Real-Time Audience Sentiment Analytics for Adaptive and Personalized Media Broadcasting

Asep Sutarman; Fandi Ahmad; Royani Royani

doi:10.68012/beam.v2i1.194

Authors

Asep Sutarman University of Muhammadiyah Prof. Dr. Hamka Author https://orcid.org/0009-0002-1029-7963
Fandi Ahmad University of Sultan Ageng Tirtayasa Author https://orcid.org/0009-0001-4452-0505
Royani Royani University of Ichsan Satya Author https://orcid.org/0000-0002-3389-8107

DOI:

https://doi.org/10.68012/beam.v2i1.194

Keywords:

Audience Sentiment Analytics, Adaptive Broadcasting, Personalized Media, Real-Time Analytics

Abstract

Digital broadcasting platforms increasingly require mechanisms capable of understanding audience reactions while content is being delivered. However, conventional audience measurement relies primarily on delayed ratings, aggregate engagement statistics, or isolated textual sentiment analysis, limiting broadcasters’ ability to adapt content responsively. This study proposes a real-time audience sentiment analytics framework that integrates textual comments, interaction behavior, and temporal engagement signals to support adaptive and personalized media broadcasting. The proposed architecture combines a transformer-based text encoder, a behavioral feature network, temporal attention, and a contextual bandit adaptation engine. A prototype evaluation was conducted using public sentiment resources and a simulated broadcasting stream containing 120,000 audience events. The system classified audience sentiment into positive, neutral, and negative categories and translated aggregated sentiment into controlled broadcasting actions, including recommendation adjustment, segment continuation, notification timing, and presentation-style adaptation. Experimental results indicate that the multimodal model achieved an accuracy of 89.6% and a macro-F1 score of 88.9%, outperforming text-only and conventional machine-learning baselines. The prototype maintained an average end-to-end latency of 184 ms and processed approximately 1,420 events per second. In the simulated adaptive broadcasting experiment, sentiment-aware personalization improved click-through rate by 15.9%, average viewing duration by 12.8%, and audience satisfaction by 10.6% compared with static broadcasting. Fairness constraints, confidence thresholds, human editorial oversight, and privacy-preserving aggregation were incorporated to reduce the risks of emotional manipulation, bias, and unstable content adaptation. The findings demonstrate that real-time sentiment analytics can provide a technically effective foundation for responsive broadcasting when deployed as a decision-support mechanism rather than an autonomous editorial authority.

Downloads

Download data is not yet available.

References

[1] Y. Yusnaini, H. Nufus, R. Saleh, W. A. S. Wibowo et al., “The digital era and the evolution of media paradigms: A critical review of the adaptation of old media in new media ecosystems,” Society, vol. 13, no. 1, pp. 573–599, 2025.

[2] R. Okyere, C. A. Bautista Isaza, J. Pyon, I. F. Ogbonnaya-Ogburu, S. Niu, and S. W. Lee, “Watch me watch: Reaction videos as a social form of online video engagement,” Proceedings of the ACM on Human- Computer Interaction, vol. 10, no. 2, pp. 1–28, 2026.

[3] R. A. Sunarjo, T. Handra, R. N. Muti, and K. A. Al-Farouqi, “Artificial intelligence driven audience sentiment analytics for interactive digital broadcasting platforms,” Bridging of Emerging AI and Media Broadcasting (BEAM), vol. 1, no. 1 November, pp. 25–36, 2025.

[4] D. Abbas, A. Simanjuntak, and T. S. Goh, “Integrating broadcasting data mining and visualizationfor effective big data decision support,” Bridging of Emerging AI and Media Broadcasting (BEAM), vol. 1, no. 2 May, pp. 99–110, 2026.

[5] Badan Kebijakan Pembangunan Kesehatan Kementerian Kesehatan RI. (2026) Analisis media monitoring kemenkes ri 7–14 agustus 2026. [Online]. Available: https://www.badankebijakan.kemkes.go.id/12774-2/

[6] Humas KPI. (2026, Jul.) Kpi yang adaptif, bertransformasi dan strategis. Komisi Penyiaran Indonesia. [Online]. Available: https://kpi.go.id/news/kpi-yang-adaptif-bertransformasi-dan-strategis

[7] I. G. N. Parthama, “Characteristics of comments in social media,” e-Journal of Linguistics, vol. 19, no. 2, pp. 130–140, 2025.

[8] C. Wu, F. Wu, Y. Huang, and X. Xie, “Personalized news recommendation: Methods and challenges,” ACM Transactions on Information Systems, vol. 41, no. 1, pp. 1–50, 2023.

[9] O. A˘gırdil, “The mechanism of filter bubbles, algorithms, and perception management in security,” in Media Literacy and the Politics of Digital Misinformation. IGI Global Scientific Publishing, 2026, pp. 129–168.

[10] A. Nuche, R. Fahrudin, and R. Royani, “Human-centered generative ai for ethical andsustainable media broadcasting,” Bridging of Emerging AI and Media Broadcasting (BEAM), vol. 1, no. 2 May, pp. 110–125, 2026.

[11] R. Das and T. D. Singh, “Multimodal sentiment analysis: a survey of methods, trends, and challenges,” ACM Computing Surveys, vol. 55, no. 13s, pp. 1–38, 2023.

[12] C. Song, Y. Zhang, H. Gao, B. Yao, and P. Zhang, “Large language models for subjective language understanding: A survey,” arXiv preprint arXiv:2508.07959, 2025

[13] B. Ghojogh and A. Ghodsi, “Attention mechanism and transformers,” in Elements of deep learning. Springer, 2026, pp. 231–257.

[14] K. Alahmadi, S. Alharbi, J. Chen, and X. Wang, “Generalizing sentiment analysis: a review of progress, challenges, and emerging directions,” Social Network Analysis and Mining, vol. 15, no. 1, p. 45, 2025.

[15] S. Zhang, Q. Dong, M. A. I. Yasin, and N. C. Fang, “Algorithms for moderating effect of emotional value from a cross-media data fusion perspective: A case study of chinese dating reality shows,” Journal of Multiscale Modelling, vol. 17, no. 02, p. 2640012, 2026.

[16] K. Zhao, M. Zheng, Q. Li, and J. Liu, “Multimodal sentiment analysis—a comprehensive survey from a fusion methods perspective,” IEEE Access, vol. 13, pp. 64 556–64 583, 2025.

[17] Z. Wu, Y. Xie, B. Zhao, J. He, F. Luo, N. Deng, and Z. Yu, “Cardiacmamba: A multimodal rgb- rf fusion framework with state space models for remote physiological measurement,” arXiv preprint arXiv:2502.13624, 2025.

[18] T.-T.-T. Do, Q.-T. Huynh, K. Kim, and V.-Q. Nguyen, “A survey on video big data analytics: architecture, technologies, and open research challenges,” Applied Sciences, vol. 15, no. 14, p. 8089, 2025.

[19] A. Vajpayee, R. Mohan, and V. V. R. Chilukoori, “Building scalable data architectures for machine learn- ing,” International Journal of Computer Engineering and Technology (IJCET), vol. 15, no. 4, pp. 308– 320, 2024.

[20] A. Bentaleb, M. Lim, M. N. Akcay, A. C. Begen, S. Hammoudi, and R. Zimmermann, “Toward one- second latency: Evolution of live media streaming,” IEEE Communications Surveys & Tutorials, 2025.

[21] D. M. Rothschild, J. Marla, A. Amaya, S. Barari, T. Buskirk, C. Cobb, J. Gennai, S. Hillygus, R. K. Vinayak, M. Krupenkin et al., “Responsible ai integration in survey research,” 2026.

[22] J. R. Saura, V. Ratten, and V. Jeremic, “Digital cognition in predictive marketing personalization: A conceptual framework,” Psychology & Marketing, vol. 43, no. 5, pp. 1228–1260, 2026.

[23] L. Wu, Z. Zheng, Z. Qiu, H. Wang, H. Gu, T. Shen, C. Qin, C. Zhu, H. Zhu, Q. Liu et al., “A survey on large language models for recommendation,” World Wide Web, vol. 27, no. 5, p. 60, 2024.

[24] S. Qassimi and S. Rakrak, “Multi-objective contextual bandits in recommendation systems for smart tourism,” Scientific Reports, vol. 15, no. 1, p. 13669, 2025.

[25] S. Hu, H. Wang, Y. Zhang, P. Wang, and Z. Lu, “Danmodcap: Designing a danmaku moderation tool for video-sharing platforms that leverages impact captions with large language models,” Proceedings of the ACM on Human-Computer Interaction, vol. 9, no. 2, pp. 1–27, 2025.

[26] D. V. Voinea, “Governing adaptive news curation: Sequential optimization, cumulative exposure alloca- tion, and societal accountability,” Social Sciences, vol. 15, no. 8, p. 496, 2026.

[27] W. Maalej, V. Biryuk, J. Wei, and F. Panse, “On the automated processing of user feedback,” in Handbook on natural language processing for requirements engineering. Springer, 2025, pp. 279–308.

[28] M. A. Almekhlafi, F. Alrowais, S. Alshahrani, M. Maray, M. A. AlAqil, M. A. Alharbi, A. E. Yahya, and R. Marzouk, “Amta: An innovative privacy-aware adaptive transformer for real-time multimodal data fusion,” Transactions on Emerging Telecommunications Technologies, vol. 37, no. 3, p. e70365, 2026.

[29] A. R. W. Sait and Y. Alkhurayyif, “Hallucination-aware interpretable sentiment analysis model: A grounded approach to reliable social media content classification,” Electronics, vol. 15, no. 2, p. 409, 2026.

[30] H. Henry, K. Lutfiyah, H. Agustian, and N. Lachlan, “Assessing the environmental and economic impact of smart grid integration in renewable energy management,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 7, no. 1, pp. 38–50, 2025.

[31] R. Hardjosubroto, U. Rahardja, N. A. Santoso, and W. Yestina, “Penggalangan dana digital untuk yayasan disabilitas melalui produk umkm di era 4.0,” ADI Pengabdian Kepada Masyarakat, vol. 1, no. 1, pp. 1–13, 2020.

[32] R. R. M. de Souza, “Legal remedies and regulatory frameworks to combat ai-driven deepfakes,” in Miti- gating the Risks of AI Deepfakes. CRC Press, 2026, pp. 94–116.

[33] N. Heluey, “Ethical ai governance, trust and deepfake regulation in the uae’s media landscape,” Journal of Digital Media & Policy, vol. 16, no. 2, pp. 195–218, 2025.

[34] X. He and L. Fang, “Regulatory challenges in synthetic media governance: Policy frameworks for ai- generated content across image, video, and social platforms,” Journal of Robotic Process Automation, AI Integration, and Workflow Optimization, vol. 9, no. 12, pp. 36–54, 2024.

[35] J. Mathew and A. Narayanan, “Reimagining truth: The role of ai-generated content in shaping media ethics and audience trust in a post-truth era,” Communication Research, vol. 2, no. 1, pp. 72–82, 2025.

[36] A. Sharma and R. Sharma, “Generative artificial intelligence and legal frameworks: Identifying challenges and proposing regulatory reforms,” Kutafin Law Review, vol. 11, no. 3, pp. 415–451, 2024.

[37] M. Krki´c, “Cultural perspectives on ai usage and regulation in deepfake creation: How culture shapes ai practices,” International Communication of Chinese Culture, vol. 12, no. 2, pp. 225–237, 2025.

[38] R. Fiasal, “Ai in media careers: Ethical and legal challenges and strategies for adaptation.” Journal of Public Relations Research Middle East/Magallat Bhut Al-Laqat Al-Amh-Al-Srq Al-Aust, no. 59, 2025.

[39] V. Ranaware and S. Karale, “Navigating legal and ethical challenges in artificial intelligence: towards responsible governance and innovation in india,” International Journal of System Assurance Engineering and Management, pp. 1–15, 2026.

[40] M. A. Shawky, D. Awasthi, A. A. Ramadan, S. Zarif, J. Ahmad, and S. T. Shah, “Secured ai-based multimedia communication,” in Multimedia and Multimodal Intelligence for Sustainable Development. CRC Press, 2026, pp. 23–46.

[41] P. Carpenter, FAIK: A practical guide to living in a world of deepfakes, disinformation, and AI-generated deceptions. John Wiley & Sons, 2024.

[42] P. B. Seel, Digital universe: The global telecommunication revolution. John Wiley & Sons, 2022.

[43] R. von Marttens and J. Alcaniz, “Dark energy and cosmic acceleration,” arXiv preprint arXiv:2502.00923, 2025.

[44] M. Zreik, B. A. Iqbal, M. Hassan, and S. Z. Syed Marzuki, “Infrastructure development, inequality, and employment in sub-saharan africa from the professional perspectives of kenya, ghana, and tanzania,” Discover Global Society, vol. 2, no. 1, p. 78, 2024.

[45] R. Chugh, “The sustainability paradox: rethinking digital technologies in education for a sustainable future,” Humanities and Social Sciences Communications, vol. 13, no. 1, p. 275, 2026.

[46] T. Kingsford, “A novel conceptual framework for real-world reinforcement learning with applications to social robotics and beyond,” Ph.D. dissertation, University of Auckland, 2022.

[47] M. Novello and J. D. Toniato, “An overview of field theories of gravity,” arXiv preprint arXiv:2402.16163, 2024.

[48] Y. Hu, J. Zhang, Z. Wang, and C. Yu, “Plotania: Exploring transparency trade-offs in ai co-writing through virtual readers and transparent attribution,” in Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, 2026, pp. 1–23.

[49] E. T. Akande, K. Wlliams, and A. Akande, “Between me and we: Navigating individualism and collec- tivism in a world on edge,” in Culture, Leadership, and Organizations. Elsevier, 2026, pp. 393–408.