Publication Search

This study is titled Analysis of the Incumbent's Defeat in the 2024 Regional Head Election in East Flores Regency (A Study of Antonius Hubertus Gege Hadjon's Defeat in East Adonara District), with the aim of analyzing the factors that led to the defeat of incumbent Antonius Hubertus Gege Hadjon in the 2024 Pilkada. This study uses Pierre Bourdieu’s political modality theory, including political, social, economic, and cultural capital. A qualitative approach with a descriptive method is employed, and data is collected through interviews with subjects consisting of the incumbent candidate, a religious leader, a youth leader, a community leader, two party representatives, and the success team. The study focuses on the support base in East Adonara District. The results of the study indicate that the incumbent's defeat was caused by the weakening of political capital, especially due to the vacancy in the regent’s position for two and a half years, which strengthened the opponent's position. This caused stagnation in public services and a decrease in the intensity of local government communication. In addition to these structural factors, weak internal party consolidation and public sentiment about uneven development also contributed to the defeat, indicating the incumbent's failure to manage his political capital amidst the dynamics of governance.

This study analyzes the economic phenomenon known as the "Purbaya Effect" in the Indonesian capital market during the second half of 2025. This phenomenon is characterized by a significant surge in the Jakarta Composite Index (IHSG), which broke the All-Time High (ATH) record 21 times within four months following the appointment of Purbaya Yudhi Sadewa as Minister of Finance. Using a mixed-methods approach combining quantitative market data analysis and qualitative policy review, this research finds that the "Purbaya Effect" is driven by aggressive liquidity injection policies (Rp 200 trillion), institutional trust built during his tenure at LPS, and strong narrative economics. However, this study also identifies significant risks related to exchange rate volatility and potential economic overheating. The findings suggest that while the "Purbaya Effect" successfully restored short-term investor confidence, long-term sustainability depends on the balance between growth acceleration and macroeconomic stability.

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

Budget efficiency is an important issue in state financial management because it is directly related to government spending priorities and their impact on public service programs. Discussions about budget efficiency policies are widespread on social media platform X, generating diverse public responses, thus necessitating an automated approach to understand public opinion trends more quickly and objectively. This research aims to analyze the sentiment of Indonesian people toward budget efficiency policies and compare the performance of the Naïve Bayes and Support Vector Machine (SVM) algorithms in classifying sentiment. The research data used 10,909 Indonesian-language tweets sourced from a public dataset, which were then processed thru the preprocessing stages including cleaning, case folding, normalization, tokenization, stopword removal, and stemming. Sentiment labeling is performed automatically using the Indonesian Sentiment Lexicon (InSet) approach to categorize data into positive, negative, and neutral sentiments. Feature extraction was performed using Term Frequency–Inverse Document Frequency (TF-IDF), and then the data was divided into training and testing sets with an 80:20 ratio. Model performance evaluation was conducted using a confusion matrix and the metrics of accuracy, precision, recall, and F1-score. The research results show that sentiment distribution is dominated by negative sentiment at 56.78%, followed by positive sentiment at 37.40%, and neutral sentiment at 5.83%. In the classification stage, SVM performed best with an accuracy of 86%, while Naïve Bayes achieved an accuracy of 74%. These findings indicate that SVM is more optimal for sentiment classification on social media text data and can be utilized to more effectively support the analysis of public response to budget efficiency policies.

This study conducts sentiment analysis of Indonesian user reviews of the CapCut application using IndoBERT and compares two evaluation schemes: a single 80/20 train–test split and stratified 5-fold cross-validation (k=5). A total of 1,048,575 reviews were collected from the Google Play Store through web scraping and labeled into three sentiment classes based on rating: negative (1–2), neutral (3), and positive (4–5). After preprocessing—cleaning, case folding, banned-word removal, normalization—and duplicate removal, 517,962 reviews were retained. IndoBERT Base P1 was fine-tuned using fixed hyperparameters (batch size 32, learning rate 2e-5, up to 4 epochs, early stopping patience 2), while undersampling was applied to the training set to address class imbalance. Performance was assessed using accuracy, precision, recall, F1-score, and ROC-AUC, supported by confusion matrix and ROC-curve visualizations. The single split achieved an accuracy of 0.756, whereas cross-validation produced a mean accuracy of 0.740. Across both schemes, the positive class achieved the best performance (F1-score 0.850; ROC-AUC 0.918–0.919), while the neutral class remained the most challenging (precision 0.198–0.206; F1-score 0.280–0.283). Overall, cross-validation is recommended for reporting because it reduces dependence on a single partition and provides a more representative estimate across multiple splits.

The rapid growth of e-commerce platforms in Indonesia, particularly Tokopedia, has resulted in a large volume of consumer reviews containing valuable information regarding customer perceptions and satisfaction. However, manual analysis of such reviews is inefficient and prone to subjectivity, necessitating an automated approach based on machine learning. This study aims to classify the sentiment of sports product reviews on Tokopedia into positive, negative, and neutral categories by applying Logistic Regression, Support Vector Machine (SVM), and Random Forest using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. The data were collected through web scraping of Indonesian-language sports product reviews and processed through several preprocessing stages, including data cleaning, case folding, tokenization, stopword removal, and stemming. Feature representation was performed using TF-IDF to transform textual data into numerical vectors, after which the dataset was divided into training and testing sets with an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the application of TF-IDF significantly improves the performance of all models, with SVM consistently achieving the most optimal performance compared to Logistic Regression and Random Forest. These findings demonstrate that classical machine learning algorithms combined with TF-IDF remain highly effective for sentiment analysis of Indonesian-language text. The implications of this study are expected to assist sellers in understanding customer opinions, support consumers in making informed purchasing decisions, and serve as a foundation for the development of sentiment analysis and recommendation systems on e-commerce platforms.

The Ministry of Social Affairs has made a new breakthrough in facilitating the public in checking social assistance recipients, namely the social assistance check application. User reviews can be used to find out whether the application provides benefits to the community or not. However, these reviews need to be processed using sentiment analysis. Then to do sentiment analysis requires machine learning. One method that includes machine learning is Naïve Bayes. The purpose of this research is to implement the Naïve Bayes method in conducting sentiment analysis and find out whether the social assistance check application is beneficial to society based on the results of sentiment analysis. In this study, two categories of sentiment are used, namely positive and negative. The author collects by crawling using the Google Play Scrapper library. The results of crawling data obtained as many as 4000 data. The results showed that the actual data that had been labeled using Textblob resulted in 987 negative label reviews and 628 positive label reviews. Meanwhile, the Naïve Bayes method is able to analyze the review sentiment of the social assistance check application with the results of 1181 negative sentiments and 434 positive sentiments. The Naïve Bayes model has a good accuracy rate of 0.77 or 77% in analyzing sentiment for social assistance check application reviews.

The growth of e-commerce in Indonesia has led to an increase in product reviews, including for beauty products on Tokopedia and Shopee. These reviews serve as important sources of information to assess consumer satisfaction; however, manually analyzing thousands of reviews daily is impractical. This study applies Natural Language Processing (NLP) with Naive Bayes, C4.5, XGBoost algorithms to classify sentiment in Indonesian-language reviews. The dataset used consists of 76,256 reviews labeled as positive, negative, and neutral. The research stages include text preprocessing, feature representation using BoW and TF-IDF, data balancing through SMOTE, and model performance evaluation based on accuracy, precision, and recall. Differences in results among the algorithms were analyzed using ANOVA. The results show that Naive Bayes achieved the highest accuracy at 67.71%, followed by XGBoost at 65.91%, and C4.5 at 58.39%, with Naive Bayes performing best in identifying positive and negative sentiments, while XGBoost and C4.5 handled more complex data patterns effectively. These findings provide guidance for sentiment analysis in Indonesian and support businesses in obtaining automated insights from customer reviews to improve product quality and services.

Sentiment analysis is a technique in Natural Language Processing (NLP) used to identify user opinion tendencies based on textual reviews. This study analyzer user reviews of the Maxim application on the Google Play Store and compares three Machine Learning algoritmhs-Naïve Bayes, Support Vector Machine (SVM), and CatBoost-in classifying sentiment. The research stages include data collection, text preprocessing, feature extraction using TF-IDF and Chi-Square, class balancing using SMOTE, and performance evaluation through Accuracy, Precision, Recall, and F1-Score. ANOVA is used to examine the influence of feature selection on model performance. The results show that each model exhibits different performance level across the tested feature combinations. The CatBoost achieved the highest accuracy of 99,26% and demonstrating the most stable performance. Meanwhile, the Naïve Bayes and SVM models experienced performance decreases experiments, especially after applying SMOTE. These findings indicate that the choise of algorithm, feature extraction method, and class balancing technique significantly affects classification outcomes. Overall, CatBoost is identified as the best-performing model, providing more consistenst classification result in accordance with the characteristics of the user reviews.

Abstract: The rapid diffusion of Generative Artificial Intelligence (AI) has intensified public debate regarding its benefits, risks, and societal implications. This study investigates public sentiment and thematic structures surrounding Generative AI by analyzing Twitter discourse as a representation of large-scale, real-time public perception. The research addresses two main problems: how public sentiment toward Generative AI is distributed and what dominant themes shape this perception. Accordingly, the objective is to map both emotional polarity and thematic narratives embedded in social media conversations. A computational mixed-methods approach was employed using a dataset of 12,470 tweets collected on 17 December 2024. Sentiment classification was conducted using a transformer-based DistilBERT model, while semantic representations were generated with Sentence-BERT. Topic modeling was performed using BERTopic, integrating HDBSCAN clustering and class-based TF-IDF to extract coherent and interpretable topics. Human-in-the-loop validation supported the interpretive robustness of topic labeling. The findings reveal that public sentiment toward Generative AI is predominantly positive (41.8%), particularly in relation to productivity enhancement, education, and creative applications. Neutral sentiment (31.4%) reflects informational discourse, while negative sentiment (26.8%) centers on ethical concerns, privacy risks, misinformation, and AI hallucinations. Seven dominant topics were identified, with clear topic–sentiment alignment showing optimism in utility-driven themes and skepticism in ethics- and risk-related discussions. In conclusion, public perception of Generative AI is dualistic—characterized by strong enthusiasm alongside persistent caution. These results provide empirical insights for AI governance, responsible innovation, and future research on socio-technical impacts of Generative AI. *    

The development of social media platforms like TikTok has created new spaces for digital economic activities, including the practive of thrifting, which has now become a trend among the public. However, government policies that block these activities have sparked various public reactions. This study aims to analyze public sentiment regarding the issue of thrifting bans on the TikTok platform using the Bidirectional Long Short-Term Memory (Bi-LSTM) method. This method was chosen because it can understand text context from both directions, allowing it to capture deeper semantic meaning. The dataset consist of 4,000 TikTok user comments collected through a crawling process. The research stages include data preprocessing, sentiment labeling, splitting training and test data, training the Bi-LSTM model, and evaluating performance using accuracy, precision, recall, and F1-score metrics. The research results show that the Bi-LSTM model achieved an accuracy of 86.15%, with stable classification performance and minimal error rate. These findings indicate that Bi-LSTM is effective for sentiment analysis of public opinions on Indonesian language social media, particularly on context specific policy issues. Further development can be carried out by adding pre-trained embeddings or attention mechanisms to improve the model’s performance.

In the investment world, stock returns are the leading indicator of a company’s performance and the basis for investor decision-making in the capital market. Fluctuations in stock returns reflect market expectations of the company’s prospects. The retail sector in Indonesia is facing significant pressure from post-pandemic shifts in consumer behavior and increased competition. This study aims to analyze the effect of financial distress, company size, liquidity, operating cash flow, and accounting profit on stock returns in retail sub-sector companies listed on the Indonesia Stock Exchange (IDX) during the period 2021 to 2023. This type of research is causally associated with a quantitative approach. The data used is secondary, in the form of financial statements from retail companies. The sampling technique used was purposive, yielding a total of 39 data points from 13 retail companies. Data testing was carried out using SPSS version 24. The results showed that partially, the variables of financial distress, company size, liquidity, and accounting profit had no significant effect on stock returns. Meanwhile, operating cash flow positively impacts stock returns. These findings indicate that fundamental indicators are not always the main determinants of stock returns. Therefore, investors are advised also to consider external factors such as market sentiment, macroeconomic conditions, and government policies that may have a greater influence on stock performance in the capital market.

This research examines the analysis of Return on Equity (ROE), Quick Ratio (QR), and Debt to Equity Ratio (DER) on corporate valuation, as assessed by Price-to-Book Value (PBV), within technology firms listed on the Indonesia Stock Exchange (IDX) during the period from 2022 to 2024. The primary aim of this investigation is to ascertain the effects of profitability, liquidity, and leverage both in isolation and in conjunction on market valuation in an industry characterized by innovation and intangible assets. This research employs panel data regression analysis utilizing EViews 13 as the quantitative methodology. The findings reveal that ROE significantly enhances PBV, indicating that investors place considerable importance on firms that are capable of generating substantial returns on equity for shareholders. Conversely, QR and DER appear to have no discernible impact on PBV. This observation can be attributed to the unique nature of technology companies, wherein investors prioritize factors other than short-term liquidity and leverage. Nonetheless, when assessed collectively, the three metrics illuminate the variations in corporate value. These results suggest that while financial stability indices exert a positive yet comparatively subdued effect on investor sentiment within the technology sector, profitability remains a paramount determinant. The study elucidates the financial determinants that influence corporate value in innovation-driven industries, providing valuable insights for managers and investors alike.

Sugar consumption in Indonesia remains high, with diabetes affecting 20.4 million people. This condition has prompted the government to introduce an excise policy on Minuman Berpemanis Dalam Kemasan (MBDK) to reduce sugar intake. Social media, particularly the X platform, serves as a medium for the public to express their opinions regarding this policy. This study aims to analyze public sentiment toward the MBDK excise policy using a lexicon-based approach for data labeling and the Multinomial Naive Bayes algorithm with unigram and bigram feature extraction. The initial results show that the highest performance was achieved using 5-Fold Cross Validation, with an average accuracy of 83%, precision of 84%, recall of 75%, and an F1-Score of 77%. After applying data balancing using Stratified Cross Validation combined with Borderline-SMOTE and limiting the features to the 700 most frequent terms, the model’s performance improved. The best results were obtained with 10-Fold Cross Validation, achieving 86% accuracy, 84% precision, 83% recall, and an F1-Score of 83%. These findings indicate that the Multinomial Naive Bayes model can effectively classify public sentiment regarding the MBDK excise policy after the data balancing process.

The rapid expansion of e-commerce in Indonesia has resulted in a significant rise in the number of customer reviews, which serve as a valuable source of insight for understanding consumer satisfaction. This study aims to classify or identify sentiments from product reviews on the Tokopedia platform into three categories, using the Support Vector Machine algorithm. The classification method data were ethically collected through web scraping and include review text, ratings, and the number of “likes.”  The preprocessing stage involved several NLP techniques such as pre-procesesing data representation was generated using the Term Frequency–Inverse Document Frequency method, while the issue of class imbalance was addressed using the Synthetic Minority Over-sampling Technique.  Based on the test results, the SVM model achieved an accuracy of 79.48% on the test data using a linear kernel, showing the best performance in classifying positive sentiments. However, the classification of neutral and negative sentiments still requires improvement. This study demonstrates that the combination of the TF-IDF method, additional numerical features, and data balancing techniques can produce an an efficient sentiment analysis model within the e-commerce domain.

This study aims to analyze user sentiment toward the integration of Artificial Intelligence (AI) in online learning platforms, which are increasingly expanding in the digital era. With the growing use of AI technologies in education—such as learning chatbots, material recommendation systems, and automated assessments—it is essential to understand users’ perceptions and reactions to these implementations. The research employs sentiment analysis based on text mining using user review data collected from various online learning platforms. The analysis process includes data preprocessing, sentiment classification using machine learning algorithms, and interpretation of results based on the proportion of positive, negative, and neutral sentiments. The findings indicate that most users express positive sentiments toward AI integration, as it enhances learning efficiency and personalization. However, some users raise concerns regarding data privacy and the lack of human interaction. This study is expected to serve as a reference for educational platform developers to design AI systems that are more adaptive, transparent, and user-centered

This study examines the stock market reaction to the Christmas and New Year holidays by analyzing abnormal return and trading volume activity for companies consistently listed in the LQ45 Index during 2021–2023. Using a quantitative causal approach and an event study design, the research observes market behavior within a 10 day estimation window and a 10 8day event window surrounding the holiday period. The findings show that abnormal return exhibits limited but notable reactions, with a significant decline observed before the holiday, indicating that investors tend to reduce risk exposure prior to market closure. After the holiday, significant movements still appear, but they remain negative, suggesting that investor activity and confidence have not fully recovered. In contrast, trading volume activity does not show significant differences either before or after the holiday, implying that changes in prices are influenced more by sentiment and price adjustments rather than shifts in trading intensity. These results indicate that the Indonesian capital market demonstrates characteristics of a semi-strong form efficiency, where public information such as national holidays is largely anticipated and absorbed by the market.

The revocation of Pinkflash's cosmetic product distribution license by the Food and Drug Supervisory Agency (BPOM) has once again attracted public attention after the brand experienced a similar incident in 2024. This crisis raises questions about Pinkflash's public relations strategy in maintaining consumer trust and preserving its brand reputation. This study aims to analyze Pinkflash's public relations strategy and measure the impact of the crisis on public perception through social media sentiment analysis using Brand24. The research method used is a descriptive qualitative approach. The main data in this study was obtained from official documents by BPOM and official brand statements, which were then analyzed using content analysis and sentiment analysis using Brand24. The results of the study show that Pinkflash's crisis response only temporarily dampened negative sentiment. The root of the problem lies in weak governance, which led this study to conclude that reputation can only be rebuilt through comprehensive improvements to the quality of its systems and supply chain, with a commitment to honest operations as the key.

This study aims to implement an information retrieval system for cryptocurrency data using an attribute-based approach integrated with the Vector Space Model (VSM). The primary objective is to develop a system capable of retrieving the most relevant digital asset information according to specific search attributes, including positive sentiment, price fluctuation, and prediction confidence level. The research adopts a descriptive qualitative method combined with an experimental approach to evaluate the retrieval performance of the cosine similarity algorithm on normalized numerical data. Data preprocessing and attribute weighting were conducted to ensure consistency and improve retrieval accuracy. The experiment demonstrates that the proposed system achieves a Precision@5 value of 1.0, which indicates that all top-five retrieved results are fully relevant to user queries. These findings validate the effectiveness of the attribute-based VSM in analyzing multidimensional cryptocurrency datasets. Overall, this research contributes to the advancement of information retrieval applications in the cryptocurrency domain, particularly for supporting data-driven decision-making and intelligent financial analysis.

This research is inspired by the extraordinary success of the domestic animated film titled Jumbo, which managed to set a new record and trigger a wave of overwhelmingly positive sentiment responses on the Instagram social media platform. Its main focus is to provide a deep qualitative interpretation of audience sentiment data that was previously collected and quantitatively evaluated by Prasetia (2025) from 764 original comments, which were then filtered down to 221 samples. The approach applied involves secondary data analysis by reviewing the frequency of Prasetia's data through the lens of social identity theory and collective efficacy theory. The results of the analysis reveal that the prevalence of positive sentiment at 68.7% does not merely reflect a simple evaluation of the film but also serves as a fundamental expression of shared pride and in-group preference. Expressions of support that emphasize appreciation for the achievement and national pride over the work of local creators act as a tool for strengthening social bonds, reinforcing the national identity linked to achievements in the film sector while also demonstrating the audience's collective belief in the potential of the domestic animation industry (mastery experience). Practically, the recommendation for local film promotion strategies is to highlight narratives about shared accomplishment and national pride to build audience loyalty and continuous interaction in the digital environment.