Filter By Year

1945 2024


Reset

Found 205 documents
Search Text-Based Approach

 16   17   18   19   20 
Text Mining for Sentiment Analysis of Social Media Regarding the Revision of the TNI Law Using Python by Utilizing the Lexicon Approach Ridwan, Ridwan; Ali, Hapzi; Lubis, Hendarman
Siber International Journal of Education Technology (SIJET) Vol. 2 No. 2 (2024): Siber International Journal of Education Technology (October 2024)
Publisher : Siber Nusantara Review & Yayasan Sinergi Inovasi Bersama (SIBER)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38035/sijet.v2i2.156

Abstract

This study aims to analyze public sentiment regarding the proposed revision of the Indonesian National Military (TNI) Law through social media, specifically Twitter. With the growing role of social media as a public sphere, it serves as a critical platform for expressing public opinions on national issues, including legal reforms. Using sentiment analysis, this research classifies Twitter posts into positive, neutral, or negative categories based on content related to the revision of the TNI Law. Data collection was carried out using the Twitter API (Tweepy), gathering 300 tweets using keywords related to the TNI Law revision. The analysis employed two methods: a lexicon-based approach using TextBlob and machine learning classification using Naive Bayes. The results reveal that the majority of the tweets express neutral sentiment (44.3%), followed by negative sentiment (28.3%) and positive sentiment (27.3%) based on TextBlob analysis. The Naive Bayes model demonstrated better sensitivity to negative sentiment, with 38.3% of tweets classified as negative. The findings suggest that public concern centers around the potential militarization of civil space, human rights violations, and threats to democracy. These concerns highlight the importance of transparent communication from the government regarding policy changes. Additionally, the research underscores the potential of natural language processing (NLP) and machine learning in monitoring public opinion in real time, which can serve as a valuable tool for policymakers in shaping responsive, data-driven legislation.
Hadis Bau Mulut Orang Berpuasa Ditinjau dari Pendekatan Bahasa: Analisis Matan secara Hakiki dan Majazi (The Smell of the Mouth of a Fasting Person from a Linguistic Approach: A Literal and Figurative Analysis of the Text) Sarah Mitha Amelia; Vera Seftia; Muhammad Sofyan Harahap; Laila Sari Masyhur
Journal of Innovative and Creativity Vol. 5 No. 2 (2025)
Publisher : Fakultas Ilmu Pendidikan Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/joecy.v5i2.314

Abstract

The hadith regarding the breath of a fasting person, which states that "The breath of a fasting person is more fragrant to Allah than the scent of musk" (HR. Bukhari and Muslim), is a significant text rich in linguistic and spiritual meaning. This study analyzes the matan (text) of the hadith through a linguistic approach, focusing on its hakiki (literal) and majazi (figurative) interpretations. Literally, the hadith refers to the physical phenomenon of the breath’s odor during fasting, but figuratively, the breath symbolizes sacrifice, sincerity, and devotion, which hold immense value in the sight of Allah, with musk representing spiritual excellence. The analysis examines linguistic devices such as metaphor and hyperbole, the cultural context of Arab society, and interpretations by scholars like Ibn Hajar al-Asqalani and al-Nawawi. The findings demonstrate that this linguistic approach not only enriches the understanding of the hadith’s meaning but also underscores its relevance in fostering sincerity and patience in worship. This study contributes to the development of language-based methodologies for hadith studies and strengthens the connection between linguistics and hadith scholarship within the Islamic intellectual tradition.
Analysis of Visitor Perceptions of Malang City Thematic Parks using a Text Mining Approach Vania, Nur Izza; Larasati, Aisyah; Chen, Yuh-Wen; Sholikha, Nikmatus
Spektrum Industri Vol. 23 No. 1 (2025): Spektrum Industri - April 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/si.v23i1.276

Abstract

Ruang Terbuka Hijau (RTH) play a crucial role in urban environments, not only supporting nature conservation but also fostering social interaction and contributing to economic growth. City parks, as representations of GOS, can be enhanced through thematic development and place branding to improve user engagement and functional value. This study aims to analyze visitor perceptions of thematic parks by identifying high-frequency keywords extracted from user-generated reviews. Text mining techniques were employed using Term Frequency-Inverse Document Frequency (TF-IDF) and Term Frequency-Relevance Frequency (TF-RF) methods, followed by text summarization using Cosine Similarity and Maximum Marginal Relevance (MMR). These methods effectively process large volumes of unstructured data to reveal meaningful insights. The analysis focused on three parks with the highest number of reviews: Alun-Alun Kota Malang (945 reviews), Taman Merjosari (552 reviews), and Alun-Alun Tugu (462 reviews). Keyword analysis showed prominent terms such as ‘tugu’, ‘olahraga’ (sports), and ‘anak’ (children) under both TF-IDF and TF-RF methods, with TF-RF emphasizing more context-specific vocabulary. Results indicate that Alun-Alun Tugu is perceived as a comfortable space near government offices featuring a lotus pond, Taman Merjosari is recognized for its sports facilities, and Alun-Alun Malang is identified as a child-friendly park with fountains. The study offers place branding recommendations by analyzing word associations in summarized user feedback. This study can contribute valuable insights for governments, architects, and urban designers in developing thematic parks that better reflect and accommodate user preferences.
Comprehensive and Innovative Language Learning Model with an Intercultural Communication Approach: A Systematic Review of Anecdotal Text Writing Lessons in Secondary Schools Sastri Br Rajaguk-guk; Ifan Iskandar; Muhammad Kamal bin Abdul Hakim
Jurnal Indonesia Sosial Sains Vol. 6 No. 3 (2025): Jurnal Indonesia Sosial Sains
Publisher : CV. Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/jiss.v6i3.1638

Abstract

This research investigates the effectiveness of various language learning models in improving students' skills in writing anecdotal texts at the secondary school level. The primary research problem addresses the gap in the existing teaching methods for anecdotal text writing and the need for innovative, intercultural, and project-based learning models. The objective of the research is to evaluate the impact of project-based learning, technology, and intercultural communication strategies on students' writing and critical thinking abilities. The research method used is a Systematic Literature Review (SLR), analyzing 50 relevant articles published in the last five years. Results show that project-based learning models and technology such as Grammarly and other digital media can improve students' writing and critical thinking skills. The intercultural approach also plays an important role in building cross-ethnic cultural understanding between teachers and students. However, there are limitations on the implementation of technology and generalization of research results, so further research is needed for the development of a more inclusive model.
Advancements in abstractive text summarization: a deep learning approach Suliman, Wesam; Yaseen, Amer; Hamada, Nuha
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i3.pp2315-2327

Abstract

With the rapid growth of data, text summarization has become vital for extracting key information efficiently. While extractive text summarization models are widely available, they often produce redundant outputs with limited capability of generating human-like summaries. Abstractive summarization, which generates new phrases and rephrases content, remains underexplored due to its complexity. This paper addresses this gap by developing an abstractive deep learning model using an encoder-decoder architecture supported with an attention mechanism. Trained on the dataset of Amazon Food Reviews, the model generates contextually rich and semantically accurate summaries. The model’s evaluation using BLEU and ROUGE metrics demonstrated promising results, with a score of 0.641 for BLEU, 0.520 for ROUGE-1, 0.345 for ROUGE-2, 0.461 for ROUGE-L and 0.428 for ROUGE-W, indicating coherence and structural integrity. This research highlights the potential of deep learning in addressing the limitations of classical methods and suggests opportunities for future advancements, such as scaling the model with larger datasets and integrating transformer-based techniques for improved summarization across diverse applications.
An Innovative Approach to Primary Education: Teaching Text Comprehension Through Neuro-Pedagogical Strategies Sotivoldiyeva Sarvinoz Khahramon Qizi
Jurnal Pendidikan Guru Sekolah Dasar Vol. 2 No. 4 (2025): August
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/pgsd.v2i4.1883

Abstract

This article presents the results of a scientific study aimed at enhancing primary school students’ reading and text comprehension skills through the application of neuro-pedagogical strategies. The research was conducted using control and experimental groups, where the effectiveness of traditional methods and neuro-pedagogical approaches was compared. The implementation of strategies such as semantic analysis, visual mapping, and clustering in the experimental group significantly improved students’ reading speed, comprehension ability, and motivation. The study emphasizes the activation of cognitive processes and the harmonization of left and right brain hemispheres to improve information retention and understanding. Statistical analysis confirmed the effectiveness of these innovative methods, and the results provide a strong foundation for reforming literacy instruction in Uzbekistan's primary education system. The article concludes with recommendations for wider implementation and future integration with international educational practices
The Effectiveness of Canva Media Using the Process Skills Approach in Learning Speech Text Writing Skills Arifah, Dinil; Charlina
Jurnal Pembelajaran Bahasa dan Sastra Vol. 4 No. 3 (2025): Mei 2025
Publisher : Raja Zulkarnain Education Foundation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55909/jpbs.v4i3.729

Abstract

This study aims to test the effectiveness of Canva media in teaching speech text writing skills using a process skills approach in class VIII MTs Pondok Pesantren Baituddin Petapahan. The background of this study is the low learning outcomes of students, which are caused by the dominance of conventional methods and the lack of visualization of materials in learning Indonesian. The study employed a quantitative approach with a quasi-experimental design involving two groups: the experimental group and the control group. The study population consisted of 32 students. The sample was set at 30 student. The research instrument was an essay test administered before and after the application of Canva media. A checklist was used to validate the scoring results and internal data analysis. Data on learning outcomes of speech text material for both pretest and posttest were analyzed using parametric inferential statistical procedures. The appropriate procedure for this is a one-sample t-test for pretest and posttest data and a paired sample t-test for comparative data between posttest and pretest results preceded by an assumption test. The results of the study: 1) the pretest for speech text writing skills for both research groups was relatively low; 2) the procedure for learning the skills of writing speech texts using the process skills approach in Canva media; 3) the posttest of the skills of writing speech texts for the experimental group in learning using Canva media is higher than the learning outcome group in the control using conventional media. Thus, the synthesis of this study is that Canva media is effective for use in learning speech material in class VIII.
Text Mining Customer Feedback: An Agglomerative Clustering Approach to Service Optimization Muthoharoh, Luluk
International Journal of Electronics and Communications Systems Vol. 5 No. 1 (2025): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v5i1.27188

Abstract

The increasing volume of customer support tickets in the e-commerce industry creates significant challenges in terms of efficiently managing unstructured text data. Traditional manual categorization methods are no longer efficient or scalable in managing well with growing data. This study proposes a text mining framework that integrates Natural Language Processing (NLP) techniques with Agglomerative Hierarchical Clustering (AHC) to automatically group customer support tickets based on their textual content similarity. The framework includes preprocessing (cleaning, tokenization, stopword removal, and lemmatization), followed by feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF), and dimensionality reduction using Principal Component Analysis (PCA). The clustered data is then visualized through dendrograms and evaluated using silhouette scores to determine the optimal number of clusters. Using a real-world dataset of 8.469 support tickets, the framework identified an optimal two-cluster configuration, distinguishing between general inquiries and specific error-related complaints. Unlike previous studies by using K-Means or DBSCAN, this framework leverage the hierarchical structure to capture nuanced textual similarities without requiring cluster number in the beginning. It also introduces integrated for evaluation and visualization pipeline tailored for operational customer use. However, because AHC has high computational complexity, this approach is more suitable for daily clustering batches than for real-time processing. Alternatives such as Mini-Batch K-Means also need to be considered for more efficient implementation. This study contributes to the development of an automated triage system and strategies for improving customer experience in digital platforms
Implementation of Interactive Media and the TaRL Approach to Improve Students’ Interest in Descriptive Text Learning Gultom, Katrin Ulina; Sari, Putri Lidiana Permata; Lubis, Wida Helmi; Hasibuan, Anita; Sirait, Lusi
Jurnal Pendidikan Tambusai Vol. 9 No. 2 (2025): Agustus
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v9i2.30113

Abstract

Penelitian tindakan kelas ini bertujuan untuk menguji apakah penggunaan media interaktif yang dikombinasikan dengan pendekatan Teaching at the Right Level (TaRL) dapat meningkatkan minat siswa dalam mempelajari teks deskriptif. Penelitian ini melibatkan 32 siswa kelas tujuh di SMP Negeri 1 Kisaran dan dilakukan selama dua siklus pembelajaran. Intervensi meliputi kuis interaktif, video, dan instruksi yang dibedakan berdasarkan tingkat kemampuan siswa. Data dikumpulkan melalui kuesioner, observasi, wawancara, dan dokumentasi. Temuan penelitian mengungkapkan bahwa minat belajar siswa meningkat dari 62% (sedang) pada pra-siklus menjadi 74% (tinggi) pada Siklus I, dan mencapai 87% (sangat tinggi) pada Siklus II. Siswa menjadi lebih aktif, percaya diri, dan antusias dalam berpartisipasi. Integrasi media interaktif dan TaRL menciptakan suasana kelas yang menarik dan adaptif. Ini mendorong pembelajaran kolaboratif dan membantu siswa memahami teks deskriptif dengan lebih efektif. Strategi ini terbukti menjadi alat yang ampuh dalam meningkatkan motivasi dan partisipasi siswa dalam pembelajaran bahasa Inggris.
The Effectiveness of Teaching at the Right Level (TARL) Approach on Learning Outcomes in Analytical Exposition Text Material for Grade XI of SMA Negeri 3 Kisaran Aryantini, Nanda Putri; Supiatman, Lis; Haini, Dalila; Lubis, Syaharuddin; Siregar, Tiopan Rahmat
Jurnal Pendidikan Tambusai Vol. 9 No. 2 (2025): Agustus
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v9i2.30776

Abstract

Penelitian ini bertujuan untuk menguji efektivitas pendekatan Teaching at the Right Level (TaRL) terhadap hasil belajar siswa dalam menulis teks Analytical Exposition. Dilakukan di kelas XI-6 di SMA Negeri 3 Kisaran dengan 36 siswa, penelitian ini menggunakan metode kuantitatif dengan menggunakan One Group Pretest-Posttest Design. Pendekatan TaRL diimplementasikan dengan mengelompokkan siswa berdasarkan tingkat kemampuan aktual mereka, yang memungkinkan instruksi yang lebih terarah dan adaptif. Data dikumpulkan melalui tes menulis dan dianalisis menggunakan uji normalitas Shapiro-Wilk dan analisis skor N-Gain. Hasilnya menunjukkan peningkatan yang signifikan dalam skor rata-rata dari 66,25 (pretest) menjadi 84,72 (posttest), dengan rata-rata N-Gain 0,550, dikategorikan sedang. Temuan ini menunjukkan bahwa TaRL cukup efektif dalam meningkatkan keterampilan menulis siswa dan dalam mengatasi kesenjangan pembelajaran di kelas heterogen. TaRL juga mendorong keterlibatan, motivasi, dan pembelajaran mandiri siswa. Oleh karena itu, direkomendasikan untuk implementasi yang lebih luas dalam instruksi yang dibedakan.

Page 18 of 21 | Total Record : 205

 16   17   18   19   20