is only available in English, Malay and Chinese. The aim of this study was to translate and validate a German version of the MAUQ (G-MAUQ). Further, we developed a short scale with 6 items (G-MAUQ-S) in German. MethodsWe used the Translation, Review, Adjudication, Pretest and Documentation (TRAPD) method to translate the MAUQ. Subsequently, we assessed content validity with 15 expert ratings and face validity with 15 German speaking mHealth users. To further validate the questionnaire, we used data from 148 participants of an RCT examining symptom checkers in the Emergency Department to assess convergent validity by correlating the G-MAUQ with the German version of the System Usability Scale and discriminant validity by correlating the G-MAUQ with other unrelated questionnaires. Lastly, we developed a short version by assessing item discrimination, factor loadings, correlation with the full scale and construct validity. ResultsAll but one item showed sufficient content validity with item-level content validity index values between CVI-I = 0.8 and 1.0. Face validity was excellent with item-level face validity index values ranging from FVI-I = 0.87 to 1. Convergent validity was sufficient with r = 0.769, and discriminant validity was sufficient with values between r = −0.014 and r = 0.220. An internal consistency of Cronbach's α = 0.93 demonstrated high reliability. The short scale showed sufficient convergent validity (r = 0.762) and discriminant validity (r between −0.012 and 0.201). ConclusionsA validated and reliable G-MAUQ can be used by researchers and practitioners to assess the usability of mHealth interventions. We also provide the German mHealth App Usability Questionnaire – Short Version (G-MAUQ-S) with six questions to quickly assess the usability of an intervention.

Toward security quantification of serverless computing

Serverless computing is one of the recent compelling paradigms in cloud computing. Serverless computing can quickly run user applications and services regardless of the underlying server architecture. Despite the availability of several commercial and open-source serverless platforms, there are still some open issues and challenges to address. One of the key concerns in serverless computing platforms is security. Therefore, in this paper, we present a multi-layer abstract model of serverless computing for an security investigation. We conduct a quantitative analysis of security risks for each layer. We observe that the Attack Tree and Attack-Defense Tree methodologies are viable approaches in this regard. Consequently, we make use of the Attack Tree and the Attack-Defense Tree to quantify the security risks and countermeasures of serverless computing. We also propose a novel measure called the Relative Risk Matrix (RRM) to quantify the probability of attack success. Stakeholders including application developers, researchers, and cloud providers can potentially apply these findings and implications to better understand and further enhance the security of serverless computing.

Principles of constructing mental models of a solution for external users in the task of generating explanations in an intelligent system

The subject of the research is the process of constructing user mental models in intelligent information systems. The aim is to improve the principles of building mental models of external users regarding the decisions of an intelligent information system to form explanations in accordance with both the needs of these users and the limitations on the use of solutions in a specific subject area. Objectives: improvement of existing principles of mental model construction based on structuring the description of the intelligent system's solution; development of a principle for constructing mental models of the intelligent system user, considering the limitations when using the obtained solution. The scientific novelty of the obtained results is as follows. The existing principles of human mental model construction have been adapted, considering the differences in constructing explanations for a solution in an intelligent system represented as a «black box». The adapted principles consider the correspondence between the structure of the mental model and the solution, the multiplicity of mental models regarding the solution, and the incompleteness of input data for decision-making. The principle of input data supplementation is proposed, which consists in using the values of solution properties that are irrelevant from the user's point of view to limit the set of relevant solutions. The use of this principle in constructing an explanation makes it possible to consider the negative aspects of using the obtained result and thereby simplify the user's choice and application of this solution.

Design of an international trade target supplier evaluation system based on CART algorithm

International trade, as an important component of economic exchange between countries, is of great significance for the economic development of each country and international cooperation. In international trade, the selection and evaluation of suppliers has always been a key issue. To ensure the smooth progress of trade and the controllability of quality, it is necessary to establish a target supplier evaluation system. This article used the CART (Classification and Regression Tree) algorithm to help identify and analyze the impact of key factors on supplier evaluation and classify and evaluate suppliers. The international trade target supplier evaluation system based on the CART algorithm was also constructed, and its performance was tested in the experimental section and compared with the international trade target supplier evaluation system based on traditional algorithms. According to the experimental results, it can be concluded that both the traditional algorithm and the CART algorithm performed well in terms of application effectiveness and system user satisfaction. In terms of application effectiveness, the average score of traditional algorithms was 4.3, with a rating range of 3.8 to 4.9, while the average score of the CART algorithm was 4.6, with a rating range of 4.2 to 5.0. The satisfaction rating of system users on the CART algorithm was slightly higher than that of traditional algorithms, indicating that the CART algorithm has better application effectiveness and user satisfaction in the design of international trade target supplier evaluation systems. The design of an international trade target supplier evaluation system based on the CART algorithm can also help enterprises reduce trade risks and improve the stability and reliability of the supply chain. It has important practical significance and application value for further promoting the development of international trade.

Audit Tools and Linked Archive System (ATLAS) in the Process of Preparing Audit Working Papers: Approach with the End User Computing Satisfaction (EUCS) Model"

This study aims to investigate the factors that influence user satisfaction with the ATLAS application for preparing Audit Working Papers, utilizing the Computing End User Satisfaction (EUCS) model. It adopts a quantitative approach with a sample of 83 auditors from KAPs in East Java Province who use the ATLAS application, selected through convenience sampling. Data analysis was performed using Partial Least Squares with SmartPLS 2.0. The findings suggest that content, accuracy, format, and timeliness positively affect user satisfaction with the ATLAS application for preparing Audit Working Papers. However, ease of use does not significantly impact auditor satisfaction as an application user.

Developing a Design Guideline for a User-Friendly Home Energy-Saving Application That Aligns with User-Centered Design (UCD) Principles

Regarding issues with the majority of home energy-saving applications, the information is often too difficult for users to understand, and they struggle to comprehend communication via graphics or images displayed on the application’s screen. Furthermore, little is known about how users of home energy-saving applications behave. Therefore, this research aims to develop and evaluate a user-friendly design guideline for a home energy-saving application that applies four stages of User-Centered Design (UCD) processes. To identify significant issues and preliminary solutions, this research employed two rounds of co-creation activities involving nine experts and nine non-experts. Subsequently, an application prototype encompassing settings, about, home data, home assessment, and assessment summary was developed. The prototype underwent evaluation through an online questionnaire with 160 participants from four user groups, spanning expert and non-expert age groups. As a results from all four factors, the application received a mean score = 4.35 (good) from both non-experts and experts. This demonstrates that the prototype adopted with the guideline performed well in terms of User Experience, User Interface and User-Centered Design. This research provides developers and stakeholders with valuable guidelines to create applications or programs that are more efficient and user-friendly. This guideline is applicable to a wide range of sectors (eg, residential homes, workplaces, and educational institutions) and various domains (eg, Internet of Things (IoT), Home Energy Management Systems (HEMS), mobile applications, AI-Assisted in IoT-based Smart Microgrids). This would lead to the creation of applications that are easy for users to navigate and presentations that are impactful, ultimately helping to decrease energy usage and promote a more sustainable environment.

Mapping the Online Reviews Sentiment Landscape: An Exploration of Emotion Spectrum in User Reviews of Mobile Apps

Mobile applications have emerged as powerful platforms for consumers and understanding the attitudes and reactions of users by content and emotional sides in a mobile context becomes crucial for marketing decision-making. The study with comprehensive approach aims to analyze the emotion spectrum in mobile applications user reviews context by examining specific emotions (anger, disgust, fear, joy, neutral, sadness, surprise). Sentiment analysis methodology (through "Emotion English DistilRoBERTa-base" transformers-model) is employed on the dataset of 302.647 reviews from 34 mobile application categories. Categorical examination of emotions indicates that neutrality is the dominant emotion category, followed by joy, sadness, disgust, surprise, and anger emotion categories, while the fear category is the least dominant category. According to polarity examination; negative polarity reviews are associated with neutral, sadness and disgust emotions; neutral polarity reviews are associated with neutral and sadness; positive polarity reviews are associated with neutral and joy emotion categories. Final part of analysis includes examination of emotions individually and mobile app categories which each emotion with the highest frequency of dominance are presented. The distribution rates of emotions and the individual relationships of emotions with different application categories can shed light on future academic research and marketing decision-making.

Identify Issues That Influence Customer Satisfaction Using Sentiment Analysis and Topic Modeling

The development of internet users in Indonesia continues to increase over time, this makes customers comfortable with digital transactions. Trinusa Travelindo Company or better known as Traveloka, which is engaged in the online travel agent sector, has proven its extraordinary achievement, namely becoming the E-tourism application that is ranked 1st most visited by the Indonesian people in 2022. However, these results are also directly proportional to the number of negative reviews created in the application review itself. This study aims to identify what issues affect customer satisfaction with topic modelling. This study uses the text mining method derived from the results of Traveloka application user reviews. The data source obtained in this study is secondary data by using the Traveloka application review data crawling technique with samples from January to May. Based on sentiment analysis, positive sentiment is more dominant (50.38%) compared to negative sentiment (49.62%). User reviews are grouped based on the results of sentiment analysis, then Topic Modelling is carried out to find out what issues affect customer satisfaction. The topic modelling of the data used is Latent Dirichlet Allocation (LDA) and Latent Semantic Analysis (LSA) with the help of phyton 6.3. to find out what words and topics often appear or as factors that influence customer satisfaction. The most influential negative issues include the refund and payment process, pay later services, and the ordering experience which is considered complicated. On the other hand, issues that contribute positively to customer satisfaction include product quality, service quality, and promos and discounts. This is reinforced by the results of topic modelling which show that these aspects are often the main concerns in user reviews on the Google Play store. Thus, this study suggests that in order to increase customer satisfaction, Traveloka needs to focus on improving the quality of service, products, and offering more attractive promos, while simplifying the refund process and ordering experience in the application, some still say it is complicated.