Evaluating of the Impact of Ministry of Health Mobile Applications on Corporate Reputation Through User Comments Using Artificial Intelligence

The concurrent think-aloud protocol (CTA) is an effective method for collecting abundant product comments related to user satisfaction during the execution of evaluation tasks. However, manual analysis of these audio comments is time-consuming and labor-intensive. This paper aims to propose an approach for automated comprehensive evaluation of user interface (UI) satisfaction. It takes advantage of text mining and sentiment analysis (SA) techniques instead of manual analysis in order to assess user comments collected by the CTA. Based on the results of the SA, the proposed approach makes use of the analytic hierarchy process (AHP) method to evaluate the overall satisfaction and support developers for UI design improvements. In order to enhance the objectivity of evaluation, a sentiment matrix originating from text mining and SA on user comments is used to replace the criteria and the relative weights of the AHP method which were previously defined by experts. A comparison between the questionnaire survey method and the proposed approach in the empirical study suggested that the latter can efficiently evaluate UI satisfaction with high accuracy and provide designers abundant and specific information directly related to defects in design. It is argued that the proposed approach could be used as an automated framework for handling any type of comments.

Purpose This study aims to analyse user sentiments towards virtual influencers on Instagram and identify key positive and negative themes to enhance the understanding of consumer perceptions of digital media strategies. Design/methodology/approach Using sentiment analysis and text-mining techniques, 20,000 comments from Instagram were systematically classified into positive and negative sentiments. The study identified seven positive themes (creativity, engagement, inspiration, aesthetic appeal, community support, brand collaboration and authenticity) and five negative themes (commercialisation, deception, privacy concerns, emotional connection and cultural insensitivity). Findings The findings revealed that users highly value creativity, engagement and authenticity in virtual influencers, which contributes to positive user experiences. Conversely, excessive commercialisation, perceived deception and cultural insensitivity are significant negative factors that can erode trust and loyalty. Research limitations/implications This study was limited to Instagram comments, which may not fully represent sentiments on other social media platforms. Further research could use a more extensive sample and apply other qualitative techniques to obtain more detailed findings. Future research could also track changes in attitudes in relation to virtual influencers over time. Practical implications The findings of this study offer practical guidelines for brands and marketers on how to leverage virtual influencers effectively. Thus, by focusing on positive aspects and responding to negative issues, brands can improve customer interaction, satisfaction and loyalty. Social implications This study contributes to the literature on virtual influencer marketing by identifying key psychological and cultural factors that shape consumer sentiment. It also introduces a replicable text mining framework for future research on digital branding, emotional engagement and artificial intelligence (AI)-driven marketing. Originality/value This study enhances the theoretical understanding of digital media and cultural sensitivity and provides practical recommendations for enhancing virtual influencer strategies. These findings can help brands and marketers better understand the consumer perception landscape in the digital media age.

This study analyses user satisfaction with digital content platforms in Turkey through user comments using artificial intelligence and text mining techniques. The 1,400 comments collected over a seven-month period were classified as positive, negative, and neutral using the TextBlob library, and emotional trends were visualised with word frequencies and word clouds. The findings show that user satisfaction fluctuates over time; positive comments increase in February and March, while neutral attitudes come to the fore in June and July. In particular, the frequent use of content-orientated expressions such as ‘scenario’, ‘series’ and ‘character’ reveals that audience feedback is shaped by thematic elements. The study provides strategic recommendations for content development and user experience management on digital platforms.

An application is a program that is developed to meet user needs. M-banking is one application that makes it very easy for users to make transactions anytime and anywhere. The services contained in the M-banking application make users do not need to bother visiting ATMs or banks. The number of BCA Mobile application installations through Playstore reached more than 50 million users The development of technology is currently increasing rapidly, including applications in the field of banking which are now widely used for mobile transactions without the need to go to a bank or ATM Of course, this makes it very easy for users or customers to make transactions using the mobile banking application. User reviews are an important source of information for developers to find out complaints from users or customers. User comments and ratings in reviews are needed by developers to improve the quality and performance of M-Banking applications. However, this does not guarantee satisfaction for application users. To identify the sentiment of BCA Mobile application users, sentiment analysis will be carried out with the Naive Bayes algorithm. This aims to assess the accuracy of the Naive Bayes algorithm. This study aims to determine the results of sentiment through comments from application users and to determine the results of accuracy, precision and recall. Whether the results of this analysis will be greater than positive or negative values. At the same time to see how accurate it is if sentiment analysis is classified with the Naive Bayes method. The data used is obtained through web scraping from 1000 user reviews on the Google Play Store application. For after web scrapping, a preprocessing stage will be carried out, and the data is divided into 60% training data and 40% training data.

Millions of mobile apps have been available through various app markets. Although most app markets have enforced a number of automated or even manual mechanisms to vet each app before it is released to the market, thousands of low-quality apps still exist in different markets, some of which violate the explicitly specified market policies. In order to identify these violations accurately and timely, we resort to user comments, which can form an immediate feedback for app market maintainers, to identify undesired behaviors that violate market policies, including security-related user concerns. Specifically, we present the first large-scale study to detect and characterize the correlations between user comments and market policies. First, we propose CHAMP, an approach that adopts text mining and natural language processing (NLP) techniques to extract semantic rules through a semi-automated process, and classifies comments into 26 pre-defined types of undesired behaviors that violate market policies. Our evaluation on real-world user comments shows that it achieves both high precision and recall (> 0.9) in classifying comments for undesired behaviors. Then, we curate a large-scale comment dataset (over 3 million user comments) from apps in Google Play and 8 popular alternative Android app markets, and apply CHAMP to understand the characteristics of undesired behavior comments in the wild. The results confirm our speculation that user comments can be used to pinpoint suspicious apps that violate policies declared by app markets. The study also reveals that policy violations are widespread in many app markets despite their extensive vetting efforts. CHAMP can be a whistle blower that assigns policy-violation scores and identifies most informative comments for apps.

TTwitter has allowed textual data to be collected using Text Mining and Sentiment Analysis techniques in the age of social media in which user-generated content becomes redundant. However, due to some inconsistencies, Text Cleaning plays an important role before Text Mining and Sentiment Analysis techniques can be conducted. Hence, this study is conducted to discover the capabilities of Text Cleaning, Text Mining and Sentiment Analysis in three different data mining tools: SAS® Text Miner (proprietary text mining tool), Python and R programming (open-source text mining tools). These data mining tools were used to conduct the Text Cleaning, Text Mining and Sentiment Analysis and their capabilities such as features, functions and characteristics were evaluated and investigated, to conduct this comparison study. All the proposed research objectives were met successfully even with the given limitation. A movie critique Dictionary is one of the major theoretical implications of this research. Based on our analysis and results, developers or educational practitioners can discover what is important and what is unimportant when conducting Text Mining and Sentiment Analysis. They will also obtain insights and guidance on how to conduct Text Mining and Sentiment Analysis using SAS Enterprise Miner, Python and R.

Due to the specificity of the characteristics and features of the Arabic language and its complexity, the field of sentiment analysis in Arabic texts still represents a major challenge. Few studies have been conducted for Arabic sentiment analysis (ASA) compared to English or other Latin languages. In addition, most of the current studies on ASA have been conducted on data sets collected from Twitter and very few studies on user comments in Mobile applications (apps) reviews in Google Play Store. Therefore, this paper presents a new approach to sentiment analysis in Arabic text based on the mobile app comments dataset of Google Play Store. The proposed approach uses algorithms such as the Levenshtein distance (LD) algorithm for preprocessing the data. Thereafter, it applies various classification models to identify the mobile applications(apps) reviews in the Google Play Store of Arabic text. The results of the experiment show that the proposed approach is effective for sentiment analysis of Arabic text. The experiments were carried out by comparing the accuracy using the Naive Bayes (NB) algorithm, and we obtained an accuracy of 95.80% and compared it with the use of the LD Algorithm, where we obtained a better accuracy of 96.40% to identify the reviews of the sentence when k=9.

Does artificial intelligence (AI) boost digital banking user satisfaction? Integration of expectation confirmation model and antecedents of artificial intelligence enabled digital banking

ObjectiveDevelopment of novel informatics methods focused on improving pregnancy outcomes remains an active area of research. The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy and improve outcomes.Materials and methodsWe searched English articles on EMBASE, PubMed and SCOPUS. Search terms included ML, AI, pregnancy and informatics. We included research articles and book chapters, excluding conference papers, editorials and notes.ResultsWe identified 127 distinct studies from our queries that were relevant to our topic and included in the review. We found that supervised learning methods were more popular (n = 69) than unsupervised methods (n = 9). Popular methods included support vector machines (n = 30), artificial neural networks (n = 22), regression analysis (n = 17) and random forests (n = 16). Methods such as DL are beginning to gain traction (n = 13). Common areas within the pregnancy domain where AI and ML methods were used the most include prenatal care (e.g. fetal anomalies, placental functioning) (n = 73); perinatal care, birth and delivery (n = 20); and preterm birth (n = 13). Efforts to translate AI into clinical care include clinical decision support systems (n = 24) and mobile health applications (n = 9).ConclusionsOverall, we found that ML and AI methods are being employed to optimize pregnancy outcomes, including modern DL methods (n = 13). Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2). Also, more work on clinical adoption of AI methods and the ethical implications of such adoption is needed.

At present, many organizations realized the importance of sentiment analysis for consumer reviews. The positive and negative comments can help to evaluate the user satisfaction of products and services to control and improve their qualities. In addition, the deep learning techniques are very interesting methods for current researches in the data mining field. Therefore, this research studied on the deep learning techniques to analyzed user reviews and comments in Thai Language from the TripAdvisor website. To begin with, user comments in four categories: hotels, restaurants, tourist attractions, and airlines were collected and tested on the combination of two basic deep learning technique that are convolutional neural network and long-short term memory. All user comments were divided into individual statements to classify into three groups: positive feelings, negative feelings, non-expressed feelings or neutrality. The research results found that the best classification model is the combination of three convolutional neural networks with 32, 64, and 128 filters, respectively, and the kernel size of 2 equal to the three components. Moreover, the performance of the proposed classification model was evaluated by accuracy, precision, and recall values which were higher than 80% in positive and negative groups, including F1 score about 0.8.

Stress and depression are prevalent mental health conditions that significantly impact society. The use of automated health monitoring systems can be vital in improving the detection and management of depression and stress through social networking. Sentiment analysis involves natural language processing and text mining techniques that aim to identify emotions and opinions. Emotional computing is the development and study of devices and systems that can recognize, interpret, process, and mimic human emotions. By using sentiment analysis and deep learning techniques, effective algorithms and systems can be created to target the assessment and monitoring of mental health disorders, especially depression and stress. This paper discusses the application of sentiment analysis and deep learning methods in detecting and monitoring depression and stress. Additionally, the paper proposes a basic design for an integrated multimodal system for stress and depression monitoring that incorporates sentiment analysis and emotional processing techniques. Specifically, the paper outlines the key issues and challenges involved in developing such a system.

Focus issue: Artificial intelligence in medical physics.

This study is motivated by the importance of implementing Good Corporate Governance (GCG) and maintaining a strong corporate reputation in managing earnings, particularly when companies are experiencing financial distress. The primary objective of this research is to examine the effects of GCG and corporate reputation on earnings management, as well as to investigate the moderating role of financial distress in these relationships. A quantitative approach was employed using panel data, with a sample consisting of 28 consumer non-cyclical sector companies listed on the Indonesia Stock Exchange (IDX) during the period 2020–2023. The data analysis technique used was panel data regression with moderation testing. The results indicate that both GCG and corporate reputation have a significant effect on earnings management, with significance levels below 5%. Moreover, financial distress was found to weaken the influence of GCG on earnings management, while strengthening the impact of corporate reputation on earnings management practices. These findings suggest that a company's financial condition plays a crucial role in determining the effectiveness of GCG and corporate reputation in influencing earnings management behavior. The conclusion of this study highlights the critical importance of adhering to sound governance principles and cultivating a strong corporate reputation, especially when facing financial pressure.

Social media platforms are extensively used in exchanging and sharing information and user experience, thereby resulting in massive outspread and viewing of personal experiences in many fields of life. Thus, informative health-related videos on YouTube are highly perceptible. Many users tend to procure medical treatments and health-related information from social media particularly from YouTube when searching for chronic illness treatments. Sometimes, these sources contain misinformation that cause fatal effects on the users’ health. Many sentimental analyses and classifications have been conducted on social media platforms to study user post and comments on many life science fields. However, no study has been conducted on the analysis of Arabic user comments, which provide details on herbal treatments for people with diabetes. Therefore, this study proposes a model to detect and discover emotions/opinions of YouTube users on herbal treatment videos is proposed through an analysis of user comments by using machine learning classifiers. In addition, a new Arabic Dataset on Herbal Treatments for Diabetes (ADHTD), which is based on user comments from several YouTube videos, is introduced. This study examines the impact of four representation methods on ADHTD to show the performance of machine learning classifiers. These methods remove repeating characters in Arabic dialect and character extension known as ‘TATAWEEL’ or ‘MAD’, stemming of Arabic words, Arabic stop words removal and N-grams with Arabic words. Experiments has been conducted based aforementioned methods to handle imbalanced proposed dataset and identify the best machine learning classifiers over Arabic dialect textual data. The model has achieved a higher accuracy that reached 95% when using Synthetic Minority Oversampling TEchnique (SMTOE) techniques to balanced dataset than imbalanced dataset.

Universal artificial intelligence workflow for factory energy saving: Ten case studies