Claim Missing Document
Check
Articles

Found 27 Documents
Search

Empowering Algebra Learning with AI-Based Adaptive Systems for High School Students Lestari, Mugi; Saputra, Moch Panji Agung; Lianingsih, Nestia
International Journal of Ethno-Sciences and Education Research Vol. 5 No. 3 (2025): International Journal of Ethno-Sciences and Education Research (IJEER)
Publisher : Research Collaboration Community (Rescollacom)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijeer.v5i3.1039

Abstract

Learning algebra is often challenging for high school students due to its abstract nature, leading to loss of motivation. This study designed and implemented an Adaptive AI Platform that personalized practice problems based on real-time performance analysis and student interests. A quasi-experimental study with 120 10th grade students demonstrated a significant effect of the platform on improving academic achievement. The experimental group (n=60) using the platform demonstrated significantly higher TPA posttest scores (adjusted mean: 81.95) than the control group (n=60) (adjusted mean: 73.65), after controlling for pretest scores. In addition, the platform substantially increased students’ learning motivation and self-confidence (Cohen’s d = 2.48 for the experimental group), supported by instant feedback and difficulty adaptation. The integration of Deep Knowledge Tracing (DKT) and Item Response Theory (IRT) models enabled dynamic content adjustments aligned with students’ cognitive progress. The results were also supported by students’ positive perceptions regarding the engagement and effectiveness of the platform. This study recommends the integration of adaptive AI platforms in high school mathematics education with adequate teacher support and infrastructure, and suggests future research for longer intervention durations and ethical analysis of AI.
Comparative Analysis of Machine Learning Models for Email Spam Detection Lestari, Mugi; Salih, Yasir; Jaizul, Alim
International Journal of Global Operations Research Vol. 6 No. 3 (2025): International Journal of Global Operations Research (IJGOR), August 2025
Publisher : iora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47194/ijgor.v6i3.392

Abstract

The development of information technology has driven a significant increase in the use of email as a primary communication tool across various sectors. Spam emails have become a serious issue that can disrupt productivity and threaten data security as well as user privacy. Conventional rule-based spam filtering systems are no longer considered effective in countering increasingly sophisticated and adaptive spam attack patterns. A more dynamic and accurate approach is required through the utilization of Machine Learning. This study aims to analyze and compare the performance of several Machine Learning algorithms in detecting spam emails, namely Extra Trees Classifier, Random Forest, Support Vector Machine (SVM) with an RBF kernel, and CatBoost. The methodology involves data acquisition from the SMS Spam Collection Dataset, data preprocessing through text cleaning and feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF), followed by model training and evaluation using Accuracy, F1 Score, and ROC AUC metrics. The results show that the Extra Trees Classifier achieved the best performance, with an Accuracy of 97.29%, an F1 Score of 0.8814, and a ROC AUC of 0.9868. Tree-based ensemble models, particularly Extra Trees and Random Forest, demonstrated superior capability in maintaining a balance between precision and recall. The SVM (RBF) recorded the highest AUC value but presented a trade-off in the form of a higher number of False Negatives. The findings of this research serve as a reference for the development of more adaptive and effective Machine Learning–based spam detection systems.
Mapping Public Opinion on the DPR Salary Increase Issue via YouTube Comment Sentiment Analysis using IndoBERTa Saefullah, Rifki; Lestari, Mugi
International Journal of Humanities, Law, and Politics Vol. 3 No. 3 (2025): International Journal of Humanities, Law, and Politics
Publisher : Communication in Research and Publications (CRP)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijhlp.v3i3.247

Abstract

The issue of salary increases for members of the House of Representatives (DPR) in Indonesia has sparked widespread public debate because it is considered inconsistent with the socio-economic conditions of the community. The policy is perceived as sensitive, particularly regarding the principles of social justice, government accountability, and political legitimacy. In the digital era, social media such as YouTube has become an important space for the public to express opinions openly. This study aims to map public opinion regarding the DPR salary increase issue through sentiment analysis of YouTube comments using a Natural Language Processing (NLP) approach. The IndoBERTa model was used to classify public sentiment into positive, negative, and neutral categories, and n-gram analysis was used to capture dominant linguistic patterns. The results showed that negative sentiment dominated with 5,463 comments, far exceeding neutral (1,391 comments) and positive (812 comments). The n-gram analysis revealed that frequently appearing words and phrases related to "people," "DPR," "salary," as well as emotional expressions such as "disband the DPR" and "dancing on the people's suffering." These findings indicate that the DPR salary issue triggered a strong, often sarcastic public response and demonstrated a crisis of trust in the legislative institution. The lack of positive sentiment confirms that this policy has almost no public support.
Analysis of Economic Growth and Tourism Potential in Tanjung Lesung, Panimbang, Banten as a Creative Economy Destination Hidayana, Rizki Apriva; Lestari, Mugi
International Journal of Business, Economics, and Social Development Vol. 6 No. 1 (2025)
Publisher : Rescollacom (Research Collaborations Community)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijbesd.v6i1.879

Abstract

Tanjung Lesung, located in Pandeglang Regency, Banten, has been designated as a Special Economic Zone (SEZ) for Tourism with the aim of encouraging regional economic growth and improving community welfare. This study analyzes the impact of SEZ on the local economy using qualitative and quantitative approaches. Data were obtained through in-depth interviews, surveys, field observations, and documentation studies. The results of the study indicate that the Tanjung Lesung SEZ has contributed positively to increasing community income by 52% and reducing the unemployment rate by 33%. In addition, investment in the tourism sector encourages business growth in the hospitality, culinary, and tourism services sectors. However, the development of SEZ also faces several challenges, such as limited infrastructure, readiness of local workers, and social and environmental impacts. Limited infrastructure, especially transportation access, is an obstacle in supporting the growth of the tourism sector. In addition, many local workers do not yet have the skills needed by the tourism industry. Environmental impacts, such as increasing waste volume and conversion of agricultural land, are also major concerns. Therefore, a comprehensive strategy is needed through improving infrastructure, strengthening human resource capacity, and implementing sustainable environmental management policies. With the right steps, Tanjung Lesung Special Economic Zone can become a successful model for inclusive and sustainable tourism-based economic development in Indonesia.
The Role of Guidance and Counseling Teachers in Addressing Juvenile Delinquency: A Literature Review Lianingsih, Nestia; Lestari, Mugi
International Journal of Ethno-Sciences and Education Research Vol. 5 No. 1 (2025): International Journal of Ethno-Sciences and Education Research (IJEER)
Publisher : Research Collaboration Community (Rescollacom)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijeer.v5i1.840

Abstract

Juvenile delinquency is an increasingly worrying phenomenon in various countries, including Indonesia. This study aims to explore the role of Guidance and Counseling (BK) Teachers in overcoming juvenile delinquency through a literature review method. This study analyzes prevention strategies, reactive approaches, and curative efforts carried out by BK teachers to deal with deviant behavior committed by adolescents. The results of the study indicate that BK teachers have a key role in preventing and overcoming juvenile delinquency through various approaches, including providing information, group guidance, mediation, home visits, and individual and group counseling. However, the implementation of these strategies often faces internal, external, and institutional obstacles, such as students' lack of confidence to open up, minimal parental attention, and limited school resources. This study emphasizes the importance of a collaborative approach involving teachers, parents, and the community in dealing with juvenile delinquency in a comprehensive and sustainable manner
Parental Involvement and Its Relationship with High School Students' Learning Achievement: A Comparative Study of Urban and Rural Schools Nurnisaa, Nurnisaa; Lestari, Mugi
International Journal of Ethno-Sciences and Education Research Vol. 5 No. 2 (2025): International Journal of Ethno-Sciences and Education Research (IJEER)
Publisher : Research Collaboration Community (Rescollacom)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijeer.v5i2.939

Abstract

This study aims to analyze the relationship between parental involvement and academic achievement of high school students by comparing schools in urban and rural areas. A comparative quantitative approach with correlational survey method was employed, involving 100 eleventh-grade students (50 from urban schools and 50 from rural schools). Data were collected through questionnaires measuring parental involvement based on Epstein's theory and documentation of report card scores for academic achievement. Results revealed a significant positive correlation (r = 0.621; p < 0.05) between parental involvement and student academic achievement. Independent Samples T-Test showed a significant difference (p = 0.002) in academic achievement between urban school students (M = 86.20) and rural school students (M = 82.45). Similarly, parental involvement in urban schools demonstrated higher average scores (M = 82.14; SD = 6.43) compared to rural schools (M = 74.88; SD = 7.12). These findings confirm that geographical context influences patterns of parental involvement in education and its impact on academic achievement. This study contributes to educational policy formulation, particularly in developing effective parental involvement strategies tailored to specific school environments, and highlights the importance of collaborative programs between schools and families to address the urban-rural achievement gap.
Sentiment Analysis of TikTok User Comments on Student Proposal Hearing Videos Lestari, Mugi; Vera
International Journal of Linguistics, Communication, and Broadcasting Vol. 3 No. 4 (2025): International Journal of Linguistics, Communication, and Broadcasting
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijlcb.v3i4.287

Abstract

The rapid growth of social media has transformed digital platforms into spaces for public communication and audience interaction, including the dissemination of academic content. TikTok, as a form of digital broadcasting media, enables users to actively respond to various types of content through comments, creating rich linguistic data that reflect audience attitudes and perceptions. However, studies examining audience sentiment toward academic activities, particularly student proposal hearing videos on TikTok, remain limited, especially from a linguistic and broadcasting perspective. This study aims to analyze the sentiment and linguistic patterns of TikTok user comments on a student proposal hearing video to understand audience responses to academic content in digital media. The research employed a quantitative descriptive approach using sentiment analysis and frequency-based linguistic analysis. Data were collected from public TikTok comments through automated web scraping, followed by text preprocessing, word frequency analysis, n-gram analysis, and sentiment classification using an Indonesian RoBERTa-based transformer model. The results indicate that neutral sentiment dominates the comment section, followed by positive sentiment, while negative sentiment appears minimally. Linguistic patterns derived from word frequency and n-gram analysis reveal that audience responses are characterized by supportive, motivational, and evaluative language, emphasizing encouragement, smooth communication, and a positive academic atmosphere. These findings suggest that TikTok functions not only as a digital broadcasting platform for academic content but also as a participatory space where audiences construct collective and supportive discourse around academic experiences.