3rd Workshop on Recommendation Systems for Television and online Video (RecSysTV 2016)
The 3rd Workshop on Recommendation Systems for Television and Online Video will be held in conjunction with the 10th ACM Conference on Recommender Systems (15h-19th September 2016) in Boston, MA, USA.
For many households the television is still the central entertainment hub in their home, and the average TV viewer spends about half of their leisure time in front of a TV (3-5 hours/day). The choice of what to watch becomes more overwhelming though because the entertainment options are scattered across various channels, such as on-demand video, digital recorders and the traditional linear TV. Recommendation systems provide TV users with suggestions about both online video-on-demand and broadcast content and help them to search and browse intelligently for content that is relevant to them.
While many open questions in video-on-demand recommendations have already been solved, recommendation systems for broadcast content (e.g., linear channels and catch-up TV) still experience a number of unique challenges due to the peculiarity of such domain. The RecSysTV 2016 workshop aims to provide a dedicated venue for papers covering all aspects of this recommendation problem.
For the news and information about previous workshops, please go here:
9:00 – 9:10: Opening Introduction
9:10 – 09:45: Time series effects for TV recommendations @ IPTV Verizon – Diana Hu (Verizon) [Slides]
Abstract: Recommendations for the television platform behave quite differently than the ones for video on demand platforms. A key difference is the dependency on television schedule and shows’ seasonality. In this talk, we will explore the time series effects that can be observed in the shows cyclicality, and more interestingly the effects of this cyclicality on users’ behavior. We’ll also go over some approaches to incorporate the time component onto different kinds of recommendations at Verizon IPTV
9:45 – 10:30: Balancing Discovery and Continuation in Recommendations – Hossein Taghavi (Netflix) [Slides]
Our objective for the Netflix recommendation engine is to create a personalized experience for our members, making it easier for them to find a video to watch and enjoy. When a member logs on to the service, she/he may be in one or a combination of different watching modes: discovering a new content to watch, continuing to watch a partially-watched movie or a TV show she/he has been binging on, playing one of the contents she/he had put in her play list during an earlier session, etc. If, for example, we can reasonably predict when a member is more likely to be in the continuation mode, and which videos she/he is more likely to resume, it makes sense to place those videos in more prominent places of the home page. In this talk we focus on understanding the discovery vs. continuation behavior and explain how we have used machine learning to improve the member experience by learning a personalized balance between those two modes. As a case study, we focus on a recent change on the personalization of a row of recommendations called “Continue Watching,” which appears on the main page of the Netflix member homepage on the website and the app and currently drives a significant proportion of member streaming hours.
10:30 – 11:00: Morning Coffee Break
11:00 – 11:45: Deep Collaborative Filtering for Video Recommendations – Tomi Poutanen (Layer 6 AI) [Slides]
We introduce a novel approach to collaborative filtering using deep learning. Our approach retains the practical performance benefits of latent factor models, but unlike typical low-rank factorization we derive the latent factors using deep learning methods on a unified neural network architecture. The benefits of this approach are that (1) we can incorporate additional user and item content attributes of any type in a principled way; (2) we can flexibly extend the network to incorporate deep learning based feature extractors which have recently been shown to be superior to other methods; and (3) we simplify training by optimizing for a single objective that aims to maximize the recommendation accuracy. We have found our approach to outperform state-of- the-art methods in terms of accuracy and in its ability to address the cold-start problem inherent to new users and new items.
11:45 – 12:30: Creating engaging content in the news room – Steven Bourke (Schibsted)
With more than 150 years in the media industry Schibsted is one of Europe’s oldest media organizations in operation today. In the last 20 years Schibsted has evolved to become a predominantly digital operation. In doing so they have gained extensive reach in Norway and Sweden with their Media house operations and worldwide success with their online marketplaces and growth initiatives. Today Schibsted has more than 200 million users globally engaging using their online services. This talk will focus on the evolution of the tooling used by journalists and editorial staff to create textual and video based content for their readers. This will cover how to include editorial judgements in the ordering of content, performance feedback to content creators and how commoditized algorithmic solutions can be used to surface interesting and relevant content.
12:30 – 14:00: Lunch
14:00 – 14:45: How to generate accurate meta-data for content-based recommendations – Faisal Ishtiaq (Watchwith)
Nowadays, Cable TV operators provide their users multiple ways to watch TV content, such as Live TV and Video on Demand (VOD) services. In the last years, Catch-up TV has been introduced, allowing users to watch recent broadcast content whenever they want to. Understanding how the users interact with such services is important to develop solutions that may increase user satisfaction, user engagement and user consumption. In this paper, we characterize, for the first time, how users interact with a large European Cable TV operator that provides Live TV, Catch-up TV and VOD services. We analyzed many characteristics, such as the service usage, user engagement, program type, program genres and time periods. This characterization will help us to have a deeper understanding on how users interact with these different services, that may be used to enhance the recommendation systems of Cable TV providers.
Recommendation systems are being explored by Cable TV operators to improve user satisfaction with services, such as Live TV and Video on Demand (VOD) services. More recently, Catch-up TV has been introduced, allowing users to watch recent broadcast content whenever they want to. These services give users a large set of options from which they can choose from, creating an information overflow problem. Thus, recommendation systems arise as essential tools to solve this problem by helping users in their selection, which increases not only user satisfaction but also user engagement and content consumption.
In this paper we present a learning to rank approach that uses contextual information and implicit feedback to improve recommendation systems for a Cable TV operator that provides Live and Catch-up TV services. We compare our approach with existing state-of-the-art algorithms and show that our approach is superior in accuracy, while maintaining high scores of diversity and serendipity.
15:30 – 16:00: Afternoon Coffee Break
16:00 – 16:50: Panel Session – Future Research Directions for TV and Video Recommendations – Moderator: Navdeep Martin (Comcast)
16:50 – 17:00: Wrap up
Call for Contributions
We would encourage participation along several themes which include but are not limited to:
- Context-aware TV and online video recommendations
- Leveraging contextual viewing behaviour, e.g. device specific recommendations
- Mood based recommendations
- Group recommendations
- User modeling & leveraging user viewing and interaction behavior
- How can social media improve TV recommendations
- Cross-domain recommendation algorithms (linear TV, video on demand, DVR, gaming consoles)
- Multi-viewer profile separation
- Evaluation metrics for TV and online video recommendations
- Content-based TV and online video recommendations
- Analysis techniques for video recommendations based on video, audio, or closed caption signals
- Utilization of external data sources (movie reviews, ratings, plot summaries) for recommendations
- Other topics related to TV and online video recommendations
- Video playlisting
- Linear TV usage and box office success prediction
- Catch-up TV recommendations
- Personalized advertisement recommendations
- Recommendations of 2nd screen web content
- Recommendations of short form videos (previews, trailers, music videos)
We will welcome works that utilizes consumption data of real TV users, with a particular consideration for those releasing the used data set to grant the reproducibility of results and the usage by other researchers.
Jan Neumann, Comcast Labs, Washington, DC (email@example.com)
John Hannon, Zalando SE (firstname.lastname@example.org)
Claudio Riefolo, ContentWise, Milan, Italy (email@example.com)
Hassan Sayyadi, Comcast Labs, Washington, DC (firstname.lastname@example.org)
Submission deadline: July 1st, 2016 (Extended)
Notification to authors: July 15, 2016
Workshop date: September 15, 2016 (full day)
Hidasi Balazs, GravityR&D
Justin Basilico, Netflix
Craig Carmichael, Rovi
Emanuele Coviello, Keevio
Humberto Corona, Zalando
Paolo Cremonesi, Politecnico di Milano
Joaquin Delgado, OnCue TV (Verizon)
Diana Hu, OnCue TV (Verizon)
Brendan Kitts, Adapt.TV (AOL)
Gert Lanckriet, UC San Diego
Rani Nelken, Outbrain
Royi Ronen, Microsoft
Barry Smyth, Insight Centre for Data Analytics
Esti Widder, Viaccess-Orca
David Zibriczky, ImpressTv