Search Articles & Publications

Showing 20 articles found for "Streaming"

Pengaruh Real Time Interactivity dan Promotion Incentive Information terhadap Impulse Buying Behavior dengan Mediasi Perceived Trust Fashion di Live TikTok

Ricky Martin, Heriyadi, Bintoro Bagus Purmono, Wenny Pebrianti
Abstract: The growing dominance of impulse buying within TikTok's live streaming commerce, particularly in the Fashion product segment, signifies a transformation in digital consumer behavior influenced by the dynamics of real-time… e interactivity and incentive-based promotional strategies. This study empirically examines the effects of real-time interactivity and promotion incentive information on impulse buying behavior, with perceived trust serving as a mediating variable that explains the psychological pathway between digital stimuli and spontaneous purchase decisions. Employing a quantitative approach with an associative causal design, data were collected from 231 active TikTok users in Indonesia and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) version 4.0. The analysis reveals that both exogenous variables significantly enhance the tendency for impulsive purchases, both directly and indirectly through the mediation of perceived trust. Responsive real-time interactions and exclusive, time-sensitive promotions effectively foster consumer trust in sellers, which subsequently accelerates unplanned buying behavior. These findings advance theoretical discourse in digital marketing literature by emphasizing the critical integration of interactivity, promotional stimuli, and affective trust mechanisms in shaping purchasing decisions within persuasive and simultaneous digital environments. The practical implications of this study offer strategic insights for businesses, encouraging the optimization of interactive features and promotional tactics to establish credibility and drive instant sales conversions in the context of e-commerce live streaming.

A COMPARATIVE ANALYSIS OF OPTIMIZED NEURAL NETWORK AND LARGE-SCALE LANGUAGE MODELS FOR MUSIC GENRE CLASSIFICATION

Marzuqi, Ahmad Naufal Luthfan, Nastiti , Vinna Rahmayanti Setyaning
Abstract: Abstract: The rapid growth of the digital music industry requires accurate music genre classification systems to enhance user experience in streaming services. This study compares a domain-specific Long Short-Term Memory… (LSTM) network with three Large Language Models (LLMs)—HuBERT, WavLM, and WAV2Vec 2.0—for Music Genre Classification (MGC). The LSTM model was trained using Mel-spectrograms transformed from the GTZAN dataset, while the LLMs were fine-tuned using a smaller set of raw audio samples due to computational constraints. All models were tested on datasets with identical genre labels to ensure a fair evaluation. Results show that the LSTM model achieved the highest accuracy of 97.10%, outperforming HuBERT (86.00%), WavLM (83.00%), and WAV2Vec 2.0 (80.00%). The LSTM demonstrated superior generalization and stability without overfitting, while the LLMs struggled to differentiate between genres with similar acoustic characteristics. These findings indicate that general-purpose pre-trained models, although powerful, are less effective in music-specific tasks due to domain mismatch. Therefore, incorporating music-specific features and architectures remains essential for achieving higher accuracy and reliability in automatic genre classification systems. Keywords: audio large language models; comparative deep learning; music genre classification.   Abstrak: Pertumbuhan industri musik digital yang pesat menuntut sistem klasifikasi genre musik yang akurat untuk meningkatkan pengalaman pengguna dalam layanan streaming. Penelitian ini dilatarbelakangi oleh perkembangan pesat model pembelajaran mendalam, khususnya jaringan LSTM dan model bahasa berskala besar LLM seperti HuBERT, WavLM, dan WAV2Vec 2.0, yang telah menunjukkan kemampuan representasi audio yang kuat. Tujuan penelitian ini ini membandingkan jaringan Long Short-Term Memory (LSTM) khusus domain dengan tiga model Large Language Models (LLM)—HuBERT, WavLM, dan WAV2Vec 2.0—untuk tugas Klasifikasi Genre Musik (MGC). Metode penelitian melibatkan pelatihan LSTM menggunakan data Mel-spectrogram hasil transformasi dari dataset GTZAN, sementara LLM disesuaikan (fine-tuning) menggunakan data audio mentah dalam jumlah lebih kecil karena keterbatasan komputasi. Seluruh model diuji pada dataset dengan label genre yang sama untuk memastikan evaluasi yang adil. Hasil penelitian menunjukkan bahwa model LSTM mencapai akurasi tertinggi sebesar 97,10%, sedangkan model HuBERT, WavLM, dan WAV2Vec 2.0 masing-masing memperoleh 86,00%, 83,00%, dan 80,00%. Model LSTM menunjukkan kemampuan generalisasi yang lebih baik tanpa overfitting, sedangkan model LLM cenderung kesulitan membedakan genre dengan karakteristik akustik yang mirip. Kesimpulan penelitian ini adalah ketidaksesuaian domain secara signifikan membatasi performa model umum saat diterapkan pada tugas berbasis musik. Oleh karena itu, penggunaan fitur dan arsitektur khusus musik sangat penting dalam membangun sistem klasifikasi genre yang lebih akurat. Kata kunci: klasifikasi genre musik; model bahasa besar; perbandingan pembelajaran mendalam.

MACHINE LEARNING CONTENT-BASED FILTERING WOMEN EMPOWERING RECOMMENDATIONS ON YOUTUBE

Yuliana, Yuliana, Mira, Mira, Hari Kristianto, Aloysius
Abstract: Abstract: YouTube is one of the most popular video streaming platforms, but it has constraints that can cause problems when clients have difficulty finding content according to their wishes. The main objective of this study… udy is to increase user capacity in viewing content specifically in the field of women's empowerment. By using content-based filtering techniques, the system will analyze user preferences and interests through recommendations for women's empowerment content. The data source is via the YouTube API and is analyzed using PHP programming content-based filtering techniques. The system's recommendations provide a list of women's empowerment content with a user request display. The results of the research evaluation obtained a precision value of 62%, meaning that the recommendations match the topic being searched for, namely women's empowerment. The recall value of 84% indicates that the system has succeeded in finding relations from the database. The f1-score value of 72% indicates that there is a balance between precision and recall, meaning that a system is needed that is not only accurate but also complete. While the cosine value shows a score of 0.7071 approaching the maximum value (1.0). The recommendation of the content-based filtering method produces quite effective women's empowerment content. Keywords: content-based filtering, recommendations, women Empowerment, youtube  

EVALUATION OF HYBRID MOVIE RECOMMENDATION SYSTEM BASED ON NEURAL NETWORKS

Widjaja, William, Robert, Johanes Terang Kita Perangin - Angin
Abstract: Abstract: Recommendation systems are becoming increasingly important with the growth of streaming platforms. The purpose of this study is to compare the performance of Content-Based Filtering, Neural Collaborative Filtering,… ing, and a combination of both in a movie recommendation system. The method used in this study involves retrieving movie details from the TMDB API and ratings from the MovieLens 32M Dataset (2010-2023). Each model's performance is evaluated using evaluation metrics such as RMSE and MAE. The results of this study indicate that Neural Collaborative Filtering achieves the best prediction performance (RMSE = 0.785423, MAE = 0.581262), followed by the hybrid model (RMSE = 0.800863, MAE = 0.660872), while Content-Based Filtering produces low performance and limits the capabilities of the hybrid model. In conclusion, these findings highlight the superiority of latent feature-based models such as NCF that learn directly from user interaction patterns over content-based approaches in the context of modern recommendation systems. Keywords: content-based filtering; hybrid filtering; movie recommendation; neural collaborative filtering.   Abstrak: Sistem rekomendasi menjadi semakin penting seiring berkembangnya platform streaming. Tujuan dari penelitian ini adalah membandingkan kinerja Content-Based Filtering, Neural Collaborative Filtering dan kombinasi keduanya dalam sistem rekomendasi film. Metode yang digunakan dalam penelitian ini melibatkan pengambilan detail film dari TMDB API dan rating dari dataset MovieLens 32M Dataset (2010-2023). Setiap peforma model dievaluasi dengan menggunakan metrik evaluasi seperti RMSE dan MAE. Hasil dari penelitian ini menunjukkan bahwa Neural Collaborative Filtering mencapai kinerja prediksi terbaik (RMSE = 0.785423, MAE = 0.581262), diikuti oleh model hybrid (RMSE = 0.800863, MAE = 0.660872), sementara Content-Based Filtering menghasilkankan peforma yang rendah dan membatasi kemampuan model hybrid. Kesimpulannya, penelitian ini menyoroti superiotas model berbasis latent feature seperti NCF yang belajar langsung dari pola interaksi pengguna dibandingkan pendekatan berbasis konten dalam konteks sistem rekomendasi modern. Kata kunci: content-based filtering; hybrid filtering; neural collaborative filtering; rekomendasi film.

USER EXPERIENCE EVALUATION ON MUSIC STREAMING APPLICATIONS WITH UEQ METHOD

Angela, Angela, Halim, Fandi, Pramana, Tri Agung, Simanjuntak, Andolin
Abstract: Abstract: Along with the development of information technology, the way people listen to music also changed with the emergence of many music streaming applications. The user experience of an application plays an important… t role in attracting and retaining application users. Therefore, this study has goal to compare the music steaming applications’ user experience of the Joox and Spotify by using User Experience Questionnaire (UEQ) method. There are 6 scales assessed by UEQ, including attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty. Data was collected by distributing online questionnaires and obtained as many as 104 responses that could be processed. The results show that both applications have positive impressions which are indicated by the average value of each scale greater than 0.8. This indicates that these two applications are considered quite fun, effective, easy to understand, and innovative. However, the comparison’ results show that between Spotify and Joox is not significantly different, with Spotify scores slightly better than Joox.             Keywords: music streaming application; user experience; user experience questionnaire     Abstrak: Seiring dengan perkembangan teknologi informasi, cara masyarakat mendengarkan musik juga mengalami perubahan dengan munculnya banyak aplikasi streaming musik. User experience suatu aplikasi berperan penting untuk menarik dan mempertahankan pengguna aplikasi. Oleh karena itu, penelitian ini memiliki tujuan untuk membandingkan user experience dari aplikasi streaming musik Joox dan Spotify dengan metode User Experience Questionnaire (UEQ). Terdapat 6 skala yang dinilai oleh UEQ yaitu daya tarik, kejelasan, efisiensi, ketepatan, stimulasi, dan kebaruan. Data dikumpulkan melalui penyebaran kuesioner secara daring dan diperoleh sebanyak 104 jawaban yang bisa diolah. Hasil penelitian menunjukkan bahwa kedua aplikasi memiliki impresi positif yang ditandai dengan nilai rata-rata setiap skala lebih besar dari 0.8. Artinya kedua aplikasi ini dinilai cukup menyenangkan, efektif, mudah dipahami, dan inovatif. Meskipun demikian, hasil perbandingan menunjukkan bahwa perbedaan antara Spotify dan Joox tidak terlalu signifikan, dengan nilai Spotify sedikit lebih unggul daripada Joox.   Kata kunci: aplikasi streaming musik; pengalaman pengguna; user experience questionnaire  

Kebijakan Pendidikan Terhadap Dimensi Politik Pendidikan

Rianty, Devi Ade, Putra, Wiene Surya, Hidayat, Ricky
Abstract:  Politik dan kebijakan adalah dua hal penting dalam menjalankan roda pemerintahan tidak terkecuali dalam dunia pendidikan. Dua elemen ini bisa mempengaruhi pelaksanaan pendidikan Islam secara keseluruhan. Sejarah politik… k dan kebijakan pendidikan di Indonesia telah dimulai sejak awal kemerdekaan bangsa ini, bahkan pergulatan politik dan kebijakan tersebut sudah ada sejak prakemerdekaan. Perkembangan politik dan kebijakan dalam dunia pendidikan di Indonesia memiliki dinamika yang cukup menarik untuk diperhatikan pada setiap periodenya, mulai dari awal kemerdekaan sampai dengan dinamika politik dan kebijakan pendidikan yang terjadi hari ini. Pembuatan kebijakan di bidang pendidikan seringkali menjadi ajang perebutan pengaruh para elite politik. Akibatnya, politisasi pendidikan kadang menjadi tak terhindarkan. Di sisi lain, upaya untuk melakukan pengarus-utamaan (mainstreaming) kebijakan pendidikan sehingga dapat sejajar dengan kebijakan di bidang lainnya juga tidaklah mudah. Bagi dunia ketiga dan negara-negara berkembang, upaya tersebut tidak saja berhadapan dengan sistem politik dan budaya yang kurang mendukung dan problem ekonomi yang akut. Akibatnya, seringkali kebijakan pendidikan dikalahkan oleh kebijakan lain seperti di bidang pertahanan, keamanan dan ekonomi.

Fangirling Culture in X: a Virtual Ethnographic Study of Seventeen Boygroup Fans in Makassar City

Nabila Rahmayuni Saharuddin, Abdul Rahman
Abstract: This study explores the cultural practice of fangirling on social media platform X as a space for identity negotiation and communal solidarity in the digital era. Using a digital ethnography approach, data was collected… through participant observation, in-depth interviews with fans, and a documentary study of the digital footprints of the informants. The results show that fangirling is not merely a form of passive consumption, but rather a communal cultural activity carried out massively and organized through fictitious kinship structures in cyberspace. This phenomenon manifests itself in the form of digital "work culture," such as the ritual of collectively streaming music and mobilizing votes to increase the symbolic capital of the idol group SEVENTEEN on the global stage. This practice confirms a shift in social interaction patterns, where group loyalty is bound by a commitment to the idol's aesthetics and achievements. Anthropologically, this activity creates a new value system that blurs the boundaries between the private space of fans and the digital public space, while simultaneously strengthening the position of social media platform X as a primary locus in the formation of contemporary popular culture.

Pengaruh Live Streaming Dan Flash Sale Terhadap Keputusan Pembelian Pengguna Marketplace Shopee Di Wilayah Wadungasri Sidoarjo

Al Arofviyanti Divia Agustin Kleo Anggraini
Abstract: Penelitian ini bertujuan untuk mengkaji pengaruh live streaming dan flash sale terhadap keputusan pembelian konsumen di Shopee, khususnya di wilayah Wadungasri, Sidoarjo. Metode yang digunakan adalah penelitian kuantitatif… if dengan pendekatan purposive sampling dengan regresi linier berganda, yang di mana responden dipilih merupakan pengguna Shopee yang telah melakukan pembelian melalui fitur live streaming dan flash sale. Pengumpulan data dilakukan dengan menyebarkan kuesioner, kemudian dianalisis menggunakan regresi linear berganda guna memahami hubungan antara variabel independen terdiri dari live streaming dan flash sale dan variabel dependen (Keputusan Pembelian). Hasil analisis menunjukkan bahwa live streaming dan flash sale memiliki pengaruh positif dan signifikan terhadap keputusan pembelian konsumen di Shopee. Semakin menarik dan interaktif presentasi yang dilakukan oleh penjual dalam sesi live streaming, semakin besar kemungkinan konsumen untuk melakukan pembelian. Temuan ini memberikan wawasan bagi pelaku usaha untuk lebih mengoptimalkan fitur live streaming dan flash sale sebagai strategi pemasaran yang efektif dalam meningkatkan konversi penjualan.

Consumer Protection in Live Streaming-Based Commercial Transactions

Yanti Yulianti
Abstract: The rapid evolution of digital technologies, particularly live streaming features in e-commerce platforms, has significantly transformed consumer behavior while introducing new risks to consumer protection. Live streaming… g based commercial transactions often involve real time, visually driven interactions that encourage impulsive purchasing decisions, making traditional regulatory frameworks insufficient. This study aims to analyze the primary factors influencing consumer protection in live commerce settings by examining five core variables: product transparency, platform accountability, perceived risk, consumer trust, and digital literacy. Utilizing a qualitative exploratory approach, this research conducted a comprehensive literature review of 77 international journal articles published between 2020 and 2024. The findings indicate that product transparency and platform accountability are fundamental to enhancing consumer trust and reducing perceived risks, whereas digital literacy acts as a moderating factor that empowers consumers to make informed decisions. The study proposes a conceptual framework that integrates behavioral and regulatory dimensions, offering both theoretical insights and practical implications for improving consumer protection in fast paced, interactive digital marketplaces.

Strategi Komunikasi Pemasaran Radio Kardop 99.4 FM Medan Dalam Meningkatkan Minat Pemasang Iklan

Ineke Fadhillah, Anang Anas Azhar, Indira Fatra Deni
Abstract: Radio Kardopa merupakan salah satu radio yang masih eksis dalam dunia penyiaran di era digital seperti saat ini. Tujuan penelitian ini adalah mengetahui bagaimana strategi komunikasi pemasaran Radio Kardopa dalam meningkatkan… atkan minat pemasang iklan. Penelitian ini menggunakan mix marketing dan teori new media. Jenis penelitian, yaitu penelitian kulaitatif dengan pendekatan deskriptif. Sumber data berupa sumber data primer dan sekunder. Teknik pengumpulan data dilakukan dengan observasi secara langsung dalam pelaksanaan strategi komunikasi pemasaran. Hasil penelitian menunjukkan bahwa strategi komunikasi pemasaran radio kardopa dalam meningkatkan minat pemasang iklan adalah menggunakan media sosial seperti youtobe, live streaming, facebook, instagram dan tiktok, membuat program yang menarik, paket sponsor, proposal yang menarik dan tim solid. Faktor pendukungnya adalah Radio Kardopa memiliki prestasi pendengar terbanyak di Sumatera Utara dan tim yang solid. Sedangkan faktor penghambatnya adalah harga yang cukup mahal dan paket sponsor tidak sesuai dengan pemasang iklan. Solusinya adalah berusaha, berdoa, dan selalu konsisten berkomunikasi dengan klien-klien. Keberhasilan yang diraih yaitu meningkatkan billing iklan menjadi paling tinggi disbanding Radio lain di Sumatera Utara dan mendapatkan pemasang iklan.