خواندن متن کامل
۱۴ صفحه · خواندن آنلاین · خارج از سقف مطالعه
چکیده
Introduction Deception elicits measurable cognitive and linguistic changes, yet accurately identifying deceptive language in high-stakes environments remains a persistent challenge. Although natural language processing (NLP) and machine learning (ML) techniques have shown promise in detecting misinformation and low-stakes deception, their performance on spontaneous, stress-induced speech remains poorly understood. This study investigates linguistic markers of deception and evaluates the performance of supervised ML models and a knowledge-grounded language model, FranklinAsk™, across both synthetic and real-world datasets. Methods Linguistic analyses were conducted on responses from a National Center for Credibility Assessment (NCCA) military training exercise involving truthful and deceptive participants. A synthetic dataset was generated using MOSTLYAI to provide a balanced corpus for ML training. Linguistic features were extracted using pretrained NLP models, and supervised classifiers, including logistic regression, Random Forest, Naïve Bayes, and Support Vector Machine (SVM), were trained using LIWC-22 features with 10-fold cross-validation. The FranklinAsk™ RAG system was evaluated using the same participant responses to compare knowledge-grounded reasoning with statistical learning. Results Two linguistic features, cardinal numbers (nominal p = 0.041) and particles (nominal p = 0.0486), reached the unadjusted significance threshold, each with a moderate effect size ( d = 0.55); neither remained statistically significant after Benjamini-Hochberg FDR correction (adjusted p = 0.668 for both). No significant sentiment differences were observed. On the synthetic dataset, logistic regression performed best (F1 = 0.930; ROC AUC = 0.978), but all supervised models showed substantial performance declines when applied to the real-world dataset. In contrast, FranklinAsk™ achieved the highest F1-score (0.519), highest accuracy (0.487), and second-highest recall (0.700) on the military exercise data. Discussion These findings highlight the limited generalizability of synthetic-trained deception models to real-world, high-stakes communication and motivate further investigation of knowledge-grounded language models as an alternative approach when labeled real-world training data are limited. Future research should prioritize expanding ecologically valid datasets and exploring hybrid approaches that combine statistical modeling with knowledge-grounded reasoning.
Miller, K., Chu, A., Reed, A., McCord, Z., Argentine, E., Allen, J., Coggins, P., Pollina, D., Senter, S., Shazly, T., Uline, M., & Boltin, N. (2026). Leveraging natural language processing, machine learning, and a knowledge-grounded language model to detect linguistic markers of deception. Frontiers in Artificial Intelligence, 9, 1965099. https://doi.org/10.3389/frai.2026.1965099
با احترام و بدون توهین، تحقیر، برچسبزنی یا حملهی شخصی با دیگران گفتگو کنید.
از نوشتن هرگونه اطلاعات هویتی یا قابلشناسایی مراجعان، بیماران یا اشخاص ثالث، از جمله نام، شمارهی تماس، تصویر، نشانی، محل کار یا جزئیات منحصربهفرد پرونده خودداری کنید.
اگر دربارهی یک تجربهی بالینی سؤال میکنید، اطلاعات را تا حد ممکن بینام و کلی بیان کنید تا امکان شناسایی فرد وجود نداشته باشد.
این بخش برای یادگیری و گفتوگوی علمی است و جایگزین ارزیابی، تشخیص، مشاوره یا رواندرمانی شخصی نیست.
در شرایط بحران یا خطر آسیب به خود یا دیگران، به این بخش اتکا نکنید و برای دریافت کمک فوری با اورژانس اجتماعی ۱۲۳ یا صدای مشاور بهزیستی ۱۴۸۰ تماس بگیرید.
انتشار تبلیغات، معرفی خدمات شخصی، شمارهی تلفن، شناسهی شبکههای اجتماعی، پیوند تبلیغاتی یا درخواست جذب مراجع در این بخش مجاز نیست.
در بیان ادعاهای علمی، بهویژه دربارهی اثربخشی درمانها، تشخیص یا یافتههای پژوهشی، تا حد امکان نام منبع معتبر، مقاله یا راهنمای علمی را ذکر کنید.
از ارائهی تشخیص قطعی، تجویز درمان یا دارو و توصیههای بالینی شخصی به سایر کاربران خودداری کنید.
پاسخهایی که کارشناسان فکر بنیان میدهند با برچسب «پاسخ فکر بنیان» یا «کارشناس فکر بنیان» نمایش داده میشوند و سایر نوشتهها بیانگر نظر کاربران هستند.
گزارش نوشتهی نامناسب: اگر نوشتهای حاوی نقض محرمانگی، محتوای آسیبزا، توهین، تبلیغ یا تخلف از این قوانین است، گزینهی «گزارش» را انتخاب کنید تا تیم سایت بررسی کند.
Background: Awareness of youth-friendly sexual and reproductive health services (YFSRHS) is an important starting point for enabling young people to identify and seek appropriate sexual and reproductive health information and care. However, awareness of these services may vary across settings, including higher education institutions. Objective: To determine the level of awareness of YFSRHS among undergraduate students at Saint Augustine University of Tanzania (SAUT), Malimbe Campus. Methods: A quantitative descriptive cross-sectional study was conducted among undergraduate students at SAUT Malimbe Campus. Data were collected using a structured, self-administered questionnaire. Of 109 questionnaires distributed, 108 completed questionnaires were included in the analysis. Descriptive statistics were used to summarize students’ awareness and reported sources of information. Results: Of the 108 respondents, 96 (88.9%) reported having heard of YFSRHS, while 12 (11.1%) had not. Social media was the most frequently reported source of information (44.0%), followed by friends or peers (41.0%) and health facilities (36.0%). University programmes and posters or advertisements were reported less frequently. Conclusion: Most respondents had heard of YFSRHS, with social media and peer networks serving as prominent information channels. Strengthening accurate information through these channels, alongside university-based communication, may help address the awareness gap among students who remain unreached.
Assessment in Arabic language learning as a foreign language (Arabic as a Foreign Language) is currently undergoing a significant paradigm shift. This transformation is influenced by the development of digital technology, the utilization of Artificial Intelligence (AI), and the implementation of the Merdeka Curriculum in Indonesia, which emphasizes flexibility, differentiation, and learning personalization. This article presents a Systematic Literature Review (SLR) aimed at identifying, examining, and synthesizing developments, innovations, methodological approaches, and various challenges in the assessment of the four Arabic language skills, namely listening, speaking, reading, and writing, during the period from 2020 to early 2026. The review employed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol to identify and analyze relevant literature. The findings indicate a shift from conventional evaluation systems based on discrete tests toward the implementation of Technology-Enhanced Assessment (TEA) and more authentic forms of assessment. The literature synthesis reveals several key findings. First, diagnostic assessment, encompassing both cognitive and non-cognitive aspects, plays an important role in designing differentiated learning within the framework of the Merdeka Curriculum. Second, the development of assessment instruments for Arabic language maharah is increasingly oriented toward measuring higher-order thinking skills (Higher Order Thinking Skills/HOTS). Third, the utilization of Generative AI, including ChatGPT, as well as various gamification-based learning platforms, has introduced new approaches to providing faster, more adaptive, and interactive feedback. Based on the synthesis, the effectiveness of modern assessment is not determined solely by the sophistication of the technology employed, but also by the alignment between technology and pedagogical objectives, the transparency of assessment procedures, and its ability to comprehensively represent learners' communicative competence while maintaining the principles of academic integrity.
Over the last decade, there has been a visible surge of students participating in and leading different forms of activism. Following the cultural reckoning of 2020, the United States saw a rise in awareness and engagement in activism among young individuals. Continuing this trend, higher education institutions have seen an increase in on-campus demonstrations in recent years. Given the recent increase in activism, political engagement, and the globalization of social issues, this study examined how attitudes, beliefs, individual factors, and prior behaviors relate to undergraduate students’ willingness to engage in different forms of activism (i.e., conventional and high-risk). Across both forms of activism, institutional advocacy (i.e., the behavioral targeting of institutional racism) was the most consistent unique predictor of a student's willingness to engage in activism. Need for cognition and individual advocacy were significantly and positively related to conventional activism, whereas political orientation was negatively related to it. Social justice orientation was significantly and negatively related to high-risk activism.
Social capital represents a relational resource developed through trust, professional networks, collaboration, peer support, and knowledge exchange. In the context of Social Studies Education, social capital can support teachers in accessing information, experiences, and professional resources relevant to professional development and instructional planning. This study aims to analyze the conceptualization of teachers’ social capital, identify its dimensions in relation to teacher professionalism, and examine its relevance to Social Studies teaching practices and instructional planning. The study employs a Systematic Literature Review (SLR) approach guided by the PRISMA 2020 framework. The literature analyzed consists of scholarly publications published between 2023 and 2026 in Indonesian and English that met the established inclusion criteria. The data were analyzed through thematic synthesis based on conceptual dimensions, forms of professional relationships, and their contributions to teaching practices. The synthesis indicates that social capital facilitates teachers’ access to information, experiences, feedback, and professional support through networks and collaborative relationships. These resources can strengthen professional learning and pedagogical decision-making relevant to Social Studies instructional planning. However, empirical evidence directly linking teachers’ social capital to the quality of Social Studies instructional planning remains limited. These findings highlight the need for further research on how social capital can be translated into improvements in the quality of Social Studies instructional planning components.
Assessment in Natural and Social Sciences (IPAS) at the elementary school level needs to document students’ knowledge, process skills, and character development continuously rather than relying solely on written test results. This study aimed to develop a flexible portfolio assessment instrument, determine its validity and practicality, and examine its perceived usefulness based on the fourth-grade teacher’s assessment at SD Negeri 075027 Silima Omo. The study employed a Research and Development (R&D) approach using the 4D model, comprising Define, Design, Develop, and Disseminate stages. The participants included three expert validators, one fourth-grade teacher, and 22 students, with 10 students participating in the small-group trial. The resulting product was a printed portfolio assessment instrument comprising seven integrated components. Validation results yielded mean scores of 3.83 for design, 3.75 for language, and 4.00 for evaluation on a four-point scale. The practicality score increased from 62.50% to 93.75%, while perceived usefulness increased from 64.29% to 85.71%. The small-group trial produced a mean portfolio score of 80.80. The instrument was considered suitable for use; however, inter-rater reliability and its effectiveness in improving learning outcomes require further empirical investigation. ABSTRAK Penilaian pembelajaran Ilmu Pengetahuan Alam dan Sosial (IPAS) di sekolah dasar perlu mencakup perkembangan pengetahuan, keterampilan proses, dan karakter murid secara berkelanjutan, bukan hanya berorientasi pada hasil tes tertulis. Penelitian ini bertujuan mengembangkan instrumen penilaian portofolio yang fleksibel, mengetahui kelayakan dan kepraktisannya, serta mengidentifikasi kebermanfaatannya berdasarkan persepsi guru kelas IV di SD Negeri 075027 Silima Omo. Penelitian menggunakan metode Research and Development (R&D) dengan model 4D yang meliputi tahap Define, Design, Develop, dan Disseminate. Subjek penelitian terdiri atas tiga validator ahli, satu guru kelas IV, dan 22 murid, dengan 10 murid sebagai subjek uji coba kelompok kecil. Produk yang dikembangkan berupa instrumen portofolio berbasis cetak dengan tujuh komponen terintegrasi. Hasil validasi menunjukkan skor rata-rata ahli desain 3,83, ahli bahasa 3,75, dan ahli evaluasi 4,00 pada skala empat. Persentase kepraktisan meningkat dari 62,50% menjadi 93,75%, sedangkan kebermanfaatan berdasarkan persepsi guru meningkat dari 64,29% menjadi 85,71%. Rata-rata nilai portofolio kelompok kecil mencapai 80,80. Instrumen dinyatakan layak digunakan, meskipun reliabilitas antarpenilai dan keefektifan terhadap hasil belajar masih memerlukan pengujian lebih lanjut.