Zoekresultaten

< Back Impressions of IBC 2025 15 Sept 2025 Ulysse’s Impressions of the International Broadcasting Convention 2025: Shaping The Future. Last Friday September 12, I visited IBC in Amsterdam, the world’s largest annual media and broadcasting conference, to present my new subtitling and translation software subtitle.ai at the EBU booth. Although being invited by Future Media Hubs as founder of Scribewave, I also wanted to share some reflections with the SRP Media audience. The first impression was sheer scale. With more than 116 000 m² (over sixteen football fields!), the RAI venue is almost unfathomable in size. Yet, despite the crowds, check-in was smooth, and within minutes I was wandering through one of the colossal halls. Exhibitors showcased everything from switch boxes and coax cables to cameras, rigs, and Media Asset Management (MAM) systems. Tech giants like Google, Nvidia, Amazon, and Microsoft dominated the floor, while I was glad to see a strong Belgian presence as well, with companies such as Mediagenix , Limecraft , and Cuez underlining the solid position of Belgium’s media technology ecosystem. As expected, Artificial Intelligence (AI) was the dominant theme, though a touch of “AI fatigue” was noticeable. Some exhibitors even highlighted their non-AI solutions as a differentiator. Still, AI was everywhere: from powering camera selection during sports broadcasts, to enabling multimodal media search, and supporting localization workflows. This naturally connects to my own pitch on AI-assisted subtitling. With subtitle.ai, I argued for a balance: maximizing automation while keeping editors firmly in control. Mine is not the only approach in this space: I noticed many competitors in the Future Tech Hall, each with their own take on the challenge of delivering professional, multi-language subtitles. The importance of subtitles is well documented, for example: Facebook found they increase viewing time by 25%, Verizon reported 80% higher completion rates, and Discovery discovered (sorry, bad pun) that subtitles increased overall views by 13%. Add to that the fact that 85% of social media videos are watched without sound, urging younger generations to default to using subtitles (or is it because of today’s often-mumbled dialogue in films and series?) and the case is clear. Subtitles don’t just boost engagement, they’re now a legal requirement too: since June 2025, the European Accessibility Act mandates closed captions for all content published in Europe. So how does subtitle.ai stand out? The software learns from your formatting guidelines (i.e. 42 CPL, two lines, natural breaks, speaker change indicators) to automate as much as possible, while still allowing editors to review and adjust quickly. Once finished, subtitles can be bulk-translated and auto-formatted into more than 90 languages. Because captions are generated at the word level, they can also be repurposed to create engaging social media highlights, with animated, colorful subtitles designed to capture attention. That was the core message of my pitch, delivered alongside a set of inspiring entrepreneurs and innovators in the media space: • Overtone: contextual intelligence for smarter brand placement in articles • Hypecast: a podcasting platform for internal business communication • SentiGeek: extracting usable insights from messy datasets • And last but not least: a live demo of an interactive audience feedback system from the founder of Pimp My Comedy I’m very grateful to VRT and Future Media Hubs for the opportunity to showcase my work, and thankful for the new connections with media professionals. While my first IBC experience was overwhelming in scale, it left me inspired and more enthusiastic than ever about the creative, inventive ways this industry is tackling its biggest challenges. Previous Next

Latest updates 15 Sept 2025 Impressions of IBC 2025 Ulysse’s Impressions of the International Broadcasting Convention 2025: Shaping The Future. Read More 21 Jul 2025 AI Summer School 2025 Aina's recap of the AI Summer School at KU Leuven Read More 15 Jul 2025 Report Published: How to Ensure Visibility and Prominence for Media Services of General Interest in Flanders Commissioned by the Flemish Minister of Media, this research report investigates findability, discoverability, and due prominence for audiovisual and auditive media services. Read More 5 Jun 2025 Ciao from EMMA in Rome! Our presentations at the emma Conference 2025 Read More 22 May 2025 Talking about Stakeholder Perspectives at WMEMC Hanne presented her research on stakeholder alignment for news recommender system development Read More 19 May 2025 Second Annual ALGEPI Workshop Insights on AI, Innovation and Media Regulation Read More 31 Mar 2025 Looking back at IUI 2025 Ulysse attended the conference and presented at the AXAI workshop Read More 27 Mar 2025 Policy Brief on Public Service Media in Belgium Findings and recommendations on the organisational and cultural challenges facing PSM in Belgium Read More 4 Feb 2025 #Etmaal2025 Hanne looking back on her presentation on Stakeholder Alignment for News Recommender System (NRS) Implementation Read More 3 Feb 2025 Call for Papers Special Issue Special Issue on Public Service Media in the Age of Platforms Read More 27 Jan 2025 New Policy Brief: Streaming Public Service Television in the Age of Platforms Evaluating Public Service Media (PSM) in-house video-on-demand (VoD) services Read More 4 Nov 2024 New policy brief: International versus local VOD In a new policy brief and webinar, we present the findings of research on motivations of Flemish viewers Read More 1 Nov 2024 New report of the Fair MusE project New report "From Value Networks for Recorded Music to Music Ecosystem" Read More 28 Oct 2024 Diversity in VOD services: Seminar highlights from Madrid Throwback on the international seminar on diversity and VOD services Read More 23 Oct 2024 Looking back at RecSys 2024 Sharing our reflections on the ACM RecSys Conference 2024 Read More 16 Oct 2024 New research network for VOD research methods A new website with all there is to know about Video-on-Demand (VoD) research methods Read More 8 Oct 2024 The RecSys Conference 2024 Our contributions to the 18th ACM Conference on Recommender Systems Read More 1 Oct 2024 Our presentations at ECREA The SRP team presented their work at the ECREA 2024 Conference Read More 1 Oct 2024 Webinar: Streaming in Vlaanderen Ontdek alle trends en inzichten in ons webinar! Read More 24 Sept 2024 Workshop: Best Practices for Responsible News Recommender Design Our takeaways from the workshop part of the NWO-funded project "Rethinking news algorithms" Read More

Unveiling groundbreaking research, innovative projects, and insights on Streaming, Recommender Systems, and Platformization (SRP) in European Media Markets. Streaming, Recommenders and Platformization in European Media Industries S trategic Research Programme at imec-SMIT, Vrije Universiteit Brussel SRP Media In our digital age, understanding the interplay between technology, society, and economics is crucial. Our research aims to analyze and ensure the economic and cultural sustainability of content production, aggregation, and consumption in an era of streaming, recommenders and platformization in European Media Industries. SRP Media is part of the Media Economics & Policy unit at imec-SMIT, Vrije Universiteit Brussel . Our research Latest news updates Impressions of IBC 2025 AI Summer School 2025 Report Published: How to Ensure Visibility and Prominence for Media Services of General Interest in Flanders Ciao from EMMA in Rome! Talking about Stakeholder Perspectives at WMEMC Second Annual ALGEPI Workshop Policy Brief on Public Service Media in Belgium Looking back at IUI 2025 More updates Contact us Pleinlaan 9, 1050 Brussels, Belgium Submit Thanks for your message!

< Back Interface real estate: Amazon Prime and visibility politics van Es, K., & Iordache, C. (2025). Interface real estate: Amazon Prime and visibility politics. Critical Studies in Television , 0 (0). https://doi.org/10.1177/17496020251375211 This paper investigates how Amazon Prime Video’s interface design affects content visibility, specifically analysing the prioritisation of Prime-included versus third-party content. Using the Vignette tool on French accounts, we conducted a mixed-methods analysis of homepage structures, including row hierarchies and title heatmaps across multiple user profiles. We find that while Prime Video shares common strategies with other services (e.g. own content prioritisation and burying the continue watching button), it distinguishes itself with a uniquely dense landing page layout featuring a large number of thumbnails and content rows. This design reveals deeper commercial logics shaped by Amazon’s integrated retail model. Previous Read the article Next

< Back Catching the waves: The case of VRT's digital-first audio strategy Van der Elst, P., Iordache, C., & Raats, T. (2025). Catching the waves: The case of VRT’s digital-first audio strategy. European Journal of Communication . https://doi.org/10.1177/02673231251370877 European public service media (PSM) are increasingly embracing strategies that balance digital platform tactics and meeting the public remit. This article addresses how a small market PSM is repositioning itself in a media landscape dominated by global platforms, streaming services and legacy media adopting platformisation strategies. We examine platformisation at the Flemish broadcaster VRT through the lens of its digital audio strategy. The study combines document analysis and expert interviews. Results show a strategic shift towards more focus on user needs and habits; a branding strategy revolving around the VRT parent brand; a necessary yet precarious presence on third-party platforms; a legacy-driven content offering complemented by online-only commissioning; and a firm editorial grip on content curation. VRT's take on these strategic innovations highlights a series of key dilemmas for PSM to reconcile public remit delivery and competitiveness in a platformised media landscape. Public Service Media Previous Read the article Next

< Back Towards a Future-Proof Public Service Media? 1 Feb 2024 New report from the PSM-AP project Towards a Future-Proof Public Service Media? Lessons from a comparative analysis in seven media markets Tim Raats, Catalina Iordache imec-SMIT, Vrije Universiteit Brussel Catherine Johnson University of Leeds www.psm-ap.com Public service media (PSM) all over the world have consistently been subject to different forms of societal and technological transition. However, recent years have brought a number of new challenges. These include radical changes in media use, the advent of streaming services and the dominance of big tech. Moreover, the increasing diversity and polarisation of societies have led to the erosion of trust in traditional media. These have challenged the legitimacy of public service media as an institution and project, but have also affected the broadcasters themselves, requiring them to transform into fully digital, online-first organisations. In this context, we present results from the research conducted during the first year of PSM-AP, a large-scale comparative research project analysing ‘Public Service Media in the Age of Platforms’. In this brief, we provide an overview of the dimensions of platformisation, and a series of core findings and discussions on PSM and platformisation, based on the analysis of media laws, broadcast contracts and licences, annual reports, and current policy debates in the following markets: Belgium (Flanders and Wallonia), Canada, Denmark, Italy, Poland, and the UK. Read the full policy brief here: https://smit.vub.ac.be/policy-brief-72-towards-a-future-proof-public-service-media-lessons-from-a-comparative-analysis-in-seven-media-markets Previous Next

< Back Wrap-up of the RecSys Summer School 16 Jun 2023 Our key takeaways from the Recommender Systems Summer School in Copenhagen From 12 to 16 June, several researchers from the Media Economics & Policy Unit took part in the Recommender Systems Summer School in Copenhagen. During this Summer School, academics and industry leaders lectured on the practice, research, and state of the art in recommender systems. The lectures covered a broad range of topics from an algorithmic as well as a methodological perspective, including hands-on sessions. This week brought many interesting insights for our strategic research program on recommender systems and this short report highlights some of the key takeaways. Not an algorithm, but a system Recommender systems encompass more than just the algorithm itself. They require the thoughtful implementation of (a combination of several) algorithms that align with specific domain objectives, account for optimal user experience in different contexts, and seek to create mutual value for various stakeholders It is crucial to recognize that there is no one-size-fits-all approach to recommender systems. The strategy employed must be tailored to the specific domain in which the system operates, considering the unique objectives, economic factors, values and challenges inherent to that domain. For instance, in the realm of news, evaluating the system's quality necessitates considerations such as diversity and serendipity, speed and coverage. The recommender system design must consider the overall user experience. This involves understanding the various features and styles influencing users’ interaction with the platform, as well as analyzing the user journey and recognizing the impact of contextual dependencies on their preferences and needs. In both academic literature and practical applications, the primary goal of recommendation systems is to create value. This entails a reciprocal relationship between user values and business values. By addressing user needs and providing quality personalized recommendations that go beyond mere accuracy the system increases short-term engagement. Furthermore, these systems aim to cultivate long-term loyalty and build strong relationships with the target audience. In summary, well-designed recommendation systems enhance user engagement by offering personalized recommendations, optimizing the user experience, reducing information overload, fostering serendipitous discovery, continuously learning and improving, integrating social features, and thereby generate added value for business through increased user satisfaction, retention, and potential revenue growth. End of the artificial clean cut between content? Media mergers are changing the industry. One of the many examples is how RTL XL will become a part of Videoland. The question rises how the video-on demand platforms can blend different content types such as movies, series, TV programs, short clips and livestreams in an appealing way. An answer to that question could be answered by formulating the optimal user experience through recommender systems. Currently, the company is analyzing user behaviour in order to develop models that can be used in online user experiments. A next step will be to start A-B testing to create the optimal recommendation model. The goal of VOD platforms is to have loyal visitors, but it is a metric that moves very slowly. Currently, the recommendation system of the RTL is built up on three different types of recommendations: content-based, popular within the genre and collaborative filtering. Interesting fact: Personalized swimming lanes compared to editorials swimming lanes generate 30 min more viewing time per active user per month. The main goal of “this recommender optimizing project” is to work towards continuous loops. Sequential recommender systems are different in that sense that they convert user’s behavior trajectory into recommended items or services. It takes into account the current and recent preferences of a user for a more accurate recommendations. Implementing this new form of recommender system will be one of the key factors to generate a user interface with “blended content” that answers the customer’s needs. A critical stance in the evaluation of recommenders Being grounded in dominantly quantitative forms of assessment, recommender system evaluation needs to pay sufficient attention to real-world significance of numerical results and to whether outcomes actually make sense in applied cases. For instance, is an overall increase in prediction accuracy of a recommendation an accomplishment when large parts of the user base still receive bad recommendations and their preferences remain ill-defined? A call for qualitative sense-making of quantitative evaluation outcomes was certainly made at the Summer School. Also, research papers that seek to evaluate recommender systems often focus more on (incremental) increases in performance percentages than on a solid basis for their actual evaluation. In terms of relevance for the academic field, consequently, little contributions are made. Papers that are characterised by vagueness and technical complexity thus prevent real progress and cannot form the basis for further research. The lack of valuable longitudinal research in the domain of recommender systems can also be related to this. Lastly, by acknowledging that recommender systems impact not only the intended end-user and that their complex nature implies influences also on those not directly involved, we argue that multiple-stakeholder considerations should be the norm. We realize that the inherent complexity of recommender systems makes this a difficult endeavour. But in our attempts to evade the McNamara fallacy and to research in the most holistic way possible, the aim should always be to keep a multi-stakeholder involvement top-of-mind. Not solely in phases of design or evaluation, but as a constant reflective thought from the outset and throughout. Previous Next

< Back Pieter Van der Elst PhD Researcher pieter.van.der.elst@vub.be Pieter Van der Elst joined imec-SMIT as a PhD candidate in 2023. Researching on the broader topic of algorithmic recommenders in the Flemish media industry, his thesis focuses on how the public service broadcaster VRT positions itself within a contemporary media context. His academic interests lie mainly in media economics and datafication of media. Before his start at imec-SMIT he briefly worked as a consultant for one of the leading social bureaus for artists (SBK’s) in the Flemish cultural industry, providing services exclusively to VRT. He obtained a Bachelor’s degree in Journalism and subsequently a Master’s degree in Communication Studies. Visit my research profile

< Back The RecSys Conference 2024 8 Oct 2024 Our contributions to the 18th ACM Conference on Recommender Systems From 14 until 18 October 2024, the 18th ACM Conference on Recommender Systems takes place in Bari, Italy. Our SRP Media researchers have various contributions to this conference, as well as the preceding ACM Europe School on Recommender Systems . ACM Europe School on Recommender Systems 2024 During the ACM Europe School on Recommender Systems, leaders in the field give lectures on the practice, research, and state of the art in Recommender Systems. This year, there will be 120 attendees among which 90 students. Click here for the full program . On Tuesday 8 Octobe r, Lien Michiels will teach a lecture on Best Practices for Offline Evaluation . On Friday 11 October, Annelien Smets lectures a course on Digital Economics and Recommender Systems . The ACM Europe School on Recommender Syste ms is organized by Ludovico Boratto (University of Cagliari, Italy) , Cataldo Musto (University of Bari, Italy) , and Fedelucio Narducci (Polytechnic University of Bari, Italy) . How to Evaluate Serendipity in Recommender Systems: the Need for a Serendiptionnaire GenUI(ne) CRS: UI Elements and Retrieval-Augmented Generation in Conversational Recommender Systems with LLMs [demo] It’s (not) all about that CTR: A Multi-Stakeholder Perspective on News Recommender Metrics Navigating Discoverability in the Digital Era: a Theoretical Framework Workshop on Normative Design and Evaluation of Recommender Systems (NORMalize) Previous Next

< Back LLMs and Recommenders Ulysse Maes PhD Researcher My four-year PhD program embarks on an insightful journey to explore the influence of foundational models, particularly Large Language Models (LLMs), on recommender interfaces. This research aims to bridge the gap between cutting-edge technology and user-centric design, focusing on how AI can enhance the user experience in recommender systems, thereby contributing to the rapidly evolving field of intelligent user interfaces, The first phase of my research delves into the transformative role of LLMs in shaping more interactive and engaging recommender user experiences. Here, I map out how these advanced models can redefine user interaction, making it more intuitive and appealing. Central to this phase is not only the exploration of the potential of LLMs but also a critical examination of the risks involved. Ensuring the ethical application of these technologies in real-world scenarios is a cornerstone of my study, as it balances innovation with responsibility. Shifting gears in the second phase, the research will pivot towards the creation and evaluation of user interfaces. This phase is dedicated to experimenting with novel layout and presentation patterns, rigorously assessing them both quantitatively and qualitatively. The goal is to uncover design strategies that align with the diverse objectives of various stakeholders in the recommender system domain. By intertwining state-of-the-art AI research with the underexplored realm of user interaction in recommender systems, my project aims to make significant contributions to the discourse on ethical AI applications. The insights gained are expected to fuel discussions around AI ethics in recommender systems and inspire professionals to adopt more user-friendly and effective design patterns. Ultimately, this research seeks to set a new benchmark in how we integrate generative AI technologies into user interfaces, ensuring they are not only advanced but also ethical and user-centric. Publications Not One News Recommender To Fit Them All: How Different Recommender Strategies Serve Various User Segments GenUI(ne) CRS: UI Elements and Retrieval-Augmented Generation in Conversational Recommender Systems with LLMs 08/10/2024 Supervisors Annelien Smets Research Professor Tim Raats Associate Professor Related news 2 Looking back at IUI 2025 Ulysse attended the conference and presented at the AXAI workshop 2 Looking back at RecSys 2024 Sharing our reflections on the ACM RecSys Conference 2024 2 The RecSys Conference 2024 Our contributions to the 18th ACM Conference on Recommender Systems Previous Next

< Back Valdy Wiratama Researcher valdy.wiratama@vub.be Growing up during the Web 2.0 era, the Internet left a favorable impression on my engagement with content. From dissecting events through discourses on Twitter to discovering new music on MySpace, the Internet enabled me to access a wider range of information and adjust my preferences at a reduced rate. While I can easily comprehend these effects as a media consumer, I can only imagine the ramifications on actors, musicians, and even print journalists. Lower barriers to entry amplify their competition, while the resulting oversupply threatens the exposure of smaller creators. With a current comprehension that requires more observations, my professional work is dedicated to understanding the supply side of the media industry and its relationship with the Internet. Particularly, I am invested in recorded music and its ever-evolving response towards platformization, online intermediaries, and the long tail hypothesis. As for the foundation that guides my outset in rationalizing phenomena, the baseline principle that I commonly work with is economics. I earned a Bachelor’s degree in economics from the University of Indonesia in 2018 and a Master of Arts degree (M.A.) in cultural economics and entrepreneurship from Erasmus University Rotterdam in 2022. To obtain the latter, I completed a thesis with the title ‘Backstage at the Pandemic: How the COVID-19 Pandemic Affected Music Production, Distribution, and Promotion among Unsigned Musicians in the United States.’ After defending the thesis, I joined an independent record label in The Netherlands before transitioning to a role that centers around fairness in the music industry (the FairMusE project) at imec-SMIT, VUB in 2023. Visit my research profile

< Back Public service algorithms: Balancing the scales between public mission and market pressures at the BBC and VRT. Iordache, C., Martin, D., & Johnson, C. (2025). Public service algorithms: Balancing the scales between public mission and market pressures at the BBC and VRT. MedieKultur: Journal of Media and Communication Research, 40(78), 59-80. https://doi.org/10.7146/mk.v40i78.147182 The public service media (PSM) shift to digital-first strategies has generated a rethinking of priorities in content production and distribution. This not only involves the integration of algorithms for the curation of their video-on-demand portals, but also a far-reaching reform at the organisational level. As personalisation through recommender systems is increasingly popularised by commercial streaming services, PSM are faced with a balancing act between market pressures and fulfilling their public mission. This article contributes to this discussion by investigating how public service algorithms are developed in practice in the cases of the BBC (UK) and VRT (Flanders-Belgium), and how their implementation is guided by the organisations’ remits. Through document analysis and semi-structured interviews conducted in 2024 with 16 PSM representatives, we discuss the ways in which market, policy, and organisational contexts inform the use of algorithms by the two organisations and suggest the need for a re-theorisation of public service algorithms. Public Service Media Previous Read the article Next