Publication Search

Political disinformation has become one of the most critical challenges in contemporary digital democracies due to the rapid expansion of social media ecosystems. This study investigates the effectiveness of machine learning approaches in detecting political disinformation across online platforms such as Twitter, Facebook, and political discussion forums. Using a qualitative research design with a content analysis approach, the study examines linguistic manipulation, emotional narratives, sentiment polarity, and behavioral communication patterns embedded in misleading political content. The findings indicate that deep learning models, particularly Long Short-Term Memory (LSTM) architectures, demonstrate superior performance in identifying contextual and semantic inconsistencies compared to traditional machine learning algorithms. The study also reveals that algorithmic amplification, echo chambers, and coordinated bot activities significantly contribute to the rapid spread of political misinformation. Furthermore, the research highlights the importance of ethical artificial intelligence governance, transparency, and digital literacy in strengthening democratic resilience and protecting information integrity within digital communication environments

The development of digital services by BPJS Ketenagakerjaan through the JMO (Jamsostek Mobile) application has triggered a surge in large-scale and unstructured user reviews on the Google Play Store, thereby complicating manual analysis and conventional sentiment analysis in accurately identifying specific issues. This research aims to implement the Aspect-Based Sentiment Analysis (ABSA) method to granularly evaluate JMO application reviews based on specific aspects, while simultaneously addressing class imbalance and computational efficiency issues. The proposed method combines the pretrained IndoBERT model as a contextual feature extractor, the SMOTE technique to balance the training data, and an artificial neural network (Neural Network) as the classification layer without performing full fine-tuning. The dataset used consists of 90,268 unique reviews categorized into five main aspects through keyword matching, namely General Satisfaction/Complaints, Performance & Stability, Service & Support, Feature Quality, and UI/UX, with initial lexicon-based labeling using the InSet Lexicon. The research results indicate that the proposed model successfully achieves highly optimal performance with an accuracy rate of 91.81% and a weighted F1-score of 92%. Furthermore, the implementation of SMOTE proved effective in enhancing model reliability on the minority class (negative sentiment), achieving an F1-score of 89%. The implications of this research contribute an accurate and efficient aspect-based sentiment analysis framework for developers, and serve as a strategic evaluation tool for BPJS Ketenagakerjaan in mapping specific user complaints to accelerate continuous improvements in the performance, stability, and service quality of the JMO application.

Document-level sentiment analysis assigns a single polarity label to an entire review, often obscuring opinion diversity within multi-sentence submissions. This limitation is particularly evident in reviews of multi-service platforms, where users frequently express heterogeneous opinions toward different aspects of the platform in the same review. To address this challenge, this study proposes a sentence-level sentiment analysis framework for Indonesian Gojek app reviews collected from the Google Play Store. The proposed framework introduces a two-stage segmentation strategy that combines punctuation-aware rules with conjunction-aware splitting based on coordinating and adversative conjunctions (e.g., tapi [but], padahal [even though]) to identify opinion boundaries and decompose mixed-sentiment reviews into independently classifiable sentence units. A total of 14,730 raw reviews collected between May and July 2025 were subjected to data cleaning and quality filtering, resulting in 7,187 valid reviews that were further segmented into 14,187 sentence-level instances. Each instance was manually annotated by three annotators using a four-class labeling scheme consisting of app-positive, app-negative, app-neutral, and service categories. Sentiment-level inter-annotator agreement, computed on the subset of instances unanimously categorized as app-related by all three annotators (n = 4,384), achieved substantial agreement (Fleiss'  = 0.636). Hyperparameter optimization was conducted using Optuna with the Tree-structured Parzen Estimator (TPE) sampler across four experimental scenarios. The best performance was achieved by IndoBERTweet under Stratified K-Fold evaluation, attaining an accuracy of 0.751 and a macro F1-score of 0.729, outperforming all IndoBERT configurations. The results demonstrate the effectiveness of domain-adaptive pre-training on informal Indonesian text and highlight the value of conjunction-aware segmentation for preserving fine-grained opinion structures in mixed-sentiment reviews. These findings suggest that domain-aligned language representations provide a practical and effective solution for sentence-level sentiment analysis of Indonesian app reviews.

The Free Nutritional Meal Program (MBG) is a government policy that is widely discussed by the public through social media, especially TikTok. Various comments that have emerged indicate differences in public opinion towards the program, so an analysis is needed to determine the tendency of public sentiment. This study aims to analyze TikTok user sentiment towards the Free Nutritional Meal Program using the Naive Bayes method. The research method is carried out through several steps, namely collecting TikTok comment data, preprocessing text, labeling sentiment data into positive, negative, and neutral, feature transformation using TF-IDF, and classification using the Naive Bayes algorithm. Based on the analysis of 500 comment data, the results show that positive sentiment dominates public opinion by 42% (210 data), followed by negative sentiment by 36% (180 data), and neutral sentiment by 22% (110 data). Testing the classification model using Naive Bayes produces excellent performance with an accuracy rate of 86%, precision of 84%, recall of 85%, and F1-score of 84%. The conclusion of this study shows that the Naive Bayes method is effective as an approach in social media sentiment analysis to map public responses to government policies.

Nature tourism is one of the sectors that plays an important role in supporting the development of regional tourism, including in Lahat Regency, which has significant waterfall tourism potential. Currently, many visitors share their reviews and experiences through digital platforms such as Google Maps. This review can be used as a source of information to understand the public's evaluation of the quality of tourist attractions. This study aims to examine public perception of tourist attractions in Lahat Regency using the Support Vector Machine (SVM) method. Research data were collected through scraping from Google Maps, totaling 500 reviews from five tourist attractions, namely Curup Maung, Curup Buluh, Senyawe Waterfall, Panjang Waterfall, and Green Canyon. The research stages include data preprocessing, consisting of cleaning, case folding, normalization, tokenization, stopword removal, and stemming. After that, feature extraction was carried out using the TF-IDF method and the classification process using the SVM algorithm. Based on the research results, the Support Vector Machine (SVM) method is able to perform sentiment classification quite well, although the accuracy level varies for each tourist attraction. Curup Maung and Panjang Waterfall achieved the highest accuracy level of 90%. Nevertheless, most visitor reviews were dominated by negative sentiments. This indicates that there are still several aspects that need to be improved, particularly related to tourist facilities and services. This research is expected to serve as a consideration for tourism managers and local governments in efforts to improve management quality as well as the development of tourism in Lahat Regency.

This study analyzes netizen sentiment concerning the 17+8 public aspirations circulating the digital platform X spanning the period from August 18 through October 31, 2025. 1,837 comments obtained through scraping method. Classification Research stages include data preprocessing, sentiment weighting based on lexicon, and feature extraction using TF-IDF. Data 80% used for learning purposes and the remaining 20% utilized for validation. The findings reveal that the majority of comments, amounting to 81.14%, contained negative sentiment, while the remaining 18.86% were positive. The outcomes demonstrate that community reactions toward the 17+8 People's Demands were dominated by unsupportive views. From a theoretical standpoint this scholarly work offers to enriching knowledge concerning public opinion classification on political issues through a computational approach, while also serving as a reference for future research focused on improving the accuracy of sentiment analysis related to political dynamics and the behavior of state institutions.

QRIS (Quick Response Code Indonesian Standard) has become a widely used national digital payment standard. User satisfaction with this service needs to be monitored continuously to ensure its sustainability. This study aims to predict the level of QRIS user satisfaction based on their experiences and perceptions expressed organically on the Twitter social media platform. The method used is sentiment analysis with the Naive Bayes classification algorithm implemented using RapidMiner software. The research data was obtained from Twitter user comments collected through web scraping techniques. The text data then went through a preprocessing stage that included cleansing, stopword filtering, stemming, and tokenizing to be prepared as features ready to be processed by the model. The data was divided into training (80%) and testing (20%) subsets for model training and validation. The results showed that the Naive Bayes model was able to predict user satisfaction sentiment with an accuracy of 80.99%. These findings indicate that the model is highly accurate in identifying satisfied comments and sufficiently sensitive in detecting dissatisfaction. This study concludes that sentiment analysis of Twitter UGC data using Naive Bayes is an effective and efficient approach for predicting QRIS user satisfaction in real time. The practical implication of this study is to provide an automatic feedback system for service providers to monitor public sentiment and take targeted corrective actions.

This study aims to analyze public sentiment toward the hashtag #KaburAjaDulu, which has circulated widely on the social media platform X (formerly Twitter). The hashtag reflects the growing anxiety among the public, especially younger generations, regarding socio-political issues in Indonesia. The data were collected using web scraping techniques, focusing on user-generated tweets that contain the hashtag. A comprehensive text preprocessing phase was conducted to clean the raw data by removing irrelevant elements such as URLs, emojis, numbers, and punctuation. The research applies a hybrid classification approach using a combination of Support Vector Machine (SVM) and Random Forest algorithms to categorize sentiment into three classes: positive, negative, and neutral. The performance of the model was evaluated using metrics such as accuracy, precision, recall, and F1-score to determine the effectiveness of the classification. The study aims to demonstrate that combining algorithms can improve classification performance compared to using a single algorithm. This research contributes to the field of sentiment analysis and provides valuable insights for researchers, policymakers, and social observers in understanding public opinion trends in digital media.

Social media X (Twitter) has become the main platform for the Indonesian public to express opinions, including on the trend of 'kabur aja dulu' (let's just run away for a bit). This research aims to classify the sentiments of the public using the Naïve Bayes and Support Vector Machine (SVM) methods, and to compare the accuracy of both in sentiment analysis. Data was collected via the Twitter API with the hashtag #kaburajadulu, resulting in 2,067 tweets, which, after the cleansing process and manual labeling, left 385 data points. The analysis process followed the CRISP-DM stages, which include business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Model evaluation was conducted using a confusion matrix with accuracy, precision, and recall metrics. The classification results show that 82% of tweets have a positive sentiment and 18% negative. The Naïve Bayes algorithm achieved an accuracy of 86.49%, slightly lower than SVM, which reached 88.05%. In conclusion, Support Vector Machine is more effective in sentiment classification on public opinion data. This research contributes to the digital mapping of public opinion and recommends the development of automatic labeling methods as well as the exploration of advanced algorithms in the future.

The growth of information technology has driven changes in consumer behavior, one of which is through e-commerce platforms such as Shopee. This phenomenon has generated a large number of customer reviews, including those for local cosmetic products such as Wardah. These reviews serve as an important source of information for understanding customer perceptions and satisfaction levels. However, manual analysis of large and linguistically diverse datasets is inefficient and potentially subjective. This study aims to implement the multi-category Naive Bayes algorithm to classify the sentiment of Wardah product reviews on Shopee into three categories: positive, negative, and neutral. The data were collected using a web scraping technique and processed through a series of preprocessing stages including case folding, tokenization, stopword removal, stemming, and text cleaning. Subsequently, term weighting was performed using the TF-IDF method prior to classification. Model performance was evaluated using a confusion matrix as well as accuracy, precision, and recall metrics. The results indicate that the multi-category Naive Bayes algorithm achieved an accuracy of 86.00%, a precision of 86.63%, and a recall of 98.24%. This approach can assist business practitioners in objectively understanding customer opinions and support decision-making in business strategy and product development.

The development of social media, especially TWITTER, has become one of the main means for people to express opinions and criticism on various issues, including the performance of law in Indonesia. This study aims to analyze public sentiment towards the performance of law based on TWITTER user comments using the Naïve Bayes algorithm. The research data consists of 1004 comments collected from several videos related to legal topics. The analysis process includes the stages of data crawling, pre- processing (text cleaning, normalization, and tokenization), labeling sentiment into positive, negative, and neutral, and testing the Naïve Bayes model. The results show that the Naïve Bayes algorithm is able to classify sentiment with an accuracy level of 93.73%. The distribution of sentiment from 1004 comments shows that the majority of public opinion is (negative/positive/neutral), which indicates that public perception of the performance of law is still (critical/positive). These findings are expected to be input for related parties to understand public opinion and improve the quality of legal performance in

The rise of social media has created a digital public sphere that enables users to express their opinions on social and political issues openly and in real-time. One of the most discussed topics on social media platform X is the trending hashtag #IndonesiaGelap, which reflects public concern and criticism regarding various governmental and societal conditions. This study aims to conduct sentiment analysis on tweets containing the hashtag to determine the overall sentiment trend among users. The method employed in this research is the Naive Bayes classification algorithm, known for its simplicity and effectiveness in text classification. To enhance the model’s performance, Particle Swarm Optimization (PSO) is applied to optimize feature selection and parameter tuning. The dataset consists of public tweets collected via the Twitter API, followed by preprocessing, feature extraction using TF-IDF, and sentiment classification into three categories: positive, negative, and neutral. The results indicate that the integration of PSO significantly improves the classification accuracy of the Naive Bayes model compared to the baseline. The majority of tweets related to #IndonesiaGelap exhibit a negative sentiment, indicating widespread public dissatisfaction and criticism. This research is expected to contribute to a better understanding of public perception and serve as valuable input for stakeholders in addressing social issues in the digital age.

The escalation of negative sentiment in the digital space towards Rohingya refugees in Indonesia throughout 2023-2026 has reflected a shift in public perspectives, from humanitarian principles to restictive rejection. This study aims to analyze how digital discourse on TikTok dan Instagram platforms frames the Rohingyan refugee issue as a national security threat through the lens of Barry Buzan`s Securitization Theory and Ruth Wodak`s Critical Discourse Analysis (AWK). This study uses qualitative methods with note-taking techniques and filtering hastag-based viral data related to refugee rejection. The results show that the securitization process was successfully driven by three main typologies of netizen narratives: domestic socio-economic jealousy, delegetimization of Internasional authorities (UNHCR) by referring to popular legal discourse on the 1945 Constitution, and demands for an active role for the military (TNI AL) and Polair at maritime borders. The accumulation of speech acts that have gone viral on social media is evidence of the creation of strong horizontal pressure, thus urging the Indonesian goverment to review its policies towards a more restrictive direction (viral-based policy) to prioritize national soverignity and security over global humanitarian commitments.

This study aims to develop a sentiment classification method for YouTube user comments related to the game Love and Deepspace using the Naïve Bayes algorithm, focusing on improving the text data processing and understanding user perceptions. Comment data were collected through scraping from YouTube videos, followed by preprocessing including text cleaning, normalization, stopword removal, stemming, and translation into English. Initial labeling was conducted using TextBlob, then the data were randomly sampled for training the Naïve Bayes model. Evaluation involved comparing sentiment distributions and visualization using Word Cloud and bar charts. The Naïve Bayes model achieved an accuracy of 77.36% in sentiment classification. The sentiment distribution shows differences between TextBlob (positive: 1,011, neutral: 1,312, negative: 575) and Naïve Bayes (positive: 901, neutral: 1,627, negative: 370), with Naïve Bayes being more conservative. The Word Cloud visualization identifies dominant words such as "bang," "game," and "main," while the bar chart shows the largest proportion of neutral sentiment. Naïve Bayes is effective for sentiment classification on informal comment data, with significant differences from rule-based methods like TextBlob. This research contributes to the development of text data processing techniques and user perception analysis, as well as opening up optimization opportunities with other algorithms like SVM for better accuracy.

This research critically investigates the circulation of disinformation concerning the instability of fuel prices on the digital platform X and its subsequent implications for the polarization of modern society. In an era where unverified economic news frequently dictates public reaction, fake news often acts as a potent catalyst for mass anxiety. By implementing a quantitative framework driven by lexicon-based computational sentiment analysis, this study effectively processed a dataset of 500 public opinion samples extracted via Google Colab spanning from April 2024 to April 2026. To ensure computational accuracy and eliminate textual noise, the data underwent a rigorous preprocessing phase encompassing case folding, alongside the systematic removal of URLs, account mentions, numbers, hashtags, and punctuation marks. The statistical outcomes revealed a highly disproportionate emotional landscape, overwhelmingly dominated by 451 negative reviews. In stark contrast, neutral observations and positive affirmations were nearly absent, recording only 40 and 9 instances, respectively. The data compellingly illustrates that the relentless influx of pessimistic narratives regarding economic instability directly induces financial panic, undermines rational discourse, and severely fragments cyberspace into deeply polarized factions.

Social media has evolved into a significant platform where consumers freely express their opinions, experiences, and levels of satisfaction regarding various products, including those offered by Micro, Small, and Medium Enterprises (MSMEs). The comments and reviews shared by customers on these platforms contain diverse sentiments that can serve as valuable indicators of how consumers perceive product quality. Understanding these sentiments is crucial for MSME owners, as it allows them to evaluate their products and adapt to market expectations more effectively. This study aims to analyze customer sentiment toward MSME products on social media by utilizing the Naïve Bayes algorithm, a widely used classification method in text mining. The data used in this research consist of customer comments collected from various social media platforms. The research process involves several stages, including data collection, manual labeling of sentiments, text preprocessing (such as tokenization, case folding, and stopword removal), and splitting the dataset into training and testing subsets. Subsequently, the classification process is carried out using the Naïve Bayes algorithm to categorize sentiments into positive, negative, and neutral classes. The results of this study demonstrate that the Naïve Bayes method is effective in classifying customer sentiments with a satisfactory level of accuracy. These findings provide a comprehensive overview of consumer perceptions regarding the quality of MSME products. Furthermore, this research is expected to assist MSME business owners in understanding customer feedback more systematically and using it as a basis for improving product quality and enhancing customer satisfaction in a competitive digital marketplace.

Mental health issues among university students have become a growing concern, driven by academic pressures, career uncertainties, and complex social transitions. However, a large proportion of students remains reluctant to seek professional psychological support due to social stigma and limited access to institutional counseling services. This study proposes the design and implementation of an Android-based chatbot application that integrates mood tracking and sentiment analysis to continuously monitor the emotional states of university students. The system employs a fine-tuned RoBERTa (Robustly Optimized BERT Pretraining Approach) model trained on the EmoContext conversational dataset (SemEval-2019 Task 3), comprising 30,160 labeled three-turn dialogue instances across four emotion classes: angry, happy, sad, and others. The model was fine-tuned for four epochs using the AdamW optimizer with a learning rate of 2e-5 and a maximum sequence length of 128 tokens. Evaluation on a held-out validation set of 6,032 samples yielded an overall accuracy of 88.28%, a macro-average F1-score of 0.87, and a weighted-average F1-score of 0.88. Per-class F1-scores were 0.89 (angry), 0.83 (happy), 0.91 (others), and 0.86 (sad). The classified emotion is transmitted in real time to the chatbot response logic, which generates empathetic replies and personalized relaxation recommendations based on the detected mood. Primary data collection through questionnaires and interviews with 62 and 19 university students respectively confirmed the need for accessible digital mental health support. The results demonstrate that RoBERTa-based fine-tuning on conversational data provides a reliable foundation for real-time emotion-aware mental health chatbot systems.

Sentiment analysis for Indonesian regional languages faces two persistent challenges: labeled training data is extremely limited for most regional varieties, and transformer models pre-trained on Bahasa Indonesia do not generalize reliably to languages with substantially different morphological structures. Prior work on the NusaX benchmark has primarily relied on direct fine-tuning, treating each regional language independently and without exploiting linguistic proximity between related languages as a transfer signal. This paper proposes Language-Similarity-Guided Transfer (LSGT), a sequential fine-tuning strategy that first adapts a pre-trained model to a pivot language selected using character trigram similarity, followed by fine-tuning on the target language. Four transformer models are evaluated across all 12 NusaX languages using the official train/validation/test splits: IndoBERT, NusaBERT, mBERT, and XLM-R. Performance is evaluated using four metrics: accuracy, macro F1, macro precision, and macro recall. Experimental results show that LSGT improves macro F1 in 44 of 48 model-language combinations, demonstrating that the fine-tuning strategy itself is a major factor in low-resource cross-lingual sentiment classification. XLM-R benefits most strongly from LSGT, achieving an average improvement of +0.137 macro F1 and a peak gain of +0.298 on Madurese. SHAP-based token attribution analysis further reveals that predictions rely heavily on named entities and domain-specific nouns rather than sentiment-bearing vocabulary, indicating a dataset-level bias inherited from the original SmSA corpus and propagated through the NusaX translation pipeline.

Indonesian culinary comments on social media platforms such as Instagram are characterized by informal spelling, regional language mixing, slang expressions, and emojis, posing substantial challenges for automated sentiment classification. While IndoBERT has demonstrated strong performance across Indonesian natural language processing tasks, the contribution of individual preprocessing components to fine-tuning performance on informal text remains underexplored, particularly in the culinary domain. This study addresses this gap by conducting a systematic preprocessing ablation study on IndoBERT-Base fine-tuning for Indonesian culinary sentiment classification, accompanied by a comparative evaluation against Naive Bayes with TF-IDF, SVM with TF-IDF, and BiLSTM as representative baselines. A dataset of 3,500 manually labeled Instagram culinary comments across three sentiment classes was used, with a stratified 80/10/10 split. Six preprocessing variants were evaluated under identical experimental conditions to isolate the contribution of each component. The results show that slang normalization is the most impactful single preprocessing step, yielding a macro F1-score gain of +0.0609 over the no-preprocessing baseline, while the full pipeline achieves an accuracy of 0.8800 and a macro F1-score of 0.8465. IndoBERT-Base with the full pipeline outperforms all baselines across all evaluation metrics. Per-class analysis reveals that the negative class achieves the lowest F1-score of 0.7600, with sarcastic expressions and Banjar regional vocabulary identified as primary sources of misclassification. These findings indicate that preprocessing decisions have a measurable and non-uniform effect on IndoBERT fine-tuning performance. In this study, slang normalization provides the most substantial individual contribution in bridging the vocabulary gap between informal user-generated text and the model’s pre-training distribution.

The phenomenon of radical transparency in the Bottled Drinking Water (AMDK) industry in 2025 triggered a reputation crisis and a massive erosion of customer loyalty. This crisis began with negative sentiment on social media that led to surprise inspections by regulatory authorities of the industry leader's "Mountain Spring" claim. The unpreparedness of the communication infrastructure in presenting technical data in real time led to a decline in brand image and a significant correction in market share to a critical figure of 47.4%. This article aims to formulate a conceptual framework for adaptive and data-driven PR presentation techniques through the integration of real-time data visualization and narrative reframing strategies. The method used is a descriptive conceptual analysis by evaluating the chronology of incidents and PR responses during the crisis. The analysis results show that unidirectional communication patterns and static presentation materials are deemed to fail to face viral and spontaneous public audits in the digital space. As a theoretical and practical contribution, this article proposes a new model, The Spontaneous Technical Presentation Model, and recommendations for the development of a Crisis Presentation Kit for the FMCG industry. Through a theoretical approach that expands the theory of Image Restoration, this study confirms that corporate image restoration in the digital era is highly dependent on the precision and transparency of visual data presented during field qualification