User Sentiment Research Articles

Advanced Feature Extraction and Machine Learning Techniques for Classifying Steam Game Feedback

The gaming industry produces vast amounts of user-generated feedback, making it challenging for developers to efficiently analyze and respond to real-time reviews. This study addresses the problem of classifying large-scale unstructured user feedback from Steam reviews. In this paper an approach that integrates traditional machine learning models and deep learning models is proposed. XGBoost is used to manage feature-rich datasets, reducing overfitting. Long-short-term memory (LSTM) and Bi-directional LSTM are used to enhance the accuracy and robustness of classification. Feature extraction techniques, such as sentiment analysis and topic modeling, are employed to enrich the dataset and improve model performance. The experimental results show that the XGBoost model achieved the highest performance with an accuracy of 0.9499 and a ROC-AUC score of 0.6113, demonstrating superior performance in distinguishing between positive and negative feedback. In comparison, deep learning models such as LSTM and Bi-directional LSTM showed lower ROC-AUC scores, indicating less effectiveness in handling the classification task. This approach offers game developers a reliable and scalable solution for classifying user sentiment, leading to better game improvements based on user reviews.

Sentiment Analysis Of Gojek, Grab, Maxim Applications Using Support Vector Machine Algorithm

This research analyzes user sentiment towards three major online transportation applications in Indonesia—Gojek, Grab, and Maxim using the \SVM algorithm. The analysis results indicate that Maxim has the highest positive sentiment rate (42.45%) compared to Grab (32.83%) and Gojek (20.21%). Maxim's advantages lie in its competitive pricing and driver professionalism. However, Gojek recorded the best performance in sentiment classification with an accuracy of 94%, followed by Maxim (90%) and Grab (87%). The evaluation based on five main variables (general sentiment, drivers, services, applications, and pricing/costs) reveals the strengths of each application in different categories. Maxim excels in general sentiment and driver satisfaction, Grab dominates in pricing/cost, and Gojek stands out in the application category. Wordcloud visualization reveals frequently mentioned words such as "driver," "application," and "order," reflecting users' primary concerns and experiences. This research provides valuable insights for online transportation service providers to improve service quality, although it has limitations in exploring external factors such as user demographics and marketing strategies, as well as relying on a single algorithm without comparison. The choice of the SVM algorithm is based on its ability to handle well-structured data and provide high accuracy in classification. SVM is effective in finding the optimal hyperplane that clearly separates data classes, making it suitable for sentiment analysis involving multiple variables.

Sentiment Analysis of Universitas Jember’s Sister for Student Application Using Gaussian Naive Bayes and N-Gram

This research aims to classify sentiment in reviews of the Universitas Jember Sister for Student application on Google Play Store, a vital student platform. The primary challenge tackled is the automated identification of positive and negative user sentiments. The study employs the Gaussian Naive Bayes method for classification and uses N-Gram techniques for sentiment analysis. The dataset consists of 1097 reviews, with 673 negative and 424 positive reviews, after removing 86 neutral spam reviews. The data is divided into 80% training data (877 reviews) and 20% test data (220 reviews). Gaussian Naive Bayes is used for modeling and combined with TF-IDF vectorization. The findings reveal that the Gaussian Naive Bayes model achieves an accuracy of 68%, precision of 68%, and recall of 71% on the test data. N-Gram analysis shows frequent occurrences of words like "bisa", "bagus", and "aplikasi" in positive sentiments, while "bisa", "hp", and "absen" are prevalent in negative sentiments. The study concludes that the Gaussian Naive Bayes model effectively classifies sentiment in application reviews, with the potential for further performance improvements.

Sentiment Analysis of National Health Security Mobile Application Review Using Machine Learning

It is widely acknowledged that digital transformation provides the opportunity for business process improvements. We can see many businesses, specifically in Indonesia's private and public sectors, leveraging technology to provide better service to their stakeholders. This research seeks insight into stakeholders’ engagement in digital transformation in the Indonesian healthcare system, namely the National Health Security Mobile application (Mobile JKN). This study employs a quantitative method to analyze user sentiment from Google Play reviews. Firstly, user reviews are extracted, preprocessing steps are applied, and machine learning-based sentiment labeling is employed afterward to categorize them into positive, neutral, and negative sentiments. The machine labeling process is carried out in document-level analysis, meaning user reviews represent their overall sentiment. Subsequently, we study the most prominent words using Word Cloud to determine the topics mainly discussed in positive and negative sentiments. The result is that 56.10% of reviews from 7 June 2016 to 14 July 2024 contain positive sentiments, while 43.17% contain negative sentiments. Neutral reviews contribute the most minor proportion, making up only 0.73%. The most prominent words in positive sentiment reviews, such as easy, sound, and helpful, suggest the user perception of the National Health Security Mobile as being easy to use and successfully accommodating the user's needs. In contrast, the words application, update, complex, login, code, verification, register, open, use, and error dominate the negative reviews, indicating users had difficulties logging in and registering user accounts, mainly related to frequent updates and Time Password errors.

Use of Big Data Analytics to Understand Consumer Behavior

The purpose of this study is to investigate the meaning and characteristics of big data and to examine aspects of consumer behavior within the framework of big data research. The results show that although external factors and internal perception are the primary determinants of consumer decision making, big data also affects customer perception through external factors. Data is too large to be handled and analyzed by standard database management system techniques (Latvia_ ESRD 43_2016, n.d.). In order to give their businesses a competitive edge, marketers can use analytics to better understand consumer behavior. This article explores the characteristics of the big data phenomenon (Ramanathan, U., Subramanian, N., Yu, W., & Vijaygopal, R., 2017). Data is gathered from clients who receive business and technical training under controlled conditions. Apart from going over technical aspects like architecture, infrastructure, logic, theory, and environment building, this study will also cover consumer behavior modeling (Erevelles, S., Fukawa, N., & Swayne, L, 2016) The first part of the literature review examines concepts related to trust in consumer behavior. It investigates the psychological foundations of consumer trust as well as the ways in which perceptions of risk, confidence, and trust influence the decision-making process (Sousa, R., & Voss, C., 2012) Furthermore, it runs counter to the idea of empowered firms by highlighting how legitimacy affects consumer trust, brand integrity, and trust. However, it looks at why customers are suspicious of unlicensed services and discusses the problems and reasons behind that mistrust. In (Anshari, M., Almunawar, M. N., Lim, S. A., & Al-Mudimigh, A., 2019). The recommendation engine essentially suggests numerous products based on a variety of factors, such as the user's age and previous purchases. This kind of data filtering technology uses machine learning algorithms to recommend the best products to a particular customer. The purpose of this study is to segment related product reviews and analyze user sentiment in order to create a product recommendation system (Ertemel, A. V., 2015).

A hybrid Hadoop-based sentiment analysis classifier for tweets associated with COVID-19 utilizing two machine learning algorithms: CNN, and fuzzy C4.5

In recent years, research on opinion mining from X (formerly Twitter) has rapidly advanced, focusing on processing tweets to determine user sentiments about events. Many researchers prefer using machine and deep learning techniques for this analysis. This work proposes a novel approach integrating the C4.5 procedure, fuzzy rule patterns, and convolutional neural networks. The approach involves six steps: pre-processing to remove noisy data, vectorizing tweets with word embedding, extracting sentiment and contextual features using convolutional neural networks, fuzzifying outputs with a Gaussian fuzzifier to handle ambiguity, constructing a fuzzy tree and rule base using a fuzzy version of C4.5, and classifying tweets with fuzzy General Reasoning. This method combines the benefits of convolutional neural networks and C4.5 while addressing imprecise data with fuzzy logic. Implemented on a Hadoop framework-based cluster with five computing units, the approach was extensively tested. The results showed that the model performs exceptionally well on the COVID-19_Sentiments dataset, surpassing other classification algorithms with a precision rate of 94.56%, false-negative rate of 5.28%, classification rate of 95.15%, F1-score of 94.63%, kappa statistic of 95.12%, execution time of 11.81 s, false-positive rate of 4.26%, error rate of 4.26%, specificity of 95.74%, recall of 94.72%, stability with a mean deviation standard of 0.09%, convergence starting around the 75th round, and significantly reduced complexity in terms of time and space.

Review Analyzer

This project focuses on leveraging generative AI to analyse user reviews from the Play Store for diverse applications. By utilizing advanced large language models (LLMs), the system processes extensive user feedback to identify key trends, sentiments, and actionable insights. The AI analyses reviews to categorize overall user sentiment (positive, negative, or neutral), highlight recurring issues, and identify popular feature requests. The generative AI’s capabilities enable it to provide nuanced suggestions to developers, such as improving app functionality, addressing common complaints, and implementing features aligned with user preferences. Additionally, the system can generate concise summaries of user reactions, offering developers a clear understanding of their app's strengths and areas needing improvement. This data-driven approach enhances app development by prioritizing updates based on real user needs, improving user satisfaction, and fostering higher ratings on the Play Store. The integration of generative AI streamlines the review analysis process, ensuring actionable recommendations for sustained app success. Key Words: Generative AI, Large Language Models (LLMs), sentiment analysis, App improvement, review analysis 1.INTRODUCTION This project utilizes generative AI to analyze Play Store reviews across various applications, providing developers with actionable insights. By leveraging large language models (LLMs), the system processes user feedback to identify sentiment trends, highlight common issues, and suggest improvements. This approach enables developers to understand user reactions effectively and prioritize updates, ultimately enhancing app quality, user satisfaction, and ratings. The integration of AI streamlines review analysis, ensuring data-driven decisions for better app performance.

Integrating Symmetry in Attribute-Based Sentiment Modeling with Enhanced Hesitant Fuzzy Scoring for Personalized Online Product Recommendations

Online product reviews provide valuable insights on user experiences and product qualities. However, issues such as information overload and the limited utilization of review features persist, particularly in personalized rankings for popular items like movies. To address these challenges—information overload in online reviews, limited review feature utilization, and personalized decision-making for high-demand products like movies—we introduce a personalized online decision-making framework that integrates a sentiment model for product attributes with an enhanced hesitant fuzzy scoring function. This framework incorporates the concept of symmetry in sentiment analysis. It employs feature words, sentiment terms, and modifiers to assess user sentiments within a hesitant fuzzy setting, utilizing symmetrical relationships between positive and negative sentiments. The improved fuzzy score function efficiently quantifies sentiment values for product features by considering the symmetrical balance of user opinions. Additionally, review quality assessment incorporates both content and reviewer characteristics, resulting in final attribute evaluations. An attribute weighting system, tailored to diverse product types, further captures product specifics and user inclinations, leveraging symmetry to balance varying user preferences. Validation through multi-genre movie sorting demonstrates the method’s capacity to handle review data across varied products and user tastes, offering a robust tool for enhancing online decision quality, especially for high-demand items.

Beyond Songs: Analyzing User Sentiment Through Music Playlists and Multimodal Data

Beyond Songs: Analyzing User Sentiment Through Music Playlists and Multimodal Data

The Classification Method is Used for Sentiment Analysis in My Telkomsel

User reviews significantly impact how mobile apps are perceived and provide developers with valuable insights into improving the functionality and quality of their products. Sentiment analysis of these evaluations helps identify the main issues faced by consumers, such as technical difficulties, costs, and service levels. The main objective of this study is to classify user sentiment into positive and negative categories, focusing on the MyTelkomsel app. With the use of Google Play Scraper, 39,493 reviews on various app versions and user experiences were collected. This data was analyzed using multiple machine learning models, including Support Vector Machines (SVM), Naive Bayes, Random Forest, and Gradient Boosting, alongside the Natural Language Processing (NLP) approach. The results show that 39.2% of the reviews are positive, while 60.8% reflect negative sentiment. Among the models, SVM showed the highest accuracy in sentiment classification with a value of (0.854792), while Naive Bayes (0.775541), Random Forest (0.829725), and Gradient Boosting (0.819344) also performed well in sentiment classification. These findings suggest that developers can leverage the insights gained from this analysis to proactively improve the performance and user experience of the MyTelkomsel app, by addressing technical and service-related issues identified in user reviews.

Enhancing digital currency adoption: examining user experiences

PurposeThis study aimed to analyse user experiences and perceptions of eRupee banking applications in India, focussing on understanding the key factors driving user satisfaction and dissatisfaction.Design/methodology/approachA comprehensive text-mining approach was employed to analyse 5,176 user reviews collected from the Google Play Store. Sentiment analysis and latent Dirichlet allocation (LDA) were used to classify reviews and uncover prevailing themes.FindingsThe analysis revealed that positive reviews highlighted the themes of usefulness, convenience, satisfaction, app attributes, and ease of use. Negative reviews emphasise issues related to lack of trust, faulty updates, unreliability, security concerns, and inadequate customer support. The Logistic Regression model demonstrated superior performance in predicting user sentiments, achieving an AUC of 0.7926 and an accuracy rate of 77.90%.Research limitations/implicationsThis study was limited to reviews from a single-platform source. Future research could incorporate data from multiple online sources and employ qualitative methods to gain deeper insight. Additionally, longitudinal studies and cross-cultural analyses are recommended to capture evolving user sentiments and global perspectives.Practical implicationsThe findings provide actionable insights for bank managers, app developers and policymakers to enhance eRupee applications by addressing identified issues and leveraging positive aspects to improve overall user experience and satisfaction.Originality/valueThis study makes a novel contribution to the literature on digital currency and advanced text-mining techniques using machine-learning models to analyse user feedback in the context of an emerging economy. The proposed conceptual model and practical recommendations serve as the foundation for future research and practical development in digital financial services.

Research on aspect-based sentiment analysis of movie reviews based on deep learning

Aspect-based sentiment analysis aims to extract the sentiment polarity of different aspects within a text. In recent years, most methods have relied on pre-trained language models such as BERT and Roberta to learn semantic representations from the context. However, in texts with ambiguous sentiment expression, the absence of domain knowledge guidance may lead pre-trained language models to miss critical information, and the attention mechanism might incorrectly focus on text that is irrelevant to the aspect categories. To address these issues, this study integrates the ontology of movie reviews to construct an aspect-based sentiment analysis model based on the ERNIE(OMR-EBA). We annotated a new Chinese data set focused on movie reviews to evaluate the model’s performance. Experimental results show that our model achieves 86% accuracy in aspectual sentiment analysis, which is better than other baseline models. The movie review domain ontology and aspect-based sentiment analysis model proposed in this study can provide valuable reference and guidance for research in the field of online movie reviews. It can also help movie production teams understand genuine user sentiments, aiding in subsequent marketing and production efforts.

Influencer marketing on Instagram—The optimal disclosure strategy from influencers’ and marketers’ perspectives

This article explores the impact of different advertising disclosure strategies (i.e., explicit sponsorship disclosure, concealing disclosure, impartiality disclosure, and no disclosure) in influencer marketing on influencer-related outcomes (user engagement, user sentiment, and influencer credibility) and marketer-related outcomes (user attitude towards the brand and users’ intention to purchase). We conducted two field experiments and an online survey with an experimental design in collaboration with an active micro-influencer on Instagram. The results of the studies indicate that from a marketers’ perspective, it is best when influencers promote products as genuine recommendations and use impartiality disclosure. From an influencer’s perspective, the optimal disclosure strategy depends on whether the influencer seeks to improve engagement with their content or their levels of credibility. When influencers’ primary focus is to increase engagement, if they provide information on sponsorship or non-sponsorship, they do not have to worry about decreasing engagement rates due to the employed disclosure strategy. Suppose influencers’ goal is to increase their credibility. In that case, it depends on their content (whether it is rich in genuine recommendations or sponsored content) and the group they want to target—i.e., if they seek to target followers versus non-followers.

Communication Mechanism and User Sentiment Analysis of Public Emergencies on Social Media: A Case Study of the Wenzhou Doctor-Patient Dispute on July 19

This study aims to explore the communication mechanism and user sentiment analysis of public emergencies in social media. Taking the doctor-patient dispute in Wenzhou, China on 7.19 as an example, the study systematically analyses the dissemination path, speed, influence and user sentiment changes of the incident in social media, and through data collection and analysis, the study reveals that the incident Through data collection and analysis, the study reveals the evolution of the incident on social media platforms from the initial release of information, to the buzz of discussion, to the decline of public opinion. The study also adopts a comparative analysis method, comparing the doctor-patient dispute in Wenzhou with the Tangshan man-beating incident, to analyse the differences between the two incidents in terms of speed of dissemination, duration, and users' emotions, and to further explore the characteristics of the dissemination of social emergencies and the influencing factors in the social media. This study provides theoretical support for monitoring and guiding public opinion in social media, and proposes strategies to effectively respond to public opinion crises.

Comparison of Naive Bayes and SVM Algorithms for Sentiment Analysis of PUBG Mobile on Google Play Store

PlayerUnknown's Battlegrounds (PUBG) Mobile is one of the most popular mobile games in Indonesia, according to data from the Google Play Store. According to the Google Play Store, the game has a rating of 3.8 with 49.5 million reviews. While a considerable number of users express satisfaction, a significant proportion of reviews also contain criticism regarding the gameplay and features. However, a cursory examination of reviews may not fully capture the nuances of user sentiment, necessitating a more comprehensive sentiment analysis. This research will employ a positive and negative sentiment analysis of Indonesian PUBG Mobile reviews on the Google Play Store, utilizing a comparative approach to evaluate the performance of two algorithms: Naïve Bayes and Support Vector Machine (SVM). The data set comprised 2,000 user reviews, which were collected using a scraping technique. Following this, a labeling process was conducted based on the rating, data were preprocessed, TF-IDF weighting was applied, and both algorithms were implemented. The findings indicated that users expressed satisfaction with the game's visuals and gameplay. However, there were also technical concerns that required attention, including bugs, server instability, lag, and performance issues. The SVM algorithm demonstrated superior performance, with an accuracy rate of 70.95%, compared to Naïve Bayes, which reached 69.83%. Despite Naïve Bayes's faster processing speed, SVM exhibited greater precision, recall, and F1-score

Sentiment Analysis on Social Media: Investigating Users' Perceptions of MRT and LRT Transportation Services

Providing excellent public transportation in response to the passenger’s complaints and recommendations results in long-term improvements to the service. This study investigates public perceptions of the MRT and LRT rail transportation services within the Klang Valley Integrated Transit System, operated by Rapid KL, through sentiment analysis in X. With 4.4 million users in Malaysia as of January 2022, X (previously Twitter) media social serves as a significant platform for public discourse. However, analyzing these perceptions poses challenges due to the limited platforms for analysis, and seeking from X is even more challenging due to the unstructured and noisy nature of the tweets. Therefore, this study aims to develop a sentiment analysis model that organizes tweets into structured data, utilizing machine learning techniques for sentiment classification into positive, neutral, and negative categories. Following the model implementation, the data are collected, translated, cleaned, labeled, analyzed, and classified using a Support Vector Machine before being deployed in a web system for ease of access. Analysis results revealed that user sentiment is predominantly neutral, with a significant focus on MRT services and topic finding related to scheduling. The model scored good accuracy 80% without a kernel and 84% with a Linear kernel, with evaluation metrics demonstrating strong performance on all three sentiment categories. Future enhancements will include label refining and applying more hyperparameter tuning to improve analysis accuracy.

Semantically-Informed Graph Neural Networks for Irony Detection in Turkish

Social media plays an important role in expressing the thoughts and sentiments of users. Irony is a way of stating a sentiment about something by expressing the opposite of the intended literal meaning. Irony detection is a recent emerging task in low-resource languages, although other tasks related to sentiment, such as sentiment analysis and emotion detection, have been widely tackled. In this study, we investigate Graph Neural Networks (GNNs) for irony detection in Turkish, a low-resource language in sentiment-related tasks. We incorporate semantic information into the GNNs using the Universal Conceptual Cognitive Annotation (UCCA) framework. Extensive experimental results and in-depth analysis show that our models outperform state-of-the-art irony detection models in Turkish. Our UCCA-GAT (UCCA-Graph Attention Network) model achieves an F 1 -score of 94.85% (7.362% gain over the state-of-the-art) on the Turkish-Irony-Dataset and an accuracy of 72.82% (4.39% gain over the state-of-the-art) on the IronyTR Dataset. We also provide a comprehensive analysis of the proposed models to understand their limitations.

ANALISIS SENTIMEN PENGGUNA PADA APLIKASI BANK DIGITAL KROM DENGAN ALGORITMA SUPPORT VECTOR MACHINE

The rapid development of financial technology has driven the widespread adoption of digital banking applications, including the KROM app, among the public. This study aims to analyze user sentiment toward the KROM Digital Bank application using the Support Vector Machine (SVM) algorithm. User review data was collected from Google Play, then processed through data preprocessing steps such as text cleaning, tokenization, and removing irrelevant words. The SVM algorithm is used to classify user sentiment into positive and negative categories. The results indicate that SVM performs well in classifying user sentiment, with an accuracy of 84,38%. This analysis is expected to provide insights for app developers to improve service quality based on user perceptions and experiences.

Sentiment Analysis of Online Vehicle Tax Renewal Application Users Using Support Vector Machine Algorithm

This study examines user sentiment towards online vehicle tax renewal applications by utilizing the Support Vector Machine (SVM) algorithm. The data was collected from user reviews on the Google Play Store for three major applications: New Sakpole, Sapawarga, and Timsalut. The reviews were preprocessed through steps including normalization, case folding, tokenization, and stopword removal. The SVM algorithm was then applied to classify the reviews into positive or negative sentiments. A comparative analysis was performed with K-Nearest Neighbors (KNN) and Naïve Bayes, with SVM demonstrating the best performance, achieving an accuracy of 76.5%. In addition to accuracy, metrics such as precision, recall, and F1-score were also evaluated to provide a more comprehensive assessment of the models. The results indicate that while these applications help facilitate vehicle tax payments, there remains significant user dissatisfaction, particularly related to technical issues and usability concerns. This study offers valuable insights for application developers, highlighting areas for improvement in functionality and user experience to better meet public expectations.

Discovering User Sentiment Patterns in Libraries with a Hybrid Machine Learning and Lexicon-Based Approach

The need to enhance library services is the focus of this study, which relies on user feedback for data-driven decision-making. Text data from library user surveys conducted at Politeknik Caltex Riau (PCR) is analyzed to categorize sentiment and identify areas for improvement. The biannual student and lecturer feedback collected from 2018 to 2023 through the institution's official survey system (survey.pcr.ac.id) is utilized, providing a comprehensive and robust picture of user needs across five years. Sentiment analysis is employed using the VADER method to classify user comments into positive or negative categories. Text preprocessing techniques, such as stemming, tokenizing, and filtering, are performed to ensure robust classification. Machine learning algorithms – Naïve Bayes, Support Vector Machine (SVM), and Random Forest – are then utilized to evaluate sentiment classification accuracy. The study offers significant findings. Both SVM and Random Forest achieve an outstanding accuracy of 99%, indicating highly reliable sentiment categorization. Notably, these algorithms also achieve 100% precision, recall, and F1-score, demonstrating their effectiveness in accurately identifying positive and negative user sentiment. While Naïve Bayes shows slightly lower accuracy at 98%, it maintains a high recall rate (100%), ensuring all negative feedback is captured. This research presents a novel approach combining user sentiment analysis with a comprehensive five-year dataset. This enables a deeper understanding of evolving user needs and priorities. The high accuracy and effectiveness of the employed algorithms highlight the potential of this methodology for libraries. Libraries can leverage user feedback for evidence-based service improvement and increased user satisfaction.