IKADO E-Journal (Institut Informatika Indonesia)
Not a member yet
470 research outputs found
Sort by
Peningkatan Daya Saing Produk Olahan Jamur KWT Rumah Jamur Takalar Melalui Penerapan Manajemen Pemasaran dan Inovasi Kemasan
No full textKelompok Wanita Tani (KWT) Rumah Jamur Takalar menghadapi tantangan dalam pemasaran dan kemasan produk olahan jamur mereka. Kegiatan pengabdian masyarakat ini bertujuan meningkatkan daya saing produk melalui penerapan manajemen pemasaran dan inovasi kemasan. Program dilaksanakan selama tahun anggaran 2024. Metode yang digunakan meliputi sosialisasi program, pelatihan manajemen pemasaran digital dan inovasi kemasan, pengembangan website, redesain kemasan produk, serta pendampingan dan evaluasi. Hasil menunjukkan peningkatan signifikan dalam visibilitas produk melalui website www.rumahjamurtakalar.com, peningkatan daya tarik kemasan, dan pemahaman anggota KWT tentang strategi pemasaran digital. Sebanyak 87% peserta melaporkan peningkatan pemahaman tentang pentingnya kemasan dan manfaat website untuk pemasaran. Program ini berhasil meningkatkan daya saing produk KWT Rumah Jamur Takalar dan berpotensi menjadi model pemberdayaan ekonomi lokal yang berkelanjutan
Analisis Pelaksanaan Pelatihan Infografis Data Dengan Microsoft Excel Bagi Guru Kabupaten/Kota Pasuruan
No full textDalam era teknologi yang berkembang pesat, pemanfaatan perangkat lunak seperti Microsoft Excel menjadi krusial, terutama di bidang pendidikan. Meski populer, sebagian besar guru di Kabupaten/ Kota Pasuruan belum sepenuhnya memaksimalkan Microsoft Excel untuk infografis data. Tim Pengabdian Kepada Masyarakat (PKM) mengusulkan kolaborasi dalam "Pelatihan Infografis data dengan Microsoft Excel Bagi Guru Kabupaten/Kota Pasuruan" tahun 2024, bertujuan meningkatkan pemahaman dan keterampilan guru sejalan dengan visi lembaga untuk meningkatkan mutu pendidikan. Pelatihan difokuskan pada pembuatan infografis data melalui fungsi Excel, meningkatkan keterampilan guru di Kabupaten/Kota Pasuruan dalam memanfaatkan perangkat lunak ini. Pelatihan ini telah dilaksanakan oleh tim secara luring pada hari Sabtu, 13 Juli 2024 bertempat di SMPN 1 Bangil. Pelatihan diikuti oleh 24 guru di beberapa SD di Pasuruan dan berjalan lancar. Pada saat pelatihan dilakukan penilaian dengan pretest dan posttest, berdasarkan hasil tes tersebut akan dilakukan pengujian menggunakan uji t, dengan hasil yang diperoleh adalah nilai thitung lebih besar dari ttabel dan terjadi kenaikan rata-rata nilai pretest (30,83) ke posttest (67,92) yang menunjukkan bahwa pelatihan yang dilakukan berhasil meningkatkan pemahaman dan kemampuan peserta, yang ditunjukkan oleh kenaikan nilai. Hasil survei evaluasi kegiatan menunjukkan bahwa secara keseluruhan, peserta memberikan penilaian yang sangat positif terhadap kegiatan PKM ini, dengan rata-rata poin keseluruhan sebesar 4.8. Hal tersebut menunjukkan bahwa materi dan penyampaian dalam kegiatan ini berhasil menarik minat dan memenuhi kebutuhan peserta, dengan mayoritas merasa antusias, termotivasi, dan mampu meningkatkan kemampuan mereka dalam membuat infografis data menggunakan Microsoft Excel
The Influence of User Experience on Customer Engagement in Grab Application: A SERVQUAL Approach for Service Quality Evaluation
No full textDigital transformation has fundamentally changed transportation services, yet existing research has predominantly applied traditional SERVQUAL frameworks without systematic integration with contemporary User Experience theories for Generation Z users. Limited research exists specifically investigating ride-hailing platforms among digital-native populations, creating a critical gap in understanding how generational characteristics influence service quality evaluation patterns. This study investigates the influence of User Experience (UX) on Customer Engagement (CE) in the Grab application among Generation Z users, utilizing the Service Quality (SERVQUAL) framework adapted for digital contexts. The research employed a quantitative approach with purposive sampling targeting 150 active Grab users aged 13-28 years who met specific usage criteria. Data collection utilized online questionnaires measuring five SERVQUAL dimensions, User Experience, and Customer Engagement variables through Likert scales, analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Results revealed fundamental shifts in how Generation Z users evaluate digital service quality. Among SERVQUAL dimensions, only visual interface elements (Tangibles) significantly influenced User Experience (β = 0.586, p = 0.001), while traditional interpersonal service dimensions showed no meaningful impact. User Experience demonstrated exceptionally strong influence on Customer Engagement (β = 0.945, p < 0.001), with the model explaining 89.3% of variance. These findings indicate that conventional service quality models require substantial adaptation for digital service contexts, particularly for Generation Z users who prioritize aesthetic design and interface functionality over traditional service elements. The study contributes to understanding how digital-native consumers evaluate technology-mediated transportation services, suggesting that service providers should focus primarily on user interface design and overall experience architecture to enhance customer engagement in the digital economy
Hybrid Framework Addressing Imbalanced Data in Indonesian E-commerce Multimodal Sentiment Analysis
No full textSevere class imbalance in Indonesian language e-commerce reviews hampers the detection of customer grievances, because about 88 percent of testimonials are positive whereas under one percent are negative. This study designs a simple yet effective framework to mitigate that bias. The data 2,611 authentic reviews covering electronics, fashion, and household goods and reflecting online shopping patterns were cleaned, structured, and represented using a combination of TF-IDF weighting and Word2Vec embeddings to condense meaning. Imbalance was addressed with the Synthetic Minority Oversampling Technique integrated with Edited Nearest Neighbour, equalising the proportions of positive, neutral, and negative classes. A Support Vector Machine was trained with five-fold cross-validation and benchmarked against Multinomial Naïve Bayes and a Decision Tree classifier. Experiments yielded 94.6 percent accuracy and a 94.8 percent F1-score, while precision for the negative class reached 100 percent, outperforming conventional approaches by up to twelve percent. The contribution of this research is the demonstration that minimal pre-processing, lightweight feature extraction, and targeted data balancing can markedly enhance grievance detection without resorting to complex model architectures. Practically, the framework enables online merchants to monitor service quality and respond to customer issues in real time, and it can be integrated into recommendation engines and business dashboards to accelerate data-driven decision making and strengthen transparency for stakeholders. Academically, the findings open avenues for integrating large language models, temporal analysis, and cross-domain adaptation to enrich the global e-commerce ecosystem
An Integrated Framework for Automated Resume Screening Using RoBERTa, Random Forest and Explainable AI
No full textThe resume screening process is a critical stage in recruitment, yet conventional methods and traditional applicant tracking systems (ATS) often rely on manual review or keyword matching, resulting in slow, biased, and less objective evaluations. This study proposes an integrated automated screening system that combines RoBERTa for contextual feature extraction, Random Forest for candidate classification, and SHAP-based Explainable AI for interpretable decisions, enhancing transparency, efficiency, and fairness beyond traditional ATS. The dataset consists of real resumes and synthetically generated ones designed to mimic the distribution of real data, with K-means clustering used to establish labeling thresholds. Experimental results show that RoBERTa achieved an F1 Score of 81.08% in feature extraction, while Random Forest reached 96% accuracy in suitability classification. SHAP-based explanations provide insights into feature contributions for each prediction, offering an actionable understanding for recruiters. This integrated framework not only improves the efficiency and fairness of resume screening but also demonstrates a practical application of explainable AI in recruitment
Peningkatan Literasi Digital dan Keamanan Berbasis Etika pada Guru: Studi Kasus Sosialisasi Etika dan Keamanan Media Sosial di SMA Negeri 1 Batu
No full textKegiatan pengabdian masyarakat ini bertujuan meningkatkan literasi digital dan praktik keamanan bermedia sosial yang berorientasi etika bagi guru di SMA Negeri 1 Batu. Kegiatan dilaksanakan secara tatap muka pada 16 Juni 2025 dengan partisipasi sekitar 40 guru. Pendekatan yang digunakan berupa sosialisasi dan pelatihan aplikatif (workshop) berdurasi ±2,5 jam yang mengintegrasikan paparan konseptual, demonstrasi teknis (manajemen kata sandi, pengaturan privasi, verifikasi dua langkah, serta identifikasi serangan phishing), dan diskusi studi kasus. Evaluasi dilaksanakan melalui instrumen pre-test dan post-test yang dilengkapi kuesioner umpan balik untuk mengukur perubahan pengetahuan dan kesiapan penerapan. Hasil evaluasi menunjukkan adanya peningkatan pemahaman konseptual serta kesiapan praktis peserta dalam menerapkan langkah-langkah keamanan digital dasar, disertai respons positif terhadap relevansi dan aplikabilitas materi. Peserta mengusulkan perluasan cakupan materi misalnya aspek tindak pidana siber dan pemanfaatan kecerdasan buatan dalam konteks pendidikan serta rekomendasi untuk mekanisme pendampingan berkala. Kesimpulannya, intervensi ini efektif dalam meningkatkan kesadaran etika dan kapasitas dasar keamanan digital di kalangan guru; untuk memastikan keberlanjutan dan penguatan kompetensi, disarankan pengembangan modul lanjutan, monitoring berkala, dan evaluasi kuantitatif yang lebih komprehensif
The Impact and Challenges of Parak Acil Online in Banjarmasin’s E-Government Transformation
Full text linkThe rapid development of information and communication technology (ICT) in the Industrial 4.0 era has transformed governance globally, including in Indonesia, where e-government initiatives are a national priority. This study examines the implementation and impact of Parak Acil Online, a digital platform introduced by the Population and Civil Registration Office (Disdukcapil) in Banjarmasin, aimed at streamlining public service delivery for population documents such as e-KTP, family cards, and birth certificates. The research employs a qualitative approach, guided by the E-GovQual and Delone & McLean IS Success models, to evaluate the platform’s performance across six dimensions: Ease of Use, Trust, Functionality of Interaction Environment, Reliability, Content and Appearance, and Citizen Support. Findings reveal that Parak Acil Online significantly enhances service accessibility, transparency, and efficiency. However, challenges persist, including digital literacy gaps, infrastructure limitations, and system performance issues, such as delays and occasional crashes during peak usage. Respondents highlighted the need for improved accessibility features, real-time support tools, and enhanced backend optimization. This study contributes by providing a comprehensive evaluation framework and actionable insights for optimizing e-government platforms in developing regions. By addressing these challenges, Parak Acil Online can achieve sustainable digital transformation and serve as a benchmark for equitable public service delivery in Indonesia and beyond
AI-based Personalization of Social Media Thumbnails Using the Stacked ID Embedding Method
No full textSocial media content creators find it hard to make thumbnails shine on Instagram, YouTube, and TikTok, where graphic design skills happen to be a significant bottleneck. To address this issue, scientists developed a text-based image generation model, PotionPix, that allows users to generate thumbnails on the fly based on text prompts and relevant images via a "Stacked ID Embedding" method. This method combines multiple identity embeddings—e.g., user interests, platform context, and content genre—into one vector representation to guide the AI to create more personalized and contextually appealing thumbnails. The system integrates a diffusion-based image generator with the stacked embedding vectors to enable dynamic adaptation to different user intents. In tests, it was observed that how relevant and good the generated thumbnails were very much a function of how specific the input image was and how clear the prompt was. However, since the AI model used was not fine-tuned on the task of thumbnail generation specifically, the visual outputs sometimes were generic and lacked the strong call-to-action elements usually found in high-performing thumbnails. Despite this constraint, the usability test conducted with 120 respondents showed promising results—83.8% of the participants confirmed that PotionPix was indeed assistive in the thumbnail design process, particularly in terms of time and effort savings. The findings show the promise of AI-driven tools in enabling the democratization of design tasks for social media content creators, as well as suggesting future work in model fine-tuning for more domain-specific outcome
Pendekatan Edukatif Dalam Penyusunan Elemen Identitas Visual: Studi Kasus Penyuluhan Pada UMKM Aisyah Muhammadiyah
No full textPenyuluhan strategi branding melalui identitas visual merupakan langkah strategis untuk memberdayakan UMKM agar mampu bersaing di era digital. Program ini menyusun bahan penyuluhan yang edukatif dengan fokus pada elemen utama branding, seperti desain logo, narasi merek, dan strategi media sosial. Pendekatan berbasis lokalitas dan visual mempermudah pemahaman audiens awam, yang sebelumnya kesulitan menerapkan konsep branding digital. Metode melalui tahapan berupa identifikasi kebutuhan, perancangan materi edukasi, dan mengevaluasi kelayakan materi penyuluhan. Hasil simulasi penyuluhan menunjukkan bahwa pendekatan ini meningkatkan pemahaman hingga 85%, meskipun tantangan berupa keterbatasan teknis peserta masih perlu diatasi. Penelitian ini menegaskan pentingnya bahan penyuluhan yang relevan, praktis, dan inklusif untuk memperkuat daya saing UMKM dan mendorong penerapan digital branding yang efektif
Iklan Rokok Elektrik Sampoerna IQOS Dalam Kajian Feminitas
No full textFeminitas dalam iklan rokok elektrik Sampoerna IQOS episode A World of Flavor dikaji dalam penelitian ini melalui pendekatan sinematografi dan teori Femininity Ideology Scale (FIS) dari Levant et al. (2017). Objek analisis mencakup elemen visual seperti warna, pencahayaan, gerakan kamera, narasi, dan simbolisme yang digunakan untuk membentuk citra feminin. Metode yang digunakan adalah analisis visual berdasarkan teori Gillian Rose dan skema monaco, serta pengukuran lima dimensi feminitas menurut FIS: Stereotypic Image and Activities, Dependency/Deference, Purity, Caretaking, dan Emotionality. Hasil menunjukkan bahwa kelima dimensi tersebut direpresentasikan secara visual dan naratif melalui penggunaan warna pastel, transisi halus, musik latar lembut, serta simbol bunga. Representasi ini mencerminkan kelembutan, keanggunan, dan emosionalitas yang selaras dengan ideologi feminitas modern. Iklan ini berhasil memadukan nilai feminin tradisional dan kontemporer, sekaligus mencerminkan perubahan dalam cara feminitas divisualisasikan di industri periklanan. Namun, penelitian juga menyoroti pentingnya aspek etika dalam representasi gender pada iklan produk berisiko. Secara keseluruhan, penelitian ini memberikan wawasan baru tentang dinamika antara estetika, gender, dan komunikasi visual dalam iklan modern