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

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.

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.

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

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.

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.

This study analyzes the formation of a digital brand community through Persib Bandung fan interactions on social media. The research aims to examine how content distribution, message functions, and engagement patterns contribute to the construction of collective identity and digital rituals among supporters. Using a qualitative-interpretative content analysis supported by quantitative descriptive data, this study analyzes 418 posts published on Persib Bandung's official Instagram, TikTok, Facebook, X/Twitter, and YouTube accounts from November 27 to December 10, 2025. The findings reveal that Persib Bandung generated 29,543,663 total interactions, with Instagram and TikTok emerging as the most affective platforms for engagement. Non-match content (41.4%) and emotional or motivational messages (40.2%) dominate communication. Despite high public engagement, no evidence of two-way talkback from the official account was found, indicating a predominantly one-way communication model. The study concludes that Bobotoh function as a digital brand community characterized by collective identity, digital rituals, loyalty, symbolic ownership, and co-creation of brand meaning through measurable public interactions. This research contributes to the understanding of sports communication and digital brand communities in emerging football markets.

The rapid development of social media, particularly Twitter, has given rise to a new form of social violence known as cyberbullying. This study aims to explore the phenomenon of cyberbullying on Twitter using Ulrich Beck's Risk Society Theory as an analytical framework. The research approach used is a literature review. This study perceives cyberbullying on Twitter as a modern, systemic risk, shaped by anonymity, cancel culture, and the individualization of risk. It acknowledges that Twitter's structural features, such as pseudonymous accounts and the rapid dissemination of information, exacerbate the potential for cyberbullying, while simultaneously positioning individual users as both victims and potential perpetrators of digital violence. These findings reinforce Beck's thesis that risks in advanced modernity are self-produced, institutionally distributed, and difficult to regulate, clearly reflected in the uncontrolled spread of cyberbullying in digital public spaces.

The development of digital technology has significantly changed the way students interact and present themselves in social life, especially through social media such as Instagram, TikTok, and Twitter. One of the emerging social phenomena is flexing, which refers to the behavior of showing off lifestyle, achievements, or ownership to gain attention and social recognition. This study aims to analyze how Sociology students of Sriwijaya University interpret flexing on social media and whether flexing is more dominant as a lifestyle or as a form of social pressure. This research uses a qualitative method with a literature review approach by examining various scientific articles, journals, and previous studies related to flexing, self-presentation, symbolic consumption, social validation, and Fear of Missing Out (FoMO). The results show that flexing is not only a form of self-presentation and symbolic consumption, but also a response to social pressure in the digital environment.

The phenomenon of hate speech on social media, particularly on platform X, has intensified alongside the increasing level of public interaction within open and largely unregulated digital spaces. This condition not only generates communicative conflicts but also shapes complex social experiences for individuals, particularly in relation to identity, emotion, and power relations. This study aims to gain an in-depth understanding of how hate speech is constructed, interpreted, and negotiated by users within the context of digital interaction. Employing a qualitative approach with a Critical Discourse Analysis (CDA) design, data were collected through in-depth interviews, non-participant observation, and digital document analysis involving 10–15 active users of platform X who have experienced hate speech. Data were analyzed thematically by identifying patterns of meaning emerging from participants’ experiences. The findings reveal three major themes: hate speech as a lingering yet normalized emotional experience; discourse as a site for the reproduction of power and identity delegitimization; and self-negotiation strategies employed by participants to survive within digital spaces. These findings indicate that hate speech operates not only at the linguistic level but also in shaping users’ social and psychological realities. Theoretically, this study reinforces Critical Discourse Analysis by emphasizing the importance of subjective experience in interpreting discursive practices. Practically, it contributes to the development of digital literacy, content moderation policies, and efforts to create more inclusive and reflective communication spaces in the digital era.

This study aims to identify and analyze Ramadan-specific lexicons used by Indonesian Muslim communities on social media, as well as to describe the cultural meanings embedded within them. The study employs an anthropolinguistic approach with a descriptive qualitative method. Data were collected through observation and note-taking techniques from three social media platforms X (Twitter), TikTok, and Instagram during the Ramadan 1446 H/2025 period. A total of 32 Ramadan-specific lexicons were identified and classified into three categories: greetings and expressions (12 items), worship-related lexicons (10 items), and culinary lexicons (10 items). The findings reveal that Ramadan lexicons circulating on social media reflect a blend of Islamic religious values, local Indonesian cultural traditions, and the influence of digital globalization. The hybrid nature of the language used — including code-mixing between Indonesian, Arabic, and English — illustrates the dynamic cultural identity of contemporary Indonesian Muslims. Ultimately, this study affirms that language is a living mirror of culture, one that continues to evolve alongside social and technological change.

Code-switching has become increasingly prevalent in digital communication among Indonesian youth, reflecting complex sociolinguistic dynamics in multilingual contexts. This study investigates code-switching patterns in Indonesian digital native youth's computer-mediated communication (CMC), examining the linguistic structures, social functions, and motivations behind this phenomenon. A mixed-methods approach was employed, analyzing 2,500 social media posts from 150 Indonesian youth aged 18–25 across Instagram, Twitter, and WhatsApp. Quantitative content analysis identified code-switching frequency and patterns, while qualitative thematic analysis explored motivations and functions. Myers-Scotton's Matrix Language Frame model guided the structural analysis. Results revealed that 78.4% of participants engaged in code-switching, with Indonesian-English being the most common pattern (62.3%), followed by Indonesian-Regional Language (23.5%) and trilingual switching (14.2%). Intrasentential switching occurred in 54.7% of cases, while intersentential switching appeared in 31.8%. Five primary functions emerged: identity construction (32.1%), emphasis/intensification (26.4%), topic shifting (18.9%), humor/creativity (14.3%), and lexical gap-filling (8.3%). Code-switching in Indonesian digital communication represents a sophisticated linguistic practice driven by identity negotiation, expressive needs, and technological affordances rather than linguistic deficiency. These findings contribute to understanding multilingual CMC in Southeast Asian contexts and have implications for digital literacy education and language policy.

The development of technology in the era of globalization has brought significant changes in society, particularly through the emergence of the internet and social media such as WhatsApp, X (Twitter), Facebook, Instagram, Telegram, and TikTok, which facilitate rapid information dissemination. This development has also given rise to a new profession, namely content creators, who produce and share content in the form of images, videos, or text for branding, professional purposes, or self-expression, often resorting to sensationalism to attract audience attention. On the other hand, the ease of access to social media has also triggered the spread of negative content, including pornography, as evidenced by Komdigi/Kominfo data showing millions of blocked negative content, with X being one of the dominant platforms. In Islamic perspective, anything that leads to adultery is prohibited as stated in QS. Al-Isra verse 32. A prominent case is Dea OnlyFans (Gusti Ayu Dewanti) who was arrested for distributing pornographic content through OnlyFans and Google Drive, charged under the Pornography Law and ITE Law, and found guilty in the Supreme Court Decision Number 2086 K/Pid.Sus/2023. This study discusses 1) How are the differences in judges' considerations at the District Court, High Court, and Cassation? 2) Can the Supreme Court judges' considerations provide a deterrent effect? This research uses a descriptive method with normative legal research based on literature study, using primary, secondary, and tertiary legal materials.

This study evaluates public sentiment toward Constitutional Court Decision No. 90/PUU-XXI/2023 regarding the age limit for presidential and vice-presidential candidates, a controversial issue closely related to Indonesia’s democratic dynamics. Understanding public opinion on Twitter, as a major platform for political expression, is essential for informing electoral policy formulation. Data were collected using Tweet Harvest through Google Colab and analyzed using the Naïve Bayes algorithm as the primary sentiment classification method, with RapidMiner employed to support and streamline the analytical process. The analysis process included data cleaning, text normalization, stopword removal, manual labeling of 80 tweets as training data, and automatic sentiment classification to identify positive and negative sentiments. From a total of 151 analyzed tweets, 84 (55.63%) were classified as negative and 67 (44.37%) as positive, with the model achieving an accuracy of 66.67%. These findings suggest a tendency toward public opposition to the decision, reflecting dissatisfaction among Twitter users. The study demonstrates that Naïve Bayes is reasonably effective for sentiment classification with limited datasets and provides insights for policymakers in understanding public responses to election-related regulations.

In today's digital era, social media has become an integral part of everyday life, especially for younger generations such as students. Platforms like Instagram, TikTok, Twitter, and Facebook facilitate fast and interactive communication, but often encourage the use of informal language such as abbreviations or emojis. This contrasts with the demands of the academic world. This study aims to analyze the influence of social media use on students' language styles in the academic world. The research method used was quantitative, namely observation. Observations were conducted to determine students' communication patterns on digital platforms (such as class WhatsApp group chats and comments on social media). The results showed a strong tendency to use slang, non-standard abbreviations, and code-mixing, carried over from social media habits into formal academic contexts. This phenomenon has contributed to the erosion of the boundaries between informal and formal language styles among students. This study concludes the need to strengthen formal language literacy to maintain professional communication in the academic world.

This study examines the phenomenon of K-Pop slang usage among young generations and its influence on lifestyle and social identity formation. The research background reveals that K-Pop culture has significantly impacted language practices, particularly through the adoption of specific terms within fan communities. The objective is to analyze how K-Pop slang functions as a linguistic creativity tool and identity marker among Indonesian youth. Using a qualitative descriptive approach, data were collected from social media platform X (Twitter) through purposive sampling of posts containing K-Pop slang terms. Findings indicate that K-Pop slang encompasses semantic shifts, acronyms, abbreviations, and new terminology that strengthen community solidarity and collective identity. The implications suggest that while K-Pop slang serves as creative expression and social bonding mechanism, excessive usage may affect proper Indonesian language proficiency in academic contexts. This research contributes to understanding the balance between linguistic creativity, global cultural influence, and Indonesian language preservation.

This study examines the role of social media, particularly Twitter, as a digital da’wah medium that is fast, interactive, and easily accessible to users. However, the extent to which the use of Twitter can enhance communication confidence among students still requires empirical validation. The focus of this research is to evaluate the effectiveness of Twitter use in influencing students’ communication abilities, especially in delivering da’wah messages. The purpose of this study is to analyze the effect of Twitter usage on the communication confidence of students from the 2020 cohort. A quantitative approach was employed using a survey method. Data were collected through a structured, scale-based questionnaire, in accordance with the positivistic research paradigm that emphasizes objective and measurable hypothesis testing. The research population consisted of 62 students, from which 38 respondents were selected using proportionate stratified random sampling to ensure representation across all population strata. The findings reveal that the use of Twitter has a significant effect on the communication confidence of KPI IAI Al-Azis students from the 2020 cohort in delivering da’wah messages. Regression analysis results show a significance value of 0.050 < 0.05, with a Pearson correlation coefficient of 0.614, indicating a strong relationship. These results suggest that the more frequently students engage with Twitter, the greater their confidence in expressing and disseminating da’wah messages through various digital formats such as text, images, and videos. Twitter thus provides an expressive platform that fosters interaction, encourages participation, and strengthens students’ digital da’wah communication skills.

Advances in technology and social media have changed the way individuals obtain information and interact, especially in the context of global culture. BTS, a famous South Korean boy band, utilized social media to build a strong relationship with their fans, ARMY, through the campaign “Love Myself.” The campaign emphasized the importance of self-love and raised issues of mental health and violence. The campaign emphasized the importance of self-love and raised issues of mental health and violence. Through platforms such as Twitter and Instagram, BTS interacted directly with ARMY, who responded with significant support, including a 2.4 billion won donation to UNICEF. This interaction not only strengthened the online community but also helped boost fans' confidence. This research analyzes the impact of the “Love Myself” campaign on ARMY's engagement in social issues through social media. Furthermore, the resulting impact provides important insights into how celebrities and social media can influence broader social change. The campaign also reflects a shift in traditional ways of advocating and supporting social issues.

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 growth of digital transactions has made it easier for people to buy goods or services, including concert tickets. However, this convenience also increases the risk of fraud, especially through social media. The case of Golden Disc Award (GDA) 2024 ticket fraud on Twitter shows a systematic modus operandi, such as the use of fake accounts and identities, suspiciously cheap ticket prices, and the transfer of communication to private platforms. Victims suffer material and psychological losses, while perpetrators often disappear after receiving payment. Legally, these actions violate Article 378 of the Criminal Code, the Electronic Information and Transactions Law, and consumer rights as stipulated in the Consumer Protection Law (UUPK). This study emphasizes the importance of consumer protection in digital transactions, strengthening regulations, and improving public digital literacy to prevent fraudulent practices. Collaboration between the government, law enforcement agencies, concert organizers, digital platforms, and consumers is key to improving the security of online transactions.