Claim Missing Document
Check
Articles

Found 18 Documents
Search

Interpretation of Deep Learning Models in Natural Language Processing for Misinformation Detection with the Explainable AI (XAI) Approach muhammadiah, mas'ud; Rahman, Rashid; Wei, Sun
Journal of Computer Science Advancements Vol. 3 No. 2 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i2.2104

Abstract

The increasing spread of misinformation through digital platforms has raised significant concerns about its societal impact, particularly in political, health, and social domains. Deep learning models in Natural Language Processing (NLP) have shown high performance in detecting misinformation, but their lack of interpretability remains a major challenge for trust, transparency, and accountability. As black-box models, they often fail to provide insights into how predictions are made, limiting their acceptance in sensitive real-world applications. This study investigates the integration of Explainable Artificial Intelligence (XAI) techniques to enhance the interpretability of deep learning models used in misinformation detection. The primary objective of this research is to evaluate how different XAI methods can be applied to explain and interpret the decisions of NLP-based misinformation classifiers. A comparative analysis was conducted using state-of-the-art deep learning models such as BERT and LSTM on benchmark datasets, including FakeNewsNet and LIAR. XAI methods including SHAP (SHapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and attention visualization were applied to analyze model behavior and feature importance. The findings reveal that while deep learning models achieve high accuracy in misinformation detection, XAI methods significantly improve transparency by highlighting influential words and phrases contributing to model decisions. SHAP and LIME proved particularly effective in providing human-understandable explanations, aiding both developers and end-users. In conclusion, incorporating XAI into NLP-based misinformation detection frameworks enhances model interpretability without sacrificing performance, paving the way for more responsible and trustworthy AI deployment in combating online misinformation.
The Effect of Family Counseling Services on the Relationship Between Parents and Problematic Elementary School Students Buka, Sisilia Prima Yanuaria; Rahman, Rashid; Razak, Faisal; Shofwan, Arif Muzayin
International Journal of Educatio Elementaria and Psychologia Vol. 2 No. 2 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijeep.v2i2.1882

Abstract

Family dynamics play a crucial role in shaping children's behavior and academic success. Conflicts between parents and children can disrupt these dynamics, particularly for elementary school students with behavioral challenges. This study examines the effect of family counseling services on improving the relationship between parents and problematic elementary school students. The research aims to evaluate whether structured family counseling can enhance communication, mutual understanding, and collaboration between parents and their children. A quasi-experimental research design was employed, utilizing pre-test and post-test measures with a control group. The sample consisted of 50 families selected through purposive sampling, divided equally into experimental and control groups. Data were collected using relationship quality questionnaires, observational records, and structured interviews. The results indicate a significant improvement in the parent-child relationship within the experimental group compared to the control group. Participants reported enhanced communication, reduced conflict, and increased emotional bonding after engaging in the family counseling sessions. These findings suggest that family counseling is an effective intervention for addressing relational issues and fostering a supportive environment for elementary school students with behavioral difficulties.
The Relationship Between Teacher Involvement in Curriculum Development and Student Learning Outcomes Kusmawan, Asep; Rahman, Rashid; Anis, Nina; Arifudin, Opan
International Journal of Educatio Elementaria and Psychologia Vol. 2 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijeep.v2i1.1890

Abstract

Teacher involvement in curriculum development plays a critical role in shaping effective teaching strategies and fostering meaningful learning experiences. However, limited participation of teachers in curriculum design processes often results in less relevant and engaging instructional practices, potentially impacting student learning outcomes. This study examines the relationship between teacher involvement in curriculum development and student achievement in elementary schools. A correlational research design was employed, involving 120 elementary school teachers and their corresponding student groups. Data were collected using teacher participation surveys, curriculum alignment evaluations, and student learning outcome assessments. The findings revealed a significant positive correlation between teacher involvement in curriculum development and student learning outcomes. Teachers who actively participated in designing curriculum elements tailored to their students’ needs demonstrated higher effectiveness in instructional delivery, resulting in improved academic performance and engagement among students. The research concludes that increasing teacher involvement in curriculum development is essential for enhancing student learning outcomes and recommends integrating collaborative curriculum design practices at the institutional level.
The Effect of Counselor Training Programs on the Quality of Interventions in Schools Belangi, Siska Putri; Nizam, Zain; Rahman, Rashid; Chai, Nong
Research Psychologie, Orientation et Conseil Vol. 2 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/rpoc.v2i1.1852

Abstract

The quality of school counseling interventions is a critical factor in supporting students’ academic, social, and emotional development. Effective counselor training programs are essential for equipping school counselors with the skills and knowledge needed to address diverse student needs. Despite the importance of training, there is limited empirical evidence on the direct impact of such programs on the quality of counseling interventions. This study examines the effect of counselor training programs on intervention quality in schools, focusing on professional competence, intervention outcomes, and counselor confidence. The research aims to evaluate how participation in structured training programs influences the effectiveness of school counselors in delivering interventions. A mixed-methods approach was employed, combining pre- and post-training surveys, in-depth interviews, and observational analysis. The study involved 150 school counselors across 20 schools, with data analyzed using thematic coding and statistical comparison of intervention outcomes. The findings reveal that participation in training programs significantly improves counselors’ confidence and professional competence, leading to enhanced intervention quality. Key improvements were observed in communication skills, problem-solving strategies, and the ability to tailor interventions to individual student needs. The study concludes that investing in counselor training programs has a substantial positive impact on the overall quality of school counseling services.
Cognitive Development in the Digital Age: A Cross-Cultural Perspective Wijaya, Wijaya; Rahman, Rashid; Fariq, Aiman
Research Psychologie, Orientation et Conseil Vol. 2 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/rpoc.v2i3.2374

Abstract

The pervasive integration of digital technologies into adolescents’ lives has fundamentally altered their developmental environments. While the cognitive impact of this “digital age” is widely debated, research often overlooks how these effects are moderated by cultural context, which shapes how technology is adopted and utilized. This study aimed to conduct a cross-cultural comparison of the relationship between specific patterns of digital technology engagement and key cognitive functions, including attention, working memory, and problem-solving skills, among adolescents. A cross-sectional study was conducted with 400 adolescents (aged 14-16) from the United States (n=200) and South Korea (n=200). Participants completed standardized cognitive tests and a Digital Usage Questionnaire. Multiple regression analyses were used to examine the interaction between culture and technology use on cognitive performance. A significant interaction effect emerged. In the U.S. sample, higher social media use correlated with weaker sustained attention. In the South Korean sample, high engagement in collaborative online gaming was positively associated with enhanced problem-solving skills and working memory. The cognitive correlates of technology use differed significantly across cultures. The cognitive impact of the digital age is not universal but is profoundly shaped by cultural values that guide technology engagement.
Hybrid Nanozyme-Enabled Biosensors for Real-Time Detection of Multi-Disease Biomarkers Judijanto, Loso; Rahman, Rashid; Anis, Nina
Journal of Biomedical and Techno Nanomaterials Vol. 2 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jbtn.v2i3.2378

Abstract

The early and accurate detection of disease biomarkers is fundamental to timely diagnosis and effective treatment, yet conventional laboratory methods are often slow, costly, and require complex instrumentation. Nanozymes—nanomaterials with intrinsic enzyme-like properties—offer a promising alternative for developing robust biosensors. This study aimed to design, synthesize, and validate a novel hybrid nanozyme-enabled biosensor platform capable of the sensitive, selective, and real-time multiplexed detection of biomarkers for different diseases from a single sample. A hybrid nanozyme was synthesized by integrating platinum nanoparticles with metal-organic frameworks (MOFs) to create a material with superior catalytic activity. This hybrid nanozyme was then immobilized onto a multi-channel electrochemical sensor chip. Each channel was functionalized with specific aptamers targeting three distinct biomarkers: cardiac troponin I (a cardiac marker), prostate-specific antigen (a cancer marker), and glucose (a metabolic marker). The detection was based on the catalytic signal amplification upon biomarker binding. The platform showed excellent selectivity with negligible cross-reactivity between channels and achieved a rapid detection time of under 15 minutes. The multiplexed assay successfully and accurately quantified all three biomarkers simultaneously in complex serum samples. The hybrid nanozyme-enabled electrochemical biosensor represents a significant advancement in diagnostic technology.
Exploration of Syntactic Structure in Virtual Sign Language: A Study on AI-Based Social Media Platforms Susanti, Ratna; Rahman, Rashid
Journal of Humanities Research Sustainability Vol. 2 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jhrs.v2i3.2244

Abstract

Background. The virtualization of sign language through artificial intelligence in social media platforms presents linguistic challenges that have not been widely explored, especially related to the accuracy of syntactic structures in digital contexts. These visual representations have the potential to reproduce grammatical misconceptions that impact the meaning and effectiveness of communication. Purpose. This study aims to explore how the syntactic structure of sign language is represented in a virtual format by AI systems used in social media such as TikTok, Instagram, and YouTube, as well as identify their accuracy and distortions. Method. The research uses an exploratory qualitative approach with a cross-platform case study design. Data were obtained from 30 virtual sign language videos and analyzed using visual-spatial linguistic frameworks and open coding techniques. Validation is carried out through thematic triangulation analysis and expert consultation. Results. The results show that the representation of syntactic structure varies greatly between platforms, with YouTube being superior in accuracy to TikTok. Factors such as the length of the video, the sophistication of the algorithm, and the presence of non-manual elements greatly affect the completeness of sentence structure in virtual sign language. Conclusion. The current representation of sign language by AI does not fully reflect the complex syntactic structure. A new approach is needed in the development of multimodal-based technologies that consider linguistic elements as a whole to make digital communication more inclusive and accurate.
Creative Economy as a Driver of Economic Growth in the Digitalization Era Pingki, Anandiya; Silamat, eddy; Hernawati, Hernawati; Rahman, Rashid
Journal of Multidisciplinary Sustainability Asean Vol. 2 No. 1 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijmsa.v2i1.1941

Abstract

Background. The creative economy has become one of the main sectors in the global economy, especially in the era of digitalization that allows the transformation of business models based on innovation and technology. The development of digital technology provides opportunities for creative industry players to expand market reach, improve production efficiency, and create greater added value. Countries with good digital infrastructure show more stable and competitive creative economy growth than countries with limited access to technology. Purpose. This study aims to analyze the role of digitalization in driving the growth of the creative economy and identify the factors that affect its success. In addition, this study also explores the contribution of the creative economy sector to the national economy by considering regulatory aspects and digital literacy. Method. The research method used is a quantitative approach with regression analysis and case studies on several creative economy sectors. Primary data is collected through surveys of creative industry players, while secondary data is obtained from official government reports and related academic publications. Results. The results show that digitalization has a significant influence on the growth of the creative economy, with the app and gaming sectors being the main examples of successful technology adoption. The creative economy sector, which is faster to adapt to digital technology, has experienced higher growth than sectors that still rely on conventional methods. Supportive regulations and a good level of digital literacy play an important role in ensuring the sustainability of the creative industry in the era of digitalization. Conclusion. The conclusion of this study emphasizes that the creative economy can be the main driver of economic growth if supported by the right policies and a conducive digital ecosystem. Digital transformation in the creative industry is not just a trend, but also a need to increase economic competitiveness on a global scale.